Water and Soil Management and Modeling
Year:2024 | Volume:4 | Issue:2|Papers Count:20

Introduction The agriculture sector, as the biggest consumer of water to produce more food, has faced the challenge of water shortage. One of the problems ahead in the agricultural industry is the sustainable use of available resources such as land, water, and labor to increase agricultural production and development, which requires proper planning and management policies. Plant models can be used to investigate the long-term effects of quantitative and qualitative changes in irrigation water on crops, soil salinity, evaporation and transpiration, deep infiltration, and surface runoff. One of the widely used plant models is the AquaCrop model, which was presented and developed by the World Food and Agriculture Organization. The Aquacrop model is one of the crop yield estimation models that can be used for a wide range of crops including fodder crops, vegetables, grains, fruits, oil crops, and tubers. In this model, the state of various stresses including water and soil salinity, simulation of lack of irrigation, and crop yield are considered. Various studies have been conducted regarding the calibration and validation of crop forecasting models in our country, and much research has been conducted on wheat at the global level. In this research, the AquaCrop model was used to predict the biomass and grain yield of wheat in Qazvin. This model can be a good substitute for field measurements and can be used in areas where there is a lack of ground information.   Materials and Methods In the present research, the data of water wheat cultivation in a lysimeter in Ismailabad, Qazvin were used. The input information of the AquaCrop model includes information on climate, soil, management, and plant characteristics. To calibrate and verify the model, some farm information was needed to be compared with the output of the AquaCrop model. The biomass of the wheat plant was determined by taking random samples of the 0.5×0.5 m2 with two replications per sampling hectare. To measure grain yield in the fields, four samples were taken at the end of the growing season at the end stage. The validated AquaCrop model was used to estimate the effect of three planting dates and three low irrigation conditions on wheat grain yield. In this step, the average regional information around the farms was used so that the implementation of the model is not unique to the conditions of a particular farm.   Results and Discussion In terms of the investigated meteorological factors, the model has moderate sensitivity to maximum and minimum temperature and low sensitivity to rainfall. The change in the maximum temperature in this region increases the error of the simulation on average. Regarding the soil parameters, the sensitivity of the model to the crop capacity moisture, wilting point, saturated moisture, and saturated hydraulic conductivity, especially in saturated conditions, is low to medium. The most sensitive of the AquaCrop model was the change in the reference harvest index. The model simulated biomass values with higher accuracy than yield. In the calibration stage, the values CRM, NRMSE, and d for biomass were -0.15, 0.17, and 92% respectively. These values were obtained in the validation stage for biomass -0.1, 0.24, and 92 % respectively, and for yield -0.03, 0.06, and 80 % respectively. By running the model in different climatic scenarios, it was determined that the maximum delay in the planting date is on November 15. A 25% reduction in irrigation water reduced grain yield in wet, normal, and dry years by 15%, 20%, and 28 %, respectively, and a 50 % reduction in irrigation water reduced its amount by 20, 25, and 45 %, respectively.   Conclusion Evaluation of the AquaCrop model for common plants in a region plays an important role in comparing crop performance in different conditions. In this research, the ability of AquaCrop 6 model to estimate the yield and biomass of wheat in Ismailabad Qazvin was investigated. The results showed that the model is capable of simulating these factors with high accuracy. The accuracy of the model in biomass simulation was higher than the grain yield. By implementing the calibrated model in different climatic scenarios, planting dates, and irrigation deficits in two regions, it was determined that to achieve optimal performance, the wheat planting date should not exceed 15 November. It was the use of calibration coefficients by spending a long time in the AquaCrop model so that a calibrated model can be used in many areas with proper accuracy. More accuracy in the simulated results can be achieved by using more calibration factors, but it is clear that the use of more calibration factors requires spending more time and money. Finding a general recalibrated model that can be used in large areas is a good solution in crop management at the farm-to-regional scale. Comparing the statistical parameters obtained in this study with previous studies on wheat yield modeling by the AquaCrop model shows that the results of this study are within an acceptable range.

Introduction In many regions, ecosystem sustainability and environmental security have become more fragile. Because watersheds are dynamic systems, their hydrological function and health are constantly changing under the influence of land use, climate change, and human interventions. Since the destruction of the ecosystems of a watershed has harmful economic and social consequences, in recent decades there has been a general tendency to evaluate the relative conditions or health of watersheds on a national and local scale. Ecologists have paid special attention to the study of how natural resource ecosystems respond to different types of stress caused by human activities. The watershed sustainability index (WSI) can be considered as an effective tool in watershed management including priorities monitoring changes and influencing factors on ecosystem management. In recent years, various studies and plans have been conducted to preserve natural resources and achieve sustainable development. The sustainability of watersheds includes four important goals of regulating the water flow regime, maintaining and improving water quality, maintaining the ecological quality of plants and animals, and energy resources. In this context, the pressure-state-response (PSR) model has been introduced and used for a comprehensive assessment of the health of an ecosystem. The conceptual model of PSR was developed using a set of criteria expressing environmental performance. This study aimed to evaluate the sustainability level of the Bujin watershed.   Materials and methods One of the methods for evaluating watershed sustainability is the use of the conceptual pressure-state-response model (PSR). Applying the causal-effect PSR model using theWSI criteria in the form of four sub-criteria of hydrology (qualitative and quantitative), environment, life, and policy-making, one can evaluate the sustainability of the watershed numerically. In this method, considering the available data and information to investigate each sub-criteria, the parameter values are determined in three modes of pressure, state, and response, and in the scoring range from zero to one, five categories are converted to quantitative mode. Therefore, the PSR framework has three types of criteria: pressure criteria that evaluate environmental pressure resulting from human activities (waste, sewage), and state criteria that express environmental conditions (water quality). and the response criteria that evaluate the society's reactions (water quality) and the response criteria that evaluate the society's responses (policies, laws, management). The sub-criteria and parameters used in this research were determined based on the index selection criteria published by the HCTF Habitat Protection Fund in 2003. Sub-criteria were investigated based on three conceptual model parameters in 10 years for the Bujin watershed. The WSI criteria were calculated at three low, medium, and high levels to assess the watershed sustainability.   Results and Discussion According to the results, the value of the pressure parameter and the quantitative status of the basin's hydrology in terms of available water variable is in class (C), i.e. in the range of 3400 > AW > 1700, which is a poor condition. The average scores were obtained for the water quality part (0.583), which shows the average to low status. The average score for the hydrology sub-criterion was 0.375, which indicates a poor situation in this region. The values of pressure, state, and response parameters for the sub-criterion of life in the Bujin watershed, during the 10 years studied, indicate a change in the state from weak to moderate. The results also showed that the pressure parameter with a score of 0.75 and the response parameter with a score of 0.625 had the highest and lowest scores for evaluating the sustainability of the Bujin watershed, respectively, indicating an appropriate response to reduce the pressure applied to the ecosystems. Sub-hydrology index with a score of 0.16 and environment with a score of 1 had the lowest and highest priority for the management of the basin ecosystem. According to the distribution maps of the criterion for evaluating watershed sustainability in conventional watershed systems during the period (2006-2016), the standard level of watershed sustainability at the beginning of the period was lower than the middle class (score 0.59) and in the middle of the period was in the middle class (score 0.62) and for the end of the period, it was upgraded to the upper than the middle class (score 0.7).   Conclusion The priorities of achieving sustainable development (the priority in improving the conditions to promote the level of sustainability and achieve sustainable development) are different, and it is important to know which sub-criterion should be improved first and which parameter the decision-makers should pay attention to avoid wasting time, money and energy, and to take faster development steps in an area. Evaluation of relative conditions of watershed sustainability using the PSR model is very useful for providing appropriate management strategies because according to the nature of the conceptual model, a specific dimension of watershed health is explained. Bujin watershed has an unstable condition in the sub-index of hydrology and a good condition in the sub-index of life and human development, although, for this watershed, obtaining a score of 0.7 for WSI criteria in the whole watershed showed that the level of watershed sustainability in the 10 years is in the middle class and it is necessary to pay more attention to improve the level of sustainability and health of the watershed.

Introduction Landfill leachate, a liquid resulting from waste decomposition, contains nutrients like ammoniacal-N, Na, K, and organic matter. Biological treatments effectively remove degradable organics from young landfill leachate, but aged leachate with recalcitrant organics requires combined physical-chemical and biological methods or advanced technologies, leading to higher treatment costs. Even after treatment, leachate may not meet environmental standards for release. In arid and semi-arid regions with water scarcity and low soil organic matter, leachate application to soil presents a potential solution. Soil’s properties enable it to retain and degrade pollutants while utilizing leachate’s nutrients to enhance fertility and crop growth. However, leachate composition and application rates are critical factors due to potential negative impacts from total nitrogen, salinity, and heavy metals. Alkaline pH in aged leachate reduces heavy metal contamination risk. Detailed leachate characterization before soil application is crucial to prevent environmental and functional problems. This review examines existing research on leachate irrigation’s effects on soil properties and plant nutrition, contributing to sustainable leachate management and agricultural practices in water-limited regions. Additionally, the review explores potential risks associated with leachate irrigation, including soil salinization, heavy metal accumulation, and groundwater contamination. By understanding both the benefits and drawbacks, informed decisions can be made regarding the suitability and implementation of leachate irrigation in specific contexts.   Materials and Methods To carry out this study, keywords such as "Landfill leachate", "Composition of landfill leachate" and "Landfill leachate irrigation" were searched in the Web of Science, Google Scholar, ScienceDirect, and SID databases. For these keywords, 205 articles were found from 1989 to 2023. After the screening, quality review, and removal of repetitive and unrelated articles, 110 relevant articles were used. The main criterion for selecting articles was the effects of landfill leachate irrigation on the various properties of soil, and the nutrition of different plant species. The quality of the articles was evaluated through the Scimago Journal Rank (SJR) index, the citation, the Impact Factor, and the source normalized impact per paper (SNIP) index.   Results and Discussion Landfill leachate presents a complex environmental challenge due to its potential for both soil contamination and enrichment. Leachate's xenobiotic and heavy metal components can induce soil contamination, altering the natural environment. Studies have documented reduced hydraulic conductivity, increased gas production, and altered microbial communities, ultimately impacting soil productivity.  Leachate percolation can also modify physicochemical characteristics, including reduced microbial biomass, phosphorus-fixing capacity, and pH shifts, depending on waste composition. Conversely, research highlights the potential benefits of leachate application in arid and semi-arid regions facing water scarcity and low soil organic matter. Leachate can contribute to the increased organic content, improved soil structure, and regulated pH, enhancing soil fertility and crop productivity.  The presence of macro and micro-nutrients such as Fe, Mn, N, P, and Zn further supports leachate's potential as a fertilizer. However, concerns remain regarding inhibitory chemicals in leachate and their potential detrimental effects on plant growth and yield. Studies report instances of leaf injury, reduced yield, and poor survival rates in certain plant species.  In contrast, research demonstrates the positive effects of diluted or low-strength leachate application, stimulating plant growth and enhancing yield, particularly for Brassica species and tree species like Acacia confusa, Leucaena leptocephali, and Eucalyptus tortellini. These contradictory findings underscore the intricate interplay of factors influencing leachate irrigation outcomes. Soil characteristics, plant species, leachate source and composition, application methods, and their interactions all play significant roles in determining the success or failure of leachate irrigation. Conclusion Landfill leachate, characterized by its elevated nitrogen and nutrient levels, presents a potential alternative water and fertilizer source for agricultural practices, particularly in arid and semi-arid regions facing water scarcity. However, responsible leachate utilization necessitates a comprehensive approach that balances maximizing benefits with minimizing environmental risks. Prior to agricultural application, detailed leachate characterization is crucial to determine its precise composition and suitability for irrigation. This includes quantifying heavy metal concentrations, salinity levels, and the presence of potentially toxic organic compounds.  Concurrent plant selection is equally important, prioritizing species with demonstrated tolerance to leachate constituents. Given the potential for salinity and heavy metal accumulation, continuous application of raw leachate, especially for sensitive crops, should be avoided. Implementing alternating irrigation regimes with conventional water sources can mitigate these risks while providing essential nutrients for plant growth.  Monitoring soil health indicators, including pH, organic matter content, and microbial activity, is vital to assess long-term impacts and implement necessary soil amendments. Determining optimal leachate application rates requires a multifaceted approach that considers plant-specific nitrogen requirements, leachate toxicity levels, and soil infiltration capacity.  This ensures adequate nutrient supply without exceeding the assimilative capacity of plants and soil, preventing environmental contamination. Further research is needed to investigate the long-term impacts of leachate irrigation on soil health, crop quality, and potential groundwater contamination. Developing standardized guidelines for leachate treatment and application, tailored to specific regional contexts and crop types, is crucial for promoting sustainable and responsible leachate utilization in agriculture.

Introduction Irrigation decision support systems (IDSS) are among the approaches considered a tool in complex decision-making for water resource managers due to the enormous development of computer systems. Modernizing at different levels of water consumption can significantly increase water productivity indicators. Performing these conditions requires technological changes. The primary pillar of any IDSS system is its ability to adapt to environmental changes. This process allows the prediction model to compare predicted values with actual results and adjust automatically. IDSS systems for designing cropping patterns and optimal irrigation programs have the critical capabilities to control and manage optimal irrigation on large levels and water rights. These systems suggest the optimal cultivation pattern and dynamically provide the water consumption optimization schedule. According to previous studies, the most critical challenge of irrigation management is the limited amount of available water, which leads to the complexity of the optimal use of agricultural water in real conditions. One of the most important strategies to save Lake Urmia is to take necessary measures to reduce water consumption in the agricultural sector. One of the primary solutions to reduce water consumption in the agriculture sector is to decrease the loss of valuable and non-useful uses of agricultural water through the improvement of irrigation management. For this purpose, in the present study, the details of the adaptability of a developed IDSS system to improve irrigation management with the conditions of irrigation and drainage network, water and soil resources, climate, and vegetation in Mahabad Plain have been discussed. Materials and Methods To evaluate the IDSS, the downstream farms of the Mahabad irrigation and drainage network located southeast of Lake Urmia were selected. The Mahabad irrigation and drainage network consists of a diversion dam, two main canals, 11 2nd-grade canals, 69 main drains, and 10 water pumping stations. Four sites from the Mahabad irrigation and drainage network were chosen as selected sites. In each site, 20 farms were considered for monitoring the IDSS. The rest of the farms were under the control of the farmer, and only optimal irrigation programs were provided to the farmer by the IDSS. The general framework of the IDSS has been developed to achieve the goal of optimal management of water consumption in agriculture, taking into account the time and amount of water availability using international methods. The IDSS provides the optimal irrigation schedule for the cropping pattern in the farm by using online information on agricultural meteorology, water access conditions of the farm, soil, and crop characteristics, and the type of irrigation system used in the farm. The IDSS can suggest the optimal cropping pattern for farm conditions. During the crop growth period, the farmer can introduce farm events as feedback to the system. In this situation, IDSS simulates new scenarios according to the existing situation in the farm and represents the new optimal irrigation schedule for the next few days. Results and Discussion To adapt the IDSS for irrigation planning the physicochemical characteristics of soil and water, water right,  soil texture, crop characteristics, and etc. were considered. It is possible to update soil and water resource details during the growing season in the system. The information on irrigation systems can be loaded separately in the IDSS. According to the uploaded details, the optimal irrigation schedule was designed. IDSS takes advantage of seven-day agricultural meteorological forecasts, which leads to the maximum use of rainfall in the region and a proper matching between the provided irrigation schedule and the forecast of meteorological information in the coming days. To adapt the IDSS for irrigation planning the physicochemical characteristics of soil and water, water right, soil texture, etc. were considered. The virtual agricultural meteorological station launched by IDSS estimated the minimum temperature, maximum temperature, and sunshine hours with a good degree and relative humidity with a very good degree compared to the regional synoptic station data. Based on statistical indicators, the performance of IDSS for simulating volumetric soil moisture is evaluated as good to very good. Also, IDSS is adapted to the social conditions, the agricultural structure of the study area, and the knowledge level of farmers.Conclusion IDSS has up-to-date simulations and is suitable for providing an optimal irrigation schedule within the study area. Determining the effectiveness of IDSS in water consumption showed that the irrigation schedule provided by IDSS reduced the water consumption in the area. In farms that are under the basin irrigation system, the use of irrigation planning provided by IDSS has resulted in an average increase of 13.5% in water consumption and 8.6% in crop yield. The reason for the increase in water requirements in the basin irrigation systems is the high advance time in the farms under monitoring, and to meet the water requirments at the end of the irrigation farms, IDSS has inevitably increased the water consumption. The use of irrigation planning provided by IDSS has been able to reduce water consumption by 41% and 14% and increase the crop yield by 10.3% and 8.6% respectively in farms under drip and sprinkler irrigation systems. Therefore, the potential application of IDSS as an irrigation consultation and the degree to which this system has improved the irrigation management of agricultural farms can be used in most areas of the Lake Urmia basin. Next, it is suggested that IDSS be evaluated for other areas and crop yields, emphasizing the application of IDSS in humid and semi-humid climates.

Introduction Recently, the presence of pathogenic bacteria in the municipal water network has been observed and proven. Applying animal manure in agricultural lands with improper drainage is the main cause of this pollution. Identifying and investigating the movement of intestinal bacteria, especially E. Coli, which is the source of their distribution in most waters, agricultural activities, and urban sewage, is considered one of the appropriate and necessary ways to preserve drinking water resources Some of the soil characteristics that affect the movement of bacteria are: particle size distribution, structure, porosity and apparent density of the soil, in addition, plant roots and pores and cracks are caused by root activity. Plants and animals in the soil create fast water passages to facilitate the transport of pollutants. These routes are called preferential pathways and the flow is named preferential flow. Therefore, considering the environmental importance of the movement of E. Coli bacteria as a pathogen in the soil, so far, most of the studies on the transfer of bacteria without the presence of plants and its effect on the release of bacteria have been investigated. Therefore, this research aims to investigate bacteria transport from cow manure in four granulation levels in the presence of grass plants. Materials and Methods This study was conducted in the greenhouse of Shahrekord University to investigate the transport of E. Coli bacteria caused by the addition of cow manure in four levels of granular size in the soil profile with/without grass cultivation. Some physical and chemical characteristics of the soil were measured by usual methods. In this research, cow manure with a scale of 36 tons per hectare with four granulation levels of 0.25, 0.5, one, and two mm was used as a source of bacteria. The grass was prepared at a height of five cm and was placed on the surface of the soil columns for 14 days to stabilize the roots. The used columns were 24, made of polyethylene and in the form of a cylinder with an external diameter of 160 and a height of 350 mm. First, the soil was passed through a two mm sieve and then the columns were filled with soil up to a height of 300 mm. The treatments included grass cultivation in two levels (without cultivation and with grass cultivation) and the size of manure particles in four levels (0.25, 0.5, one, and two mm). The columns were irrigated with the usual irrigation schedule (once every two days) with the same volume and flow in the surface method until the field capacity was reached. After seven irrigations, the transfer test was performed. The transfer test with municipal water in the columns continued up to seven pore volumes (PV) and sampling was carried out in pore water volumes of 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7,0.8,0.9, 1, 1.2, 1.4, 1.6, 1.8, 2, 2.5 3, 3.5, 4, 4.5, 5, 5.5, 6, 6.5 and 7 were done for each treatment. After the end of the transfer test, to measure the population of bacteria in the soil profile, samples were taken from every five cm of soil depth. In this study, the live count method was used to measure the bacterial population. Results and Discussion There is no significant difference in the relative concentration curve of bacteria in the state of cultivation and without the cultivation of grass. It can be said that the effect of the cultivation of grass in the transfer of bacteria was not observed for 2 mm fertilizer particles, but the shape of the curves has changed in diameters less than 2 mm. It can be stated that in all treatments, the larger the amount of fertilizer, the higher the relative concentration of bacteria in low PVs. In other words, by washing the bacteria from the surface of the fertilizer particles, they are freed and enter the soil, and by continuing the washing, the maximum relative concentration of bacteria in the treatments without grass cultivation and in the diameters of 2.0, 1.0, 0.5 and 0.25, respectively, is 0.6. 0.7, 0.6, and 0.9 times the pore volume occurred. These values were equal to 0.7, 1.0, 0.9, and 1.0 times the pore volume in the treatments with grass cultivation, respectively. After this period, the concentration of released bacteria decreased sharply. The results showed that the presence of grass in the soil for all diameters of fertilizer, except the diameter of 0.25 mm, caused the peak of the breakthrough curve to be delayed. In addition, it is observed that the relative concentration of bacteria in the treatments with grass cultivation has decreased with a gentler slope compared to the treatments without grass cultivation. The amount of zero torque in the treatments with grass cultivation in all fertilizer sizes was more than the same treatment as compared to the conditions without cultivation, and this indicates that the presence of grass caused more bacteria to escape from the drainage of the columns. For fertilizers with particle sizes of 0.25, 0.5, and 2.0 mm in the condition of no cultivation, there is not much difference in the delay factor with the similar treatment in the condition of grass cultivation, but in the treatment with the particle size of one mm in the condition of grass cultivation, the rate of fertilization is delayed. has had a significant increase. Conclusions The results showed that for two mm fertilizer particles, the amount of bacteria transfer increased in the case of no grass cultivation compared to the one, 0.5, and 0.25 mm treatments. The maximum relative concentration of bacteria in the breakthrough curve for 0.25 mm fertilizer particles was lower between one and two mm compared to larger fertilizer particles and was observed with a delay compared to coarser fertilizer particles. In the treatment without grass cultivation, the maximum concentration per fertilizer with the particle size of 0.25 mm was observed at PV 0.9, while in the treatment with the particle size of two, one, and 0.5 mm, the maximum relative concentration of bacteria was 6.6, respectively. About 0.0, 0.7, and 0.6 times the pore volume occurred. In the presence of grass in the soil, the bacteria reached the bottom of the soil column at a faster rate. One of the causes of this phenomenon is the role of plant roots in accelerating the transfer of bacteria in the soil in such a way that the preferential flow paths created by grassroots have moved the bacteria down.

Introduction Water quality assessment is paramount for various sectors, including environmental planning, public health, and industrial operations. With the increasing importance of ensuring safe water sources, especially for drinking and irrigation purposes, modern methodologies like data mining offer valuable tools for predictive analysis and classification of water quality. Knowledge of water quality is considered one of the most important needs in planning, developing, and protecting water resources. Determining the quality of water for different uses, including irrigation and drinking in different areas of life. The use of modern data mining methods can be beneficial for predicting and classifying the quality of provider water. In the current study, the water quality of the Qizil-Uzen River was evaluated at Qara Gunei stations. In this regard, the drinking water quality index (WQI) using the chemical compounds of glass hardness, alkalinity (PH), electrical conductivity, total dissolved substances, calcium, sodium, magnesium, potassium, chlorine, carbonate, bicarbonate and sulfate in the statistical period of 21 years (2000-2020) was estimated. Water quality assessment is paramount for various sectors, including environmental planning, public health, and industrial operations. With the increasing importance of ensuring safe water sources, especially for drinking and irrigation purposes, modern methodologies like data mining offer valuable tools for predictive analysis and classification of water quality.   Materials and Methods Due to the relatively large number of variables, principal component analysis and independent component analysis methods were used to reduce dimensions, and then different machine learning algorithms including decision tree, logistic regression, and multi-layer perceptron artificial neural network were used to model the water quality index. By using these methods, the number of parameters needed to calculate the quality index was reduced from 12 to 2. Reducing the dimensions of the data saves the time of sampling, monitoring the samples, and determining the quality of the water and reduces the costs required for modeling to a significant amount. The results showed that among the dimensionality reduction methods, the principal component analysis method can perform better than the independent component analysis method. In the current research, the WQI index was modeled using machine learning algorithms including decision tree, logistic regression, and artificial neural network method. The quality of water in the Qizil-Uzen Qara Gunei river station has been evaluated. Then, to estimate the numerical values of the WQI index, TH, pH, EC, TDS, Ca, Na, Mg, K, Cl, CO3, HCO3, and SO4 parameters of the mentioned station in the statistical period of 21 years (1378-1398) were used. PCA and ICA methods have been used to select different input parameters. Modeling has been done in a Python programming environment. Among the available samples, 75% are considered for training and 25% for testing.   Results and Discussion In the present research, to model the water quality index in the first stage, different dimensionality reduction methods such as PCA and ICA were used to reduce the time and cost of implementation. In the second stage, machine learning methods such as decision tree, linear regression, and multilayer perceptron were used. In the method used by Tripathi and his colleagues, by using the principal component analysis method, they reduced the number of parameters needed to calculate the quality index from 28 to 9 and calculated the water quality index with the number of 9 parameters. Examining the two methods of PCA and ICA has reduced the dimensions of the problem from 12 dimensions to 2 dimensions. The results show that the PCA method can help us improve performance with little cost and high accuracy. Because of the PCA dimensions. The comparison of the results of the models was done using different numerical and graphical evaluation criteria, including R2, RMSE, and modified Wilmot coefficient as numerical criteria and Taylor diagram as graphical criteria. Because the PCA algorithm can help reduce noise in data, feature selection, and generate independent and unrelated features from data. The results show that multi-layer perceptron, decision tree, and logistic regression methods accurately perform the water quality index. In this research, for the first time, using the ICA dimension reduction algorithm, while reducing the dimensions of the problem, the water quality index is predicted with an accuracy of over 90%.   Conclusion Water quality index modeling holds significant relevance in agricultural practices, where access to clean water is crucial for irrigation and crop growth. Surprisingly, only a limited number of studies have explored variable reduction methods in water quality index modeling, with none incorporating the relatively novel Independent Component Analysis (ICA) method for dimensionality reduction. Thus, the current research fills this gap by employing PCA and ICA techniques to reduce the dimensionality of large datasets in water quality index modeling. By utilizing these advanced methods, the study aims to enhance efficiency and accuracy in assessing water quality, thereby offering valuable insights for agricultural water management. Following dimensionality reduction, the dataset is then subjected to modeling using various machine learning algorithms. This approach not only optimizes computational resources but also facilitates a deeper understanding of the complex interrelationships among water quality parameters. Through this pioneering research endeavor, the efficacy of ICA alongside PCA in addressing water quality index modeling challenges is evaluated. By integrating these techniques with machine learning methodologies, the study endeavors to provide actionable intelligence for agricultural stakeholders, aiding in informed decision-making and resource allocation. Moreover, by venturing into unexplored territory with the inclusion of ICA, the research contributes to expanding the methodological toolkit available for water quality assessment. As agriculture faces increasing pressure from climate change and resource scarcity, such innovative approaches hold promise in ensuring sustainable water management practices.

Introduction The runoff generation in a watershed is mainly influenced by the hydrological, geomorphological, and climatic conditions of the region. Regarding rainfall-runoff models, the problem becomes very complicated due to the non-linear response of the watershed to the rain event. Prediction of daily river flow is one of the most important hydrological issues, which is very important for flood management. River flow rates can be estimated by several methods, each of which has strengths and weaknesses. Regarding rainfall-runoff models, the problem becomes very complicated due to the non-linear reaction of a watershed to the rain event. In addition, due to the spatial changes of precipitation in an area, this complexity increases. In this research, the rainfall and runoff model is analyzed with the help of statistical methods and multivariate regression. The purpose of this study predict the inflow to Amirkabir Dam using multivariate regression methods and artificial intelligence (AI) methods, including the network model. It is an artificial neural network (ANN).   Materials and Methods To investigate the relationship between rainfall and runoff and to estimate the water entering the dam due to the rainfall upstream of the watershed, the rainfall of all the stations of the watershed upstream was received. The 7-year statistics of Karaj river flow (2016-2022) were used. After checking the rainfall data of the upstream stations, the homogeneity of the data was checked and the stations that had a suitable correlation in terms of climate were selected. At this stage, stations with appropriate conditions were selected by using factor analysis between upstream precipitation and runoff and water entering the dam downstream of the watershed. Then, to more properly analyze the relationship between rainfall and runoff, two-day and three-day cumulative rainfall at the selected stations was calculated. Then, the relationship between rainfall and runoff to the dam was investigated using statistical methods of multivariable regression and artificial intelligence. To get more accurate results, different seasons of the year were divided and the relationship between rainfall and runoff entering the dam in different seasons was investigated. Error statistics were calculated for calibration and verification during the test and training period. Finally, the final analysis of the data and the prediction of the runoff entering the dam was estimated using the upstream rainfall.   Results and Discussion Determining the effective stations in the runoff generation entering the dam as well as the delay time of their precipitation was achieved using multivariable regression and four stations of Nesa, Sira, Shahristanak, and Amirkabir Dam., the model of the volume of inflow to the dam, and precipitation in the catchment area of Amirkabir Dam. The coefficient of determination (R2) of the calibrated model was calculated as 76%, which is an acceptable coefficient in the relationship between precipitation and runoff. Based on the calibration and validation models of rainfall-runoff evaluation of rainfall forecasting models in July 2022, good rains are predicted for the watershed of Amir Kabir Dam. The rain system entered the country on July 28th and 29th and until July 31th it had relatively good coverage in the whole country, and on August 1st and 2nd this system weakened and only operates in limited parts of the country such as the Amir Kabir watershed. The results of evaluating the performance of the models with indicators such as coefficient of explanation (R2), mean absolute value of error (MAE), and root mean square error (RMSE) showed that the ANN model in both calibration (training) and validation (testing) stages ) has performed better than the multivariate regression model. The accuracy indices of the model for the ANN model training stage were equal to R2=0.77 and RMSE=0.27 m3 s-1, while these indices for the testing stage were equal to R2=0.87 and RMSE=0.46 m3 s-1. It indicates the better performance of the ANN model.   Conclusion The research results of this article showed that due to the presence of 5 rain gauge stations in the catchment area of Amir Kabir Dam, all the stations can not have the same effect on the water entering the dam. Using the cluster cluster method, the effect of all the stations on the inflow to Amirkabir Dam was investigated and suitable rain gauge stations were selected. Also, the results showed that the relationship between the rainfall of the watershed and the runoff entering the Amirkabir dam is different in different seasons and it has the highest correlation in the winter season because it is less affected by other factors affecting the runoff of the basin, including water from melting snow or thunderstorms. One of the other results of this study was that the calibrated and validated model had a slightly higher yield in the three seasons of winter, spring, and autumn, and a slightly lower yield in the autumn season.

Introduction Organic matter is one of the important indicators of soil quality. Organic matter increases water retention in the soil and helps to transport water and air in the soil. Organic matter increases crop growth and provides nutrients needed by plants and soil microorganisms. The amount of soil organic matter in nature depends on factors such as climate, soil properties, and agricultural management, especially in the plowing stage. This is although in many cultivated and undisturbed soils, the amount of soil organic matter reaches a constant value after some time and becomes balanced.On the other hand, most regions of Iran the arid and semi-arid and have low organic matter. The chemical composition of organic matter is approximately 50% of carbon, 5.0 % of nitrogen, 0.5% of phosphorus, 0.5% of sulfur, 39% of oxygen, and 5.0% of hydrogen, and these values change from one soil to another. The management of compost and plant waste is one of the most essential aspects of soil fertility management in the direction of sustainable agriculture. The research results showed that organic matter and carbohydrates are two factors related to the stability of soil structure. Considering the role and effect of using organic fertilizers (from animal sources and urban waste compost) on the physical characteristics of the soil, it is necessary to improve the productivity of soil and water, changes in the physical characteristics of the soil in different crop management (rotation) in fixed plots and in several years to be reviewed and evaluated consecutively.   Materials and Methods This research has been done to investigate the effect of applying organic manure from animal sources and urban waste compost in different and conventional crop rotations in fixed plots and also to investigate the changes in the physical characteristics of the soil due to the application of the following treatments in Alborz Province (at the research station of the Soil and Water Research Institute, Karaj) was implemented from November 2016. After planting wheat in 2016 and harvesting it in 2017, the land alternated with fallow. Wheat was planted again in the fall of 1997 and corn was planted in July 1998. In the fall of 1998, wheat was planted again and then the land was alternated with fallow. This research was conducted in the form of randomized complete blocks in five treatments and three replications in plots with an area of 200 square meters. The treatments include 1- no planting (T1), 2- control without fertilizer use (T2), 3- application of nitrogen, phosphorus, and potassium chemical fertilizers based on soil test (T3), 4- annual application of 20 ton/h of animal manure (T4) and annual application 20 ton/h of compost (T5). By taking soil samples from the surface layer, the physical characteristics of the soil, including field capacity, permanent wilting point, bulk density, final infiltration of soil, and aggregate stability of soil were measured in different treatments. Soil physical characteristics were measured after harvesting each product from a depth of 0-30 cm in three replicates. By removing the soil surface layer, the aggregate stability was determined by the wet sieve method.   Results and Discussion Treatments T1, T2, and T3 did not show significant changes in field capacity. The mean values of the field capacity of these treatments T1, T2, and T3 are about 17.8% and the treatment using animal manure (18.1%) and compost (18.3%) increases the field capacity by about 1.0 and 2.0 %, respectively, compared to the average treatments without the use of organic fertilizers. The values of bulk density changes in the treatments for the desired periods are not significant and it indicates that there is no specific trend in each period due to the changes in soil surface conditions for the treatments. The values of changes in the soil aggregate stability values have become significant only in the treatments of organic fertilizer consumption (from animal sources and compost) in the desired periods. The soil aggregate stability index in the treatment of using compost and manure increased by 27 and 18%, respectively, compared to the average of treatments without fertilizer use (1.1 mm), which indicates the role of organic fertilizer use in increasing the aggregate stability. The average final infiltration rate in the treatments without using fertilizer is about 28.1 mm h-1 and the average rate of final infiltration in the treatments using manure and compost is about 32.7 and 33.3 mm h-1, respectively. The average rate of final infiltration in the treatments using manure and compost has increased by about 16 and 19%, respectively, compared to the average of other treatments.   Conclusion According to the obtained results and the changes in the physical characteristics of the soil affected by the use of manure and compost in the cultivation periods, the role of the use of these materials in improving the physical characteristics of the soil is generally evident. The average bulk density of treatments T1 to T5 was equal to 1.47, 1.52, 1.54, 1.54, and 1.54 g cm-³, respectively, indicating a relative increase in bulk density in organic fertilizer treatments. The soil aggregate stability index in the treatment of using compost and manure increased by 27 and 18%, respectively, compared to the average of treatments without fertilizer use, which indicates the role of organic fertilizer use in increasing the aggregate stability. The average final infiltration rate in manure and compost treatments has increased by about 16 and 19%, respectively, compared to the average of other treatments, which indicates the effect of manure and compost application in increasing the final soil infiltration rate. Because for each crop rotation, the soil is subjected to tillage operations, therefore destruction of the surface layer of the soil (with more organic matter) and as a result intensifying the activity of microorganisms, from the effect of organic matter on the characteristics, the physical properties of the soil are reduced and it even causes that no special trend can be seen in the physical characteristics of the soil during the cultivation periods. Therefore, it is necessary to use a set of management strategies to improve the amount of organic matter or the physical characteristics of the soil.

Introduction Global warming threatens human survival in today's scenario; and has become an environmental challenge. The climate data shows the warming trend in many parts of the world, which has led to a wide range of climate effects such as reduced precipitation, drought, and the occurrence of extreme events. The increasing vulnerability of many urban areas, especially in developing countries, has been one of the main concerns of life. Therefore, examining the risk of risks caused by global warming on a national and local scale is a fundamental step to increase the readiness of urban areas to reduce current and future risks caused by climate change. Droughts have effects on vegetation, soil and freshwater quality, and etc., and are a serious ecological problem around the world, its impact on crops and water availability for humans can jeopardize human life. Although drought has always been common, the drought risk has become increasingly prominent because of the climatic warming that has occurred during the past century. Therefore, these effects of are noticeable in all climates, and Iran, having a dry and semi-arid climate, is one of the countries that is always at risk of drought, and this causes great economic damage to the country every year.  in addition to this, the review of the history and climatic texts shows that the importance of the effects of climatic elements (rainfall and temperature) on the drought situation of the region in the coming period is essential. Until now, the study of global warming in terms of increasing the risk of drought using the sixth report and new climate data has not been studied in Tehran province. So this study aims to investigate the effects of climate change on increasing the risk of drought in Tehran province.   Materials and Methods This research, First, the parameters (temperature and precipitation) for the synoptic stations (Abali, Shemiran, Mehrabad) for the period (1988-2020) were received from the Tehran Meteorological Organization. To projection in the future, down-scaling methods (SDSM-DC model) and The Mann-Kendall test were used to investigate the changes in temperature and precipitation. Climatic parameters change in space and time scale for many reasons. that these changes should be checked based on observations and statistical methods. Rainfall is one of those climate parameters that is not normal, and methods such as Menn-Kendall should be used to deal with such conditions; For this purpose, using Macro Excel, the value of age slope and Z statistic was calculated in the period (1988-2020) for the stations (Mehrabad, Shemiran and Abali) to investigate the trend of precipitation and temperature from the past to the present at a confidence level of 95-99% computed. In the following NetCDF data together with CanESM5 predictors from the base period (1979-2014) according to the most recent SSP release scenarios of the IPCC 6th Report were obtained from the Canadian Climate Change website. Among them, only Mehrabad station had a complete basic period compared to other stations, it was chosen as the selected station in Tehran. Drought indices are used as an index to track and quantify drought, this research is SPI index with DIC software has been used to evaluate the drought. in this index Precipitation, which has been one of its main components, whose output and results are more consistent with reality.   Results and Discussion The results using the Mann-Kendall test showed that the examination of temperature changes in the stations (Mehrabad, Shemiran, Abali) was an increasing trend. Rainfall in most months of the year is a stable trend, only jumps are observed which can be justified by the increase in the frequency of rainfall. In the simulation with the CanESM5 model under the SSP5 scenario at Mehrabad station, the highest temperature was assigned to July and the highest rainfall will be in March. in this research, The drought survey showed that Mehrabad station experienced severe drought only during 1989-1993, while the duration of the drought period was longer in Abali and Shemiran stations and both of them faced very severe drought in 2014. in addition, this Investigation of three stations with a common period of 32 years in Tehran shows that Tehran has overcome the drought situation in recent years; But most of the time, the region may be in close to normal climatic conditions. But the risk of dry to very dry conditions will be very close. On the other, the results confirmed that drought depends on both rainfall and temperature.   Conclusion As drought depends on both precipitation and temperature, The more the drought is accompanied by the trend of increasing temperature, decreasing precipitation, and the prediction of climate models, the more likely it is that climate change will occur due to global warming. As a result, the temperature of Tehran will increase. And while the rainfall is decreasing, it will be fluctuating and torrential. so In the future, Tehran's climate will have more fluctuations in rainfall and will be warmer than the current conditions. In addition, rains will occur more randomly but with more intensity. Tehran has had a drought in recent years, but most of the time the region has been in near-normal climatic conditions, but is the risk of dry and very dry conditions. This factor will create environmental challenges in the future. In addition to this, it is necessary to have a plan for climate risk management in the future due to the new climate of Tehran, which is prone to drought.

Introduction Climate change is one of the greatest challenges of our time to achieve sustainable development. The dangers of global warming and climate change can be recognised and planned for, so efforts should be made to identify the consequences and methods of adaptation to reduce their impact, as trees and plants are sensitive to climate change, heat and moisture stress, and forest ecosystems are affected by these changes. Climate change is one of the greatest challenges of our time to achieve sustainable development. The threats of global warming and climate change can be identified and planned for, so efforts should be made to identify the consequences and methods of adaptation and reduce their impacts because the sensitivity of trees and plants to climate change, heat and moisture stress, forest ecosystems are affected by these changes. Forest degradation due to climate change is a global phenomenon affecting many tree species. One of the major challenges to Iran's natural resources is the degradation of oak forests. The increase in temperature in recent years has lengthened the growing season of Iranian oak, and due to the lack of rainfall, the intensity of water stress on this forest species has increased. Understanding the extent of climate change in the Zagros ecosystem based on standard indicators that show climate change can help managers and planners take action to adapt to conservation and restoration conditions.Materials and Methods In this study, based on the standard indicators established and updated by the World Meteorological Organization, the occurrence of climate change in six sites monitoring the decline of oak trees in Ilam Province, including Sarabeleh, Mala Siah and Dalab Strait, was detected in both north and south directions. The trend slope line, trend slope error and trend significance of the indices in the statistical range P value=0.05 were calculated using ClimPACT software in R program environment. The characteristics of heat, cold, combined, and precipitation indices such as day, number of occurrences, and continuity of the index in the nearest synoptic station to each site were identified, and daily data of minimum temperature, maximum temperature, and precipitation parameters were used between 1987 and 2019. The variations of each index were plotted and analyzed as graphs in the R software environment. Accordingly, the trend slope and significant indices affecting heat stress (hot temperature indices and cold-temperature indices) and water stress were calculated with the software ClimPACT in the R programme environment.Results and Discussion The results of the trend and significance of thermal indicators for climate change detection showed that of the 16 heat indices studied, in Ivan station, 11 indicators showed a significant trend of about 70% and in Ilam 9 indicators showed a significant trend of about 56%.The heat-based temperature indices, especially those based on maximum temperatures, showed a significant change towards warming, while those based on minimum temperatures showed no significant trend. The study of heat waves showed that the northern and northwestern regions of the province were subjected to several periods of heat waves, which occurred with greater frequency and continuity in the northwestern part of the province (Malah Siah and Dolab Strait sites) than in the northern part (Sarab sites) of the province, confirming the emergence of high mountain regions as a result of climate change. Cold-based temperature indices of 8 studied indices in Ivan-e-Sorchrove station, 7 indices were above 87% and Ilam 3 was about 38% the trend was significantThe cold-based temperature indices in Ivan West station show a significant change in the direction of a decrease of frost and cold and their persistence and warming, and in Ilam station the decrease of cold and warming of air after 2008 indicates a decrease of cold and warming. The results of the trend and significance of the combined indices for climate change detection in Ivan West station were 100% and in Ilam station 50% showed significant trend. The combined indices confirm climate change in terms of increase in air temperature due to increase in growing season and increase in trend of change in maximum temperature. The study of the trend and significance of ten precipitation indices related to the frequency and intensity of heavy rainfall and the length of dry and wet periods showed only one index in Ivan-e-West station, which was about 10%. The station Ilam did not show significant changes in the precipitation index.Conclusion It can be concluded that zagros vegetative region in Ilam province has experienced severe thermal changes during 1987-2019 and climate change in the north of Zagros vegetative region is a type of temperature increase that has been extended to the northwestern regions of this region since 2008. The results show that in deterioration sites, in addition to increasing temperature, some precipitation has increased. Therefore, it can be said that the occurrence of climate change phenomenon causes increasing temperature, occurrence of floods, emergence of droughts and creating dust phenomenon, especially from neighboring countries and intensifying it in the country, all of these factors are the starting factors of the decline of Oak Trees in Ilam province. What seems to be important is to take necessary measures to prevent and mitigate the effects of climate change. These two measures can be effective and useful in reducing the effects of flood severity and risk. Therefore, managers and planners of forest ecosystems should have adaptive strategies to climate change in order to maintain and revive their executive plans so that Zagros can survive as a forest ecosystem. Although the occurrence of climate change phenomenon is one of the most important factors of drought and deterioration of Zagros forests, conservation and restoration of oak forest ecosystems can help reduce greenhouse gas emissions and climate change.

Introduction Irrigation water salinity is a very serious problem in different parts of the world, especially in arid and semi-arid regions. Increasing fresh-water demand due to population growth causes the pressure on water resources to increase in the future causing the water supply through saline and unconventional water to become a serious issue, especially in areas facing water scarcity. On the other hand, agriculture is the world's greatest water consumer where saline water reduces the products, destroys the soil structure, and damages the environment. Wastewater desalination and water reuse is a relatively new approach in the water industry that solves saline-water problems through various methods. But it is uneconomical due to high equipment costs and energy consumption, especially in agriculture where water consumption is much higher. To remove pollutants, various studies have used different adsorbents such as biochar, activated carbon, zeolite, and resin among which biochar can effectively remove pollutants from aquatic environments because it is an effective, inexpensive, polar, high-porosity adsorbent. Ion exchange, complex formation, surface adsorption, electron sharing, and biochar (carboxylic and pHenolic) - functional group interaction are among various mechanisms where the presence of negative charge on the biochar surface and positive charge on metal ions improve the adsorption process. As the activated carbon is made from cheap materials as wood, coal, oil, coke, sawdust, and plant waste, it is quite economical and highly capable of removing a wide range of organic and inorganic pollutants from aquatic and gaseous environments. Materials and Methods To prepare biochar, this research used the sugarcane bagasse as primary biomass by 1) washing it several times with ordinary and distilled water and drying it in the open air to remove its remaining salts, 2) crushing it with an industrial mill and placing it in an oven at 60 °C for 24 hrs to remove its excess moisture, 3) grinding the crushed bagasse with a small mill for further milling, 4) passing it through 60 and 100 mesh sieves in two stages for more uniformity and 5) placing it in closed containers. Biomass was converted to biochar (BC) using a heat-programmable electric furnace where the temperature rise was set at five °C/min for a uniform heat distribution. Bagasse was placed inside a steel reactor into which nitrogen gas was injected at a fixed flow rate and prevented oxidation. Biomass was kept at 600 °C for two hrs thereafter the furnace was turned off, while nitrogen gas was injected, and the temperature was slowly lowered to that of the lab. Considering the sizes of the furnace and reactor, each time 20 g biomass was placed in the reactor and about five g biochar was produced after the carbonization process; the biochar production efficiency under these conditions was about 25%. Nano biochar (N-BC) was made by a planetary ball mill with ceramic cups and bullets where the bullet-to-biochar weight ratio was 15-to-one and the rotation speed was 300 rpm. The good mill-activity time was two, four, and six hrs. It worked for three min and rested for one minute to prevent the temperature from rising and cohesive masses from forming in the samples; as size and uniformity of particles were important, use was made of a gradation device. Results and Discussion In all treatments, by increasing the initial Chlorine concentration, the Chlorine removal had an increasing trend. on average, this was, using activated nano biochar 74.4% more than activated non-nano biochar. Magnetizing nano-absorbents reduced the Chlorine removal by 18.8%, on average. The highest and lowest Chlorine removal reductions due to the adsorbent magnetization were 31.6 and 10.9%, respectively. The highest Chlorine removal in all three activated non-nano, activated nano, and magnetically activated nano adsorbents (200 and 400 W treatments) was measured for an activator-to-biochar ratio of three. According to the results, Chlorine adsorption by magnetically activated nano absorbent reached equilibrium after 480 min in the treatment with 200 and 700 W microwave power and after 540 min in treatment with 400 W microwave power. Increasing the initial Chlorine concentration from three to 25 g l-1, increased the Chlorine removal by the magnetically activated nano absorbent by three, 3.5, and 2.6 times in 200, 400, and 700 W microwave power treatments, respectively. Conclusion The pseudo-first-order kinetic model had a good correlation with the data and the pseudo-second-order kinetic model did not correlate well with the data in times less than 60 min; hence, the dominating adsorption mechanism was not chemical in this interval. Intraparticle diffusion was an effective Chlorine-adsorption factor from the beginning of the adsorption process. Considering the correlation coefficient and sum of squared errors, the pseudo-first-order kinetic model and the intraparticle diffusion model had the highest correlation with the measured data. The average correlation coefficient for Langmuir and Freundlich models was found to be 0.9938 and 0.886, respectively. Therefore, the Langmuir isothermal model conformed better to the measured data than the Freundlich model.

Introduction Analysis of the spatial and temporal trends of precipitation is pertinent for the future sustainable management of water resources. Urbanization and climate change affected local rainfall and intensity. As rainfall characteristics are often used to design urban drainage systems, so watershed modeling, and estimate of the flood properties, updating and reviewing rainfall characteristics is necessary. The Intensity-Duration-Frequency (IDF) curves are a suitable tool to estimate the threshold values of precipitation in different return periods. IDF curves should be prepared based on the long-term rainfall statistics in each region and can change under the influence of climate change. These curves which indicate the frequency and maximum intensity of annual rainfall in the different return periods are suitable tools for planning and managing the water resources. IDF curves are broadly used for different purposes, such as the design of flood control and diversion structures in the cities. The main purpose of this research is to investigate the effect of climate change on temperature, precipitation, and IDF curves in the different return periods in an arid environment.   Materials and Methods In this research, the effect of climate change on IDF curves was investigated in Kashan City as a dry region. Kashan city with an area of 9647 km2 is located in the northern part of the Isfahan Province. In this study, RCP8.5, RCP4.5, and RCP2.6 scenarios (which are introduced as optimistic, intermediate, and pessimistic scenarios) reported in the fifth assessment report of the Intergovernmental Panel on Climate Change (IPCC), were used to predict the impacts of climate change on temperature and precipitation changes. Then, IDF curves were calculated evaluated, and compared for the basic (1993-2017) and future periods (2011-2070). To examine the impact of climate change on the rainfall intensity patterns, it is necessary to extract IDF curves in different climate conditions. Bell's method is a usual method for extraction of the IDF curves, which was promoted by Gharehman-Abkhezr in Iran. In this study, the latest promoted relationships developed were for the desert and southern regions (e.g;Nizar-Salfachgan, Kuhpayeh, Herat, and Jiroft basins in the central Provinces, Qom, Isfahan, Kerman, and Yazd) have been presented and used to extract IDF curves. To investigate the effects of climate change on IDF curves, first, the base period curves were extracted via rainfall data measured at the Kashan synoptic station. Then, using the new climate scenarios (RCP8.5, RCP4.5, and RCP2.6) and the output data of the LARS exponential microscale model, the IDF curves were extracted for different climate scenarios in the future (2011-2030), (2031-2050), and (2051-2070). Finally, the results of these curves were compared with the base period.   Results and Discussion According to the results, for the base period, the precipitation and temperature data were predicated with an acceptable accuracy by the LARS model. The accuracy of the model has been higher in estimating the minimum and maximum temperature. the Nash and explanation coefficients for the maximum and minimum temperatures were 0.99 and 0.99, respectively. While, the explanatory and Nash coefficients for precipitation data were 0.95 and 0.93, respectively. Based on the results, the rainfall intensity will have fewer changes compared to the base period for long-term duration rainfall compared to short-duration rainfall (less than four hr. The maximum changes are related to rainfalls with a duration of less than one hour, whereas the minimum changes are predicted for 24- hr rainfalls. For all studied scenarios, a significant difference (P<0.05) was predicted between the average rainfall intensity of 0.17 to 24 hr in the region. As in the two-year return period and under the 2.6 scenario, rainfall intensity was increased from 10.75 to 30.54 mm hr-1 for the duration time of 0.17 hr.   Conclusion An increase in air temperature, decrease in rainfall, change in the rainfall pattern, decrease in river discharge, and increase in sudden floods, followed by an increase in soil erosion, and a decrease in the amount of agricultural products are the results of climate change. Therefore, the long-term analysis and monitoring of climatic conditions can be very effective for crisis management caused by climate changes such as floods and droughts. Based on the results, the effect of climate change on the intensity of short-term rainfall is greater than long-term duration rainfall, as the intensity of short-term rainfall will increase more than long-term rainfalls.

Introduction Evaporation, the process by which water molecules escape a surface after absorbing sufficient energy to overcome vapor pressure, is a major contributor to water scarcity, especially in arid and semi-arid regions where heat readily facilitates this escape. Accurately estimating evaporation losses is crucial for effective water resource management, crop water demand prediction, and irrigation scheduling. Machine learning (ML) has emerged as a powerful tool for tackling the complex and stochastic nature of environmental problems. ML models excel at identifying relationships between predictor variables and outcomes (predictands), often surpassing traditional methods. However, their performance can vary depending on input factors and climatic conditions. Recently, hybrid techniques that combine multiple models have gained traction in climate and hydrology studies. These techniques leverage the strengths of different approaches within a single algorithm, potentially capturing more complex patterns in data series. This research will explore the potential of various individual ML models and propose a novel hybrid approach for estimating pan evaporation in Sistan and Baluchistan Province.   Materials and Methods This study investigates pan evaporation simulation and prediction in Sistan and Baluchistan Province, Iran. Synoptic station data (1980-2019) served as model inputs, while pan evaporation measurements from these stations provided the observed values. In this research, in the approach of individual performance of data mining models, eight data mining models were used to simulate and predict evaporation from the pan. In addition to the individual performance approach, the combined VEDL approach was used to provide a hybrid model (a combination of the mentioned eight individual models of deep learning). In this hybrid approach to regression issues, the estimators of all models are averaged to obtain an estimate for a set called vote regressors (VRs). There are two approaches to awarding votes: average voting (AV) and weighted voting (WV). In the case of AV, the weights are equivalent and equal1. A disadvantage of AV is that all of the models in the ensemble are accepted as equally effective; however, this situation is very unlikely, especially if different machine learning algorithms are used. WV specifies a weight coefficient for each ensemble member. The weight can be a floating-point number between Zero and one, in which case the sum is equal to one, or an integer starting at one denoting the number of votes given to the corresponding ensemble member. the weight of each model was selected based on the accuracy of the model's performance using the evaluation criteria obtained from the training implementation section of individual models. the model’s performance was assessed using statistical measures, including R2, RMSE, MAE, and Taylor diagram.   Results and Discussion The results showed that all the models had very good results in both the training and testing stages. All models exhibited excellent performance during training and testing. The Artificial Neural Network (ANN) achieved the highest accuracy in both phases at the Zahedan station (R² = 0.89, RMSE = 45.95 in training; R² = 0.96, RMSE = 44.18 in validation). It emerged as the best model for monthly pan evaporation prediction at this station. Other models also performed well, with the Support Vector Machine (SVM) and Random Forest (RF) models achieving R² values of 0.89 and 0.88 in training, respectively. Notably, the BART model ranked second in validation (R² = 0.96). The Tree Model (TM) had the lowest accuracy (R² = 0.84 and 0.93 in training and validation, respectively). Across all stations, ANN, SVM, and RF consistently delivered the best results in both training and testing. In the test phase, the SVM model outperformed others in Khash, Iranshahr, and Chabahar stations (R² = 0.94, 0.96, and 0.94, respectively). At the Saravan station, the RF model achieved the highest R² (0.94) during testing. To develop a hybrid data mining model, the Voting Ensemble for Deep Learning (VEDL) technique was employed with weighted voting in the training stage. The combined model significantly improved upon the best individual model. RMSE decreased from 45.95 to 33.1, R² increased from 0.89 to 0.94, and MAE improved from 32.92 to 23.9. Evaluation using the Taylor diagram further confirmed the superior performance of the VEDL model compared to the individual ANN model.   Conclusion The results showed that among all the models, ANN, SVM, and RF models had the best performance in the two stages of training and verification. In the validation stage, the SVM model with R2 values equal to 0.94, 0.96, and 0.94 performed best in the Khash, Iranshahr, and Chabahar stations. At the Saravan station, in the Sensji validity stage, the RF model with an R2 value of 0.94 had the best performance among the models. The excellent performance of the models in the two stages of training and validation is another finding of the research, These results are consistent with the results of researchers who have expressed the appropriate efficiency of machine learning models in estimating evaporation/evaporation and transpiration in different climatic regions of Iran. The results of the combined model showed that the combined model improved the results compared to the best individual model so that the RMSE values increased from 45.95 to 33.1, the R2 values increased from 0.89 to 0.94, and the MAE value improved from 32.92 to 23.9. The use of the VEDL approach to estimate evaporation from the pan was a new approach that has not been used in past studies. Therefore, according to the results of this research, the proposed deep sensing model is proposed to estimate the evaporation of arid and semi-arid areas for water resources management and agricultural planning.

Introduction Rivers are always faced with erosion and sediment transport. Sediment transport in rivers is one of the most complex topics in river engineering and is always the focus of experts and water engineers. This phenomenon is one of the important hydrodynamic processes that affect many hydraulic systems and water facilities and is considered one of the basic problems in the exploiting surface water resources globally. Estimating the sediment load of rivers is one of the important and practical issues in the studies and design of water engineering projects, such as the design and development of irrigation and drainage networks, water extraction from rivers, etc. Sediment concentration can be calculated by direct or indirect methods, which are usually expensive and time-consuming direct methods. Various factors affect this phenomenon, which makes their analysis difficult. Therefore, they cannot model the sedimentation phenomenon with acceptable accuracy. Hydraulic models cannot always be trusted due to the need for a lot of data, unavailability of the required data, and the inaccuracy of the data due to human error for simulating sediments. Nowadays, fuzzy and neural intelligent conductor systems, due to their ability to solve complex and nonlinear phenomena, have found many applications in various water engineering problems, including sedimentation. The purpose of this research is to evaluate and compare adaptive neural fuzzy models (ANFIS), support vector machine (SVM), gene expression programming (GEP), and group model of data handling (GMDH) in estimating the sediment load of Tirah River, Markazi Province.   Materials and Methods In this research, first, the long-term daily statistics of temperature, rainfall, average flow rate, and sediment concentration of Hasan Abad hydrometric and sediment measuring station located on the main branch of the Tirah River were collected. Then, the data sufficiency test for analysis, checking the correlation between parameters of river discharge, precipitation, temperature with sediment discharge, and determining the long-term average of suspended sediment in the studied stations were performed. In the next step, a suitable combination of input variables was selected. The design of the input parameter pattern can be based on the relationship between flow and sediment flow parameters, rainfall, temperature, flow, and sediment flow. Of course, considering that the mentioned parameters have a historical course, therefore, the design of the input patterns of soft computing models should be done based on time delays (like what is discussed in the analysis and forecasting of time series). Determining the most appropriate time delay of the input parameters in the modeling of discharge, sediment, temperature, and rainfall, then the appropriate design of the structure of the used soft calculation models was done. In the next step, the estimation of sediment discharge using an SVM, GEP, and ANFIS group method of GMDH data control and comparison of three data mining methods, and also with the sediment rating curve and observational data. About 70 % of the research data was used as training and between 20 to 30 % for validation and testing.   Results and Discussion Based on the statistical indicators of optimal model selection, the best performance of the SVR model has been obtained for model number one. In this model, the R2 and RMSE obtained from the model are 0.96 and 0.0047, respectively. Besides, the R2 and the RMSE error of the models in predicting suspended sediment values in the test stage are 0.95 and 0.014, respectively for the ANFIS model, and 0.50 and 4.97, respectively for the GEP model. The best performance of the ANFIS model has been obtained for model number one. In this model, the R2 and the RMSE obtained from the model are 0.95 and 0.014. The R2 and RMSE of the models in predicting suspended sediment values in the test stage are 0.96, 0.0047 for the SVR model, and 0.50, 4.97 for the GEP model, respectively. The best performance of the GEP model has been obtained for pattern number nine. In this model, the R2 and RMSE obtained from the model are 0.99 and 0.010, respectively. The R2 and the RMSE of the models in predicting the amount of suspended sediment in the test stage are respectively equal to 0.70, 0.015 for the ANFIS model and 0.78, 0.0185 tons respectively for the SVR model.   Conclusion It can be seen that the performance of the GEP model was better compared to other models. SVR and ANFIS models are ranked second and third. In the next step, the best-selected pattern of ANFIS, SVM, and GEP models was used as the input of the GMDH model. First, input pattern one, which was selected as the best pattern for ANFIS and SVM models, was introduced as the input of the GMDH model. In the training and test, the values of R2 statistical indices are 0.94 and 0.99, respectively, the RMSE error value is 0.0079 and 0.0038, respectively, the MSE value is 0.000062 and 0.000015, respectively, and the MAPE values are respectively 0.007 and 0.003. In the next step, input pattern nine, which was selected as the best pattern for the GEP model, is introduced as GMDH input. In the training and test steps, the value of R2 is equal to 0.95 and 0.98 respectively, the RMSE error value is equal to 0.0077 and 0.0045 respectively, and the MSE value is equal to 0.0006 and 0.00002 respectively, and MAPE value is equal to 363 and 502. The results showed the acceptable performance of the GMDH model with the highest R2 equal to 0.99 and 0.98 and the lowest RMSE equal to 0.0038 and 0.0045, respectively.

IntroductionA landslide is one of the mass movements on the top surface of the earth. Landslides have resulted in notable injury and damage to human life and destroyed infrastructure and property. Landslides represented approximately Nine percent of the natural disasters worldwide during the 1990s. According to studies, this trend is expected to continue due to increased human development. Many studies have been done to determine the factors affecting mass movement. In large part of Iran including the mountain areas, tectonic activity and seismic high with diverse geological and weather conditions led to many countries prone to landslide. Landslides cause wide damage to natural resources, human settlements, infrastructure, mud floods, and filling reservoirs. Landslides cause extensive property damage and occasionally result in loss of life. Besides, should not be ignored the social and environmental impacts resulting from the occurrence of this phenomenon, such as immigration and unemployment. One of the strategies for reducing losses due to a range of movements is the identification and management of unstable slope areas. To identify unstable regions pay to landslide hazard mapping. The main purpose of this research is to assess the effective parameter on landslide occurrence and to compare different machine learning models including SVM, GP regression, and RF for landslide susceptibility zoning. Materials and Methods The study area is a part of the Haraz Watershed, Mazandaran Province, Iran, occurrence many landslides are damaged after each heavy rain. So, it was selected as a suitable Watershed to evaluate the landslide susceptibility mapping (LSM). The vegetation covers and land mainly consists of rangeland. The geology of the study area consists mainly of Quaternary and Shemshak formations. The first step for the assessment of landslide susceptibility is gathering the necessary data and preparing information. These data were determined based on several factors. Considering the literature review, the local conditions, and previous studies. In this study, nine parameters such as slope angle, slope aspect, elevation, geology, land use, the distance of fault, the distance of the road, the distance of the river, and precipitation were identified as key factors for the prediction of landslide susceptibility. To assess the effectiveness of GP-PUK, GP-RBF, SVM-PUK, SVP-RBF, AND RF to estimate the landslide susceptibility map (LSM), data used in the present study were taken from field data. In this study, the dataset contains 148 observations of landslide occurrence and landslide non-occurrence points. The landslide data have been randomly separated into training (70% of landslides; 103) and testing (30% of the landslides; 45). To judge the performance of the soft computing techniques, statistical evaluation parameters were used. In this research, three statistical evaluation parameters were used. These parameters are the correlation coefficient (C.C.), root mean square error (RMSE), and Nash–Sutcliffe model efficiency (NSE). Results and DiscussionAccording to the results of the comparison of methods, RF was the best model and the accuracy of the RF model was more suitable for the estimation of the landslide occurrence. So, in this study, RF was used for the landslide susceptibility map. Single-factor ANOVA test suggests that there is an insignificant difference between observed and predicted values of landslide occurrence and landslide non-occurrence using GP_PUK, GP_RBF, SVM_PUK, SVM_RBF and Random Forest approaches. According to the results of the comparison of methods, RF was the best model and the accuracy of the RF model was more suitable for the estimation of the landslide occurrence. The map of landslide susceptibility map was divided into five classes from none susceptible to very high susceptibility. According to the final Landslide susceptibility map, the area belonging to the “non-susceptible” class covers 35.86 km2, “low susceptibility” class 36.19 km2, “moderate susceptibility” class 15.06 km2, “high susceptibility” class 10.95 km2 and “very high susceptibility” class 14.46 km2 of Haraz Watershed. Sensitivity analysis was performed to find the most significant input parameter in the prediction of landslide occurrence and landslide non-occurrence. The result shows that aspect has a major role in predicting landslide occurrence and landslide non-occurrence in comparison to other input parameters, respectively. Conclusion Due to all results, some zones are potentially dangerous for any future habitation and development. Thus, there is an immediate need to implement mitigation measures in the very high-hazard and high-hazard zones, or such zones need to be avoided for habitation or any future developmental activities. The results of this research can be used by the local authority to manage properly, and systematically and plan development within their areas.

Introduction Due to global warming, accurately estimating evaporation has become a key challenge in water resource management, and due to the important role it plays in the withdrawal of water from human reach, it has always attracted the attention of researchers. Therefore, modeling and awareness of the value of evaporation as one of the hydrological variables is of great importance in agricultural research and soil and water conservation. Gorgan was chosen for the study due to its proximity to the Caspian Sea with a humid climate and a higher rate of evaporation than other cities. On the other hand, Shiraz has a hot and dry climate, is located in central Iran far from water resources such as the sea, and has a lower evaporation rate. Kish also has a warm and humid climate due to its proximity to the sea, with a lower evaporation rate than Shiraz but higher than Gorgan. Several meteorological variables affect the process of evaporation and transpiration, and due to the complexity of the evaporation parameter, a method with high accuracy should be used to determine them. Recently, artificial neural network methods have become very popular among researchers due to their common use and the ease with which they can solve complex problems. Therefore, many intelligent algorithms have been suggested to find the best solution for complex engineering problems, as they can find optimal answers faster and more accurately.   Materials and Methods Artificial neural networks are designed based on inspiration from the memory and learning mechanisms in the human brain. To train artificial neural networks, a set of valid input and output data is used based on the type of problem. The accuracy of the network output depends on the amount of training data and how the inputs and their features are processed. To design different scenarios for adjusting input data, the correlation values of the data with evaporation were used. In this study, three synoptic stations with different climates, including Gorgan, Shiraz, and Kish, were chosen. Three stations with different climates were used to better evaluate and repeat the steps of the method so that the efficiency of the method could be more accurately assessed. Considering the importance of the value of evaporation in nature, evaporation modeling with the ANN and its combination with the COOT algorithm, which mimics the natural life of a COOT bird, was performed using five meteorological parameters, including the minimum air temperature, maximum air temperature, wind speed, average relative humidity, and sunshine hours on a monthly between 2000 and 2022. The dataset was divided into two phases: training (70 % of the dataset) and testing (30% of the dataset). To evaluate the performance of developed models, statistical indices of these models such as correlation coefficient (R), root-mean-square error (RMSE), Nash-Sutcliffe coefficient (NS), and their graphical representations were compared with each other.   Results and Discussion As mentioned, four models of ANN-COOT with varying input parameters were developed and compared to four conventional ANN models. Statistical performances were calculated, and comparison plots were made in the training and testing phases to find the most adequate model for the prediction of evaporation. Comparing of obtained results from statistical indices for the testing phase revealed that the COOT-ANN4 model had the best performance for Gorgan with the R, RMSE, and NS equal to 0.99, 8.19, and 0.99 respectively. Shiraz also obtained values of the R, RMSE, and NS equal to 0.99, 18.43, and 0.98 respectively. Similarly, for Kish, the values of the R, RMSE, and NS equal to 0.97, 19.36, and 0.93 respectively, have better performance than the other models. Compared with the results of different input combinations, the hybrid ANN-COOT model (ANN-COOT4) at three stations was found superior with input combinations of Tmin, Tmax, SSH, RH, and WS. Additionally, to evaluate the accuracy of developed models, Scatter plots, Violin plots, Relative error percent plots (RE %), Taylor diagrams, and Histograms were drawn. By comparing the graphical representations, it can be determined that the hybrid COOT with ANN4, namely the COOT-ANN4 model, has improved the artificial neural network at Gorgan, Shiraz, and Kish stations.   Conclusion The algorithm of COOT is an optimization algorithm that is generally used to solve optimization problems. As observed from the overall performance of the results of the hybrid model in predicting evaporation, the objective function was minimized. The results indicated that scenario four of the COOT-ANN4 hybrid model with input parameters of minimum temperature, maximum temperature, sunshine hours, relative humidity, and wind speed has better accuracy and performance at all three stations. In general, the findings of this study revealed that the COOT algorithm can improve the artificial neural network (ANN) structure in any climate and provide a hybrid model with higher accuracy and less error for modeling the evaporation parameter. Considering that the COOT algorithm is powerful and efficient, it is better to use it in various fields to improve the performance and accuracy of models. The testing results revealed that the lowest Root Mean Square Error RMSE (18.43, 19.36 and 8.19) and highest coefficient of correlation R (0.99, 0.97, and 0.99), and the highest Nash–Sutcliffe Efficiency Coefficient (N-S) (0.98, 0.93 and 0.99) attained by the ANN-COOT4 hybrid model (relative to other ANN and ANN-COOT models) tested for three selected stations in Shiraz, Kish and Gorgan sites. Concerning the predictive efficiency, the developed ANN-COOT hybrid model, improved the modeling performance at extreme points, which outperforms the ANN model, indicating its capability in the prediction of monthly evaporation.

Introduction Effective approaches and policies including identifying priorities and optimal water allocation techniques, especially in basins with different users are considered essential for sustainable development in each region. With 1100 m3 of renewable water per person per year, Iran is considered to be the most critical region in the world in terms of water resources. Unfortunately, most plans in the water sector of such countries are based on local economic growth, and no attention is paid to the amount of available water resources. Considering the issue of a water crisis and the droughts of the last few years, the issue of water resources management has gained high importance. To overcome the mentioned problems, it is inevitably essential to use newly developed water management techniques based on advanced approaches. Although optimization techniques are well-known tools in these issues, the simulation method is utilized as a helpful approach. To simulate water management in the basin, there are various available models. RIBASIM, MIKE BASIN, WEAP, and MODSIM models are famous and user-friendly ones in this collection. WEAP software is a comprehensive and advanced water resource system simulation tool widely used in watershed management and can consider physical and hydrological processes. The scenarios that can be investigated with this software include population growth, economic development, changing the policy of operating reservoirs, extracting more from underground water resources, saving water, allocating ecosystem needs, integrated use of surface and underground water, reuse of water, etc.   Materials and Methods This study was conducted in the Nahand catchment area which is located in East Azerbaijan province. Nahand river is the main draining course of this catchment, on which a dam has been built to supply a part of Tabriz's drinking water. To control the performance indicators of the reservoir, several management and exploitation scenarios were developed and evaluated in the WEAP model. The WEAP model was presented in 1990 by the Stockholm Environment Institute (SEI). It is a comprehensive and advanced model for simulating water resource systems, which is extensively used in the management of water resources in watersheds. This model has provided a practical tool for water resource planning and policy analysis to put all the issues related to water resources and uses in a single environment. The WEAP model is capable of simulating issues related to consumption such as water consumption patterns, water reuse strategies, costs, and water allocation patterns, as well as issues related to resources such as river flow, groundwater resources, reservoirs, and water transmission lines. The inputs of the WEAP model include data on the population of Tabriz City, per capita consumption of drinking water per person, the amount of water wastage in the distribution network, the inlet discharge of the Nahand reservoir, the information of the Nahand dam, the amount of cultivated area, etc., and to evaluate the model R^2, RMSE, and MAE statistical indicators were used in two periods of calibration and validation. Then, various operating conditions were investigated by compiling the Reference (continuation of the status quo), SC1 (increase of input flow by 10%), and SC2 (decrease of input flow by 10%) scenarios. Besides, Reservoir performance indicators are used to measure its performance under different operating circumstances.   Results and Discussion The simulation results of the studied area indicated that the WEAP model with evaluation criteria including R2, RMSE, and MAE in the calibration stage was 0.89, 1.16, and 1.01 MCM, respectively, and in the validation stage were 0.88, 6.22, and 6.01 MCM, respectively. The results also showed that the amount of water demand for the near future period (2021-2040) will increase due to the increase in population, and therefore, the resources in the basin will not be able to meet all assumed needs. The findings showed that the studied system for the near future period (2021-2040) under the reference (continuation of the status quo), SC1 (increase in flow by 10 %) and SC2 (decrease in flow by 10 %) scenarios from the drinking water supply point of view, will result in a shortage of 28.1, 7.3 and 44.3%, respectively, and from the supply of agricultural needs point of view will result in 31.4, 18.3 and 44.4%, respectively. Also, by evaluating the reservoir's performance indicators, it was found that under all assumed scenarios, the system will fail under the condition of supplying 100% and 80% of the needs, whereas the reservoir will be more sustainable by applying the SC1 scenario in comparison with the other two scenarios.   Conclusion To choose the best management and exploitation scenarios, due to existing circumstances and limitations such as time limitation, cost, possible risks to the environment, etc., it is not possible to apply all scenarios in the basins and, thence, it is logical to choose the most suitable scenario. Therefore, software tools can help experts to make decisions by considering all limitations. By examining the results of the reservoir performance indicators, it can be seen that the reservoir will encounter failure in supplying 100 and 80% of the needs in the future period under all scenarios and the sustainability index of the reservoir (remedial stability) in supplying 100%. The needs under the Reference, SC1, and SC2 scenarios will reach 31, 49, and 22%, respectively, and in meeting 80% of the needs, the sustainability index will be slightly higher.

IntroductionRiver flow forecasting has been one of the important challenges of water resources management in recent decades, so many researchers have proposed different methods to improve the performance of forecasting models. In the last decade, artificial intelligence methods have been most widely used in the simulation of various processes, including hydrological processes, due to their flexibility and high accuracy in modeling. However, the results of these methods have always been associated with uncertainty due to several factors such as structure, algorithm, input data, and the type of method chosen for data calibration. One of the methods that can somewhat solve this problem is the uncertainty analysis of the predictions made by these models. Materials and MethodsIn this study, the uncertainty of the results of artificial neural network (ANN) and support vector machine (SVM) models in predicting the monthly flow of the river has been evaluated. In this research, the time series of the monthly flow of the Ghezelozan River using the data of the Bianlu-Yasaul Stream gauging station in 39 years from 1976 to 2014 was used, where 75% and 25% of the data was used for training and testing the models, respectively. In these models, to estimate the monthly flow of the Ghezelozan River, six different input combinations including the flow of one, two, and three months before and the number of months of the flow were used. Then, the accuracy and performance of the models were compared using the coefficient of determination (R) and root mean square of errors (RMSE). Finally, the uncertainty of the results of ANN and SVM models in predicting the monthly flow of the river was evaluated by the Monte-Carlo method using d-factor and 95PPU values. Results and DiscussionThe evaluation of the performance of the ANN model shows that the best performance is related to the combination where the flow of the previous two months and the number of the month of the flow are the inputs of the model so that R and RMSE indexes were obtained as 0.757 and 9.45, respectively. In the SVM model for the monthly river flow series, the best performance is related to the combination where the flow of one, two, and three months ago and the number of months of the flow were the inputs of the model, and the R and RMSE indexes for this input pattern were 0.729 and 10.946, respectively. After studying the uncertainty of the models, the results showed that the ANN model has more uncertainty in the output values compared to the SVM model, and this is while the d-factor of the ANN model, both in the training and test phase, it was more than the SVM model. The comparison of the uncertainty analysis of the results of the ANN and SVM models showed that the SVM model with d-factor and 95PPU values equal to 0.155 and 17.241, respectively, compared to the ANN model with d-factor and 95PPU values equal to 0.993 and 85.470, respectively, has less uncertainty in the output values. So the number of observation data placed in the 95% confidence range (95PPU) of the ANN model compared to the SVM model has increased significantly in both the training and testing phases. Also, the results showed that both models have more uncertainty in the months with a large volume of water, which can be due to the complexity of the process and the involvement of uncertain factors in these months, as well as the effect of factors that are not considered in the structure of predictive models.ConclusionThe results of ANN and SVM models in predicting the monthly flow of the Ghezelozan River showed that although the ANN model with R-value equal to 0.757 and RMSE value equal to 9.45 has a good performance compared to the SVM model with R-value equal to 0.729 and RMSE value equal to 10.946 in predicting the river flow, the results of this model are associated with high uncertainty. The comparison of the uncertainty analysis of the results of ANN and SVM models by Monte-Carlo method showed that the SVM model with d-factor and 95PPU values equal to 0.155 and 17.241, respectively, compared to the ANN model with d-factor and 95PPU values equal to 0.993 and 85.470, respectively, has less uncertainty in predicting the monthly flow of the Ghezelozan River and it is better than ANN model. According to the results of this research, taking into account the fact that advanced artificial intelligence models also have uncertainty, it is necessary to apply these methods in the fields of risk management and future planning to obtain the best performance.

Introduction Accurate quantification of environmental trends must consider variation at different temporal scales when ignoring variation at one scale could lead to incorrect conclusions about variation at another scale. Many environmental monitoring programs collect temporally resolved but irregular time series data to quantify trends for regulatory, management, or research purposes. Conducting a study to understand the trends and predict future conditions in hydrological aspects such as river water quality is essential. During the last decades, river water quality monitoring has increased by measuring several water quality parameters. Therefore, the analysis of water quality trends is important in providing information about changes or variations in water quality through time series data .Furthermore, determining the quality status of water resources is necessary to adopt proper policies to prevent and enhance the reduction of water quality. Additionally, based on this information, it is possible to identify the quality of river water and implement protective measures to improve and manage rivers and drainage basins in a more integrated way. In recent years, the water quality of the Karun River has been affected by various pollutants, including agricultural runoff and industrial wastewater; Therefore, it seems necessary to monitor the quality of the river and the process of its changes over time and place to know the current situation and provide the necessary measures in the future. Therefore, this research analyzed the Karun River's water quality trend over 20 years at four water quality monitoring stations. Materials and methodsTo check the quality of river water in hydrometric stations, the obtained data were assessed from physical and chemical parameters, including Total Dissolved Solids (TDS), Electrical Conductivity (EC), Sodium adsorption ratio (SAR), Na, and Cl in 20 years from 1998 to 2017 in four hydrometric stations including Gotvand, Shushtar, Mollasani, and Ahvaz of Karun river in the wet season (first six months of the water year) and dry season (the second half of the water year). The process of river water quality and inspecting the changes were conducted using the Mann-Kendall test and a geographic information system, respectively. Wilcox's classification was used to check the water quality from an agricultural point of view, as there are relevant standards. By putting the sodium absorption ratio against salinity, Wilcox presents a chart for the water quality assessment for agricultural purposes and can classify water into different classes based on EC and SAR values. Results and DiscussionAccording to the results, the river water salinity in the wet season in three hydrometric stations significantly increased. The increment was at the level of 10% at the Shushtar and Mollasani stations. However, at the Ahvaz station, it rose to the level of five percent. Due to the different annual rainfall amounts during the study period, the river water’s electrical conductivity had relatively large fluctuations in all the investigated stations. The range of electrical conductivity (EC) alterations in the wet season was between 490 and 2800 µS/cm and in the dry season between 397 and 2806 µS/cm. TDS increased in the wet and dry seasons. Moreover, the p-value showed that the value of this statistic was significant at the level of 10% in the Shushtar and Mollasani stations and at the level of five percent in the Ahvaz station. The range of changes in the wet period was between 250 and 1750 mg/liter and in the dry period between 220 and 1700 mg/liter. The alterations in total dissolved solids were more in the wet than in the dry season and did not have a uniform trend. In fact, the decrease or increase in the amount of precipitation affected the intensity and weakness of the TDS amount during the year. ConclusionThe results of the Mann-Kendall test showed that the parameters of TDS, SAR, Na, Cl, and EC increased during the last twenty years, indicating the expansion of the entry of sewage and industrial and agricultural effluents. According to the Wilcox index, water quality for agricultural purposes was in the average category in all the studied stations. Meanwhile, Na, Cl, and TDS parameters were in the average and inappropriate range in some years, being an alarm regarding the low water quality. Additionally, there is a risk of water quality decline in the investigated stations. In general, the watershed of the Karun River is noteworthy due to the presence of a large population, cities, and centers. Specifically, the city of Ahvaz and the heavy steel industries located in this watershed are important fundamental in terms of water consumption and producing pollutants affecting the quality of water resources, which faces many quantitative and qualitative challenges in water. The study of the changes in the water quality parameters of the stations located in the Karun River during the study period demonstrated that the amount of dissolved salts in these rivers increased and caused the reduction of water quality due to incorrect utilization and failure to comply with the principles of river exploitation.

Introduction In recent years, one of the most significant environmental crises has been the phenomenon of wind erosion and dust emission. Wind erosion is considered one of the effective factors in desertification and land degradation in dry regions. The process of wind erosion, due to the transport of soil nutrients along with fine particles, is recognized as one of the limiting factors for soil fertility in many parts of the world. Evaluating this type of erosion and estimating the soil loss requires the installation of various measuring stations. Establishing and equipping these stations and providing the necessary equipment require large costs and a long time. In addition to direct measurement methods in wind erosion, the use of modeling results, especially in combination with remote sensing techniques, to study and predict environmental effects, trends, and risk assessment has greatly contributed to research in the last two decades. Therefore, this study aims to monitor and investigate the warning zones of wind erosion in northwest Golestan Province using the wind erosion hazard index (WEHI) model.                                        Materials and Methods To assess wind erosion in the western part of Golestan Province, the WEHI model was implemented. This model predicts the sensitivity of the landscape to wind erosion by considering a set of surface and climatic thresholds and using a geographic information system (GIS). In this model, wind erosion severity is determined in three classes: low, moderate, and severe, by multiplying wind speed by the percentage of bare soil and dividing it by the percentage of soil moisture percentage. To monitor wind erosion, the normalized difference moisture index (NDMI) was used to evaluate soil moisture, and the modified bare soil index (MBI) was used to assess bare soil. For validation, these indices were compared to field data and plots in each working unit. Additionally, three statistical parameters, Pearson correlation coefficient, coefficient of determination (R2), and root mean square error (RMSE), were employed to calculate the correlation between these indices and ground data. Furthermore, a Markov chain model was used to examine changes in wind erosion classes. Finally, after monitoring wind erosion and considering a threshold value for this model, the area of warning zones during the statistical period was investigated.   Results and Discussion The results obtained from the WEHI model indicate severe wind erosion intensity in the working units of Atark floodplain deposits, saline lands, longitudinal dunes, Barchan dunes, bare lands, and margins area of wetlands. According to the WEHI model, the region was divided into three classes: low (54% frequency), moderate (21% frequency), and severe (25% frequency). The model classified the northern regions into severe and moderate classes, while the southern areas of the region fell into the low wind erosion class. High correlation coefficients between the WEHI model indices based on remote sensing and field data demonstrate the model's ability to monitor wind erosion over time and at different scales. Wind erosion monitoring results showed that the high wind erosion class increased from 59,940.88 ha to 71,698.3 ha, indicating an increase of 11,757.43 ha. Spatial analysis of wind erosion classes indicated that most changes occurred in central areas, with most areas around the Sangartappeh playa and central regions changed to severe wind erosion class, while western, eastern, and central areas changed to the low wind erosion class. Finally, monitoring the warning zones revealed an increase of 41,000 hectares in the areas under warning, in the western, northwestern, and central regions.   Conclusion In this study, the performance of the WEHI model in assessing wind erosion risk in the western part of Golestan Province was confirmed. Although factors such as roughness, soil structure, and organic matter content are not directly considered in the model, they are indirectly incorporated in scoring the percentage of bare soil. To control wind erosion in these areas, planting salt-tolerant species and implementing soil fertility enhancement strategies, such as soil mulching in heavy-textured areas, are recommended. Finally, mechanical operations and the establishment of windbreak networks are suggested for controlling wind erosion in abandoned land units. This research can serve as a useful approach for planning and managing vulnerable areas to wind erosion in northwest Golestan Province.