Background and objectives: In preventing fire and reducing their effects, forest fire management is important. The purpose of this study was to provide a map of fire hazard potential and determine the effective factors on forest fires using GIS and artificial neural network for the cities of Ali-Abad, Ramayan, Azadshahr, Minoodasht and Kalaleh in Golestan province. Materials and methods: The criteria used in this research included forest and rangeland lands, temperature, rainfall and evapotranspiration, slope, aspect, elevation of the sea level, distance from urban areas, distance from rural areas, distance from agricultural land and distance from the road. Vegetation map, digital elevation map and land use map provided from the forests of the rangelands and watersheds of the country, and the maps of temperature, rainfall, and evapotranspiration obtained from the organization of the meteorological for the whole of Iran. The influence of each parameter on fire ignition was determined by collecting of 37 samples from burned area and 37 sample from not burned area. 15 fire points that were not used in the modeling process was used For Validation the potential fire hazard map. For formation network between criteria and fire occurrence used of Multilayer perception (MLP) with Hyperbolic Pattern Algorithms. To this end, 70% of the data was used to train the network, 15% of the tests were tested and 15% of the data were used to validate the results. Results: The results were shown raining and distance from the road had must be influenced on forest fire ignition. Validation test showed that the best network was obtained in run 4 and epoch 450 with 0. 0038 Final Mean Square Error (FMSE) in training steps. Furthermore, about 95 percent of area burned and 84 of unburned areas has been properly classified. Finally, forest fire hazard maps was obtained based on each criteria weight. Results showed this network with 2 hidden layers and 12 neurons in each of them has best accuracy, and correlation coefficient (R) was 0. 80. Furthermore, after determining the location of the 15 forest fire points on the map of potential fire hazard, the results showed that 7 points located in the area were very high fire risk, and 6 points in the area with a high fire risk, and 2 points located in the area with a low fire hazard. Conclusion: According to the findings of this research, roads and rain reduction have a growing impact on the development of fire and natural forest fire managers need to adoption the necessary measures to better manage the forest and rangeland areas in these situations to prevent the occurrence or spread of fire.

Road is one of the most important and obvious extractable feature in satellite imagery. Automatic road extraction from satellite imagery has many advantages such as updating data bases by spending less time and cost. The aim of present research is the automatic extraction of forest roads map using Liss_IV sensor imagery of IRS_P6 satellite. Because of frequent irregular objects in forest, roads are very complicated for extracting automatically. Therefore, the designed methodology for this research was in a way that can deal with this problem. For this aim, image of the study area was classified into two road and non road areas by a fuzzy logic. Then, morphological mathematic algorithm was used to extract the existed roads. By this method, forest roads map was extracted automatically with 88% overall accuracy. Also, morphological mathematic algorithm showed a great ability for recovering road line that was hidden or was cut off under forest canopy.

Forest areas are among the most important natural and ecological resources on the Earth and are considered as one of the main pillars of sustainable development in any country. Fires ruins almost 5500 hectares of Iran‘ s forests yearly. In this research, firstly, the fire points were identified using the fire data of Forest Organization in combination with MODIS sensor data between 2012 and 2017. Due to the fact that more than 75% of fires were happened in the hot season of the year (June, July, and August), the data of the three months was used for modeling. Then, the effective parameters in fire occurring were evaluated and the dependent parameters were removed. Accordingly, two methods, including multiple linear regression and multivariate adaptive regression spline were studied to predict the fire risk. Some important parameters including the root-mean-square error (RMSE), R2, the correct estimation percentage of fire and non-fire points, and error distribution were used to evaluate. After modeling, it was found that the multivariate adaptive regression spline has better performance— where its RMSE of test data was 0. 1628, its R2 of test data was 0. 893, and its correct estimation percentage of test fire points and test non-fire points was near 94% and 88% respectively, as well as its error distribution was better than the other method...

In recent years, the Kandovan-Chalus axis in the north of the country (in Mazandaran province) has experienced numerous dangerous floods. Geological and topographic features, precipitation and human intervention have made the Kandovan-Chalus axis susceptible to potential flood risks. In addition to natural factors; lack of dredging, lack of proper watershed management and unprincipled human interventions have led to an increase in flood risks in the researched area. The aim of this research is to zone flood-prone areas and determine the priority of factors affecting their occurrence using the random forest algorithm in the Kandovan-Chalus axis. For this purpose, 9 land use indicators were selected: distance from the river, slope, height, failure to observe the river boundary, river discharge, waterway network, rainfall, and lack of river dredging. After determining the variance inflation factor and tolerance coefficient, in the next stage, modeling was carried out by entering the data related to the effective factors into the ARC/MAP10.2 software. Then, the random forest algorithm was used to determine the role of the effective factors in the occurrence of floods in the region. Finally, a flood risk zoning map was prepared in three very dangerous, medium-risk, and low-risk zones in the ARC/MAP10.2 environment. The results show that based on the flood potential map, the risk of flooding in the region is about 261.43 square kilometers of the region, 151.1 square kilometers of the region are considered low-risk areas, 118.3 square kilometers of the region are considered medium-risk areas, and about 118.3 square kilometers

Background and objectives: Spatial prediction of fire risk and preparing the forest fire risk map across the natural areas are among the ways that can be used to prevent and to manage fire. The aim of this research was zonation of forest fire risk in Golestan National Park using non-parametric algorithms, namely Artificial Neural Network (ANN), Support Vector Machine (SVM) and Random Forest (RF).Materials and methods: About 100 occurred fire points were considered for modeling the fire risk. The effective factors on fire occurring including vegetation types, physiographic, climatic, and human factors were identified and their relevant maps were prepared from different sources. To modeling purposes, initially the zone was divided into 1-ha levels of decision-making and modeling and then the pixel values of the effective factors on classes of fire occurring, across the 1-ha levels, were extracted and standardized. Based on non-parametric algorithms, fire risk was modeled with 70 percent of the fire points, as training samples. The prepared forest fire risk map was zoned in terms of four classes of low-risk, medium-risk, high-risk and dangerous. The classification accuracy of the maps, resulted from this modeling, was assessed through the overall classification accuracy given 30 percent of the remained fire points.Results and Conclusion: The results indicated that RF algorithm, with the overall accuracy of 75%, was the best algorithm in predicting the fire risk compare to other ones. Likewise, after matching the fire risk occurring with the results gained from algorithms, it turned out that all algorithms were able to classify the area properly in terms of the fire risk, as more than 80 percent of fire points were placed in the high-risk and dangerous classes.

In this research, the possibility of using Rapid Eye satellite imagery for mapping the crown distribution of oak trees in Zagros forests was investigated in the Dashtebarm forest area of Kazeroun, Fars province. In this study, data quality was investigated geometrically and radiometrically and geometric correction of the images was done using a linear method and using precision ground control points. In order to investigate the use of artificial bands obtained from appropriate processes in the classification process, images of appropriate plant spectrum indices were created by mapping the bands and images of the main components using the principal components analysis (PCA index). The vegetation map of crowns of trees was measured by measuring the crowns of trees in square sample samples with an area of 400 square meters in a randomized way. 70% of samples were selected as educational sample and 30% of the rest were randomly selected. Two-point and polygonal classifications with two maximum likelihood algorithms and support vector machines were performed on the original image, the processed bands, and the main image composition of the processed bands. The results of the accuracy assessment of the maps in this study showed that the highest overall accuracy and Kappa coefficient were 98. 52% and 0. 97, respectively, in the point of processing with processed bands and maximum likelihood algorithms, as well as by composition of the original image with processed bands and support vector machines algorithm (SVM). Also, in the polygonal classification, the highest overall accuracy and kappa coefficient of the maps classified using the processed bands were 87. 50% and 0. 75 with the maximum likelihood algorithm and 90. 78% and coefficient Kappa 0. 81 has been supported by the car engine algorithm. In general, the results of this study showed that Rapid Eye images are suitable for preparing the crown distribution map of forest trees in Zagros forests.

In order to evaluate the capability of ETM+ remotely- sensed data to provide "Forest- shrub land- Rangeland" cover type map in areas near the timberline of northern forests of Iran, the data was analyzed in a portion of nearly 790 ha located in Neka- Zalemroud region. First, ortho-rectification process was implemented to correct the geometric errors of the image, which yielded 0/68 and 0/69 pixels of RMS error toward X and Y axis, respectively. The original multi-spectral bands were fused to the panchromatic band using PANSHARP Statistical module. The ground truth map was prepared using 1 ha field plots in a systematic- random sampling grid. Vegetative form of trees, shrubs and rangelands was recorded as a criterion to allocate the plots. A set of channels including original bands, NDVI and IR/R indices, and first components of PCA was used for classification procedure. Automatic band selection command was used to select the appropriate channel set. Classification was carried out using ML classifier on both original and fused data sets. It showed 67% of overall accuracy and 0/43 of Kappa coefficient in original data set. Due to the results present presented above, it's concluded that ETM+ data has an intermediate capability to fulfill the spectral variations of 3 form- based classes, in the studied area. Furthermore, applying complementary methods to minimize the background spectral effect is proposed for future studies.

Background and objectives: Rangeland fires have devastating effects on the landscape, performance and services of rangeland ecosystems. Despite the efforts of experts, decision makers, stakeholders and government agencies in recent decades to reduce the effects of fire, its number and related economic and human losses are increasing worldwide. One of the most important measures to reduce the damage caused by fire is to predict and prevent the occurrence of fire, which is based on determining the fire prunes. The purpose of this study is to identify and determine areas sensitive to fire in the winter rangelands of Mohammad Gholi in Arak city of Markazi province. Methodology: The studied rangelands with an area of 3100 hectares with arid to semi-arid climate are located 15 km southeast of Arak city in Markazi province. The altitude of the region is 1900 to 2500 meters (a. s. l) and the average annual rainfall is 225 mm. The thermal extremes of the region are-11 (February) to 35 degrees Celsius (August). In order to zoning the fire risk prune in the region, 9 factors of slope, direction of slope, altitude, geology, land use, distance from the road, distance from the waterway network, soil science and vegetation percentage were used. Fire events were considered as a basis for predicting future fires. Non-fire areas were also identified and selected. For backup zoning and fire prediction, two support machine models (SVM) and random forest model (RF) were used. In order to evaluate the results of these models, the statistical indices of coefficient of explanation (R2: correlation between observational and estimated data), the square root of the mean squared error (RMSE: deviation of predicted values ​​from observed values) and efficiency coefficient (CE: coefficient of efficiency: between infinite negative and 1, the closer to one indicates the higher the performance of the model in forecasting) was used. The output of RF and SVM models is between 1 and zero, which is divided into 5 (floors) of the area with very low to very high fire hazards. The models will identify the most important variables affecting the past fire and then zoning the fire risk in the region. Results: Vegetation, direction, slope and altitude variables had the greatest impact on fire, respectively, and the variables of geology, land use, distance from the road, distance from the waterway network and soil science were removed from the modeling process due to inappropriate and insignificant coefficients. Were. The most sensitive slope floor in case of fire is 12-25% and above and floor 8-12 has the lowest fire incidence. Also, the highest fire occurred at an altitude of 2100-1900 meters and the lowest at an altitude of 2500-2400. In terms of direction, the southwestern and southern slopes had the most and the northern slopes and the non-sloping direction had the least fire events. Vegetation, by providing the necessary fuel, has shown the highest incidence of fire in the coverage of 50-75% and the lowest in the coverage below 25%. According to the results of the implementation of the models, the support vector machine model with a coefficient of efficiency of 0. 86 and an error of 3. 55 in the test phase is a more accurate model in this study. The results also showed that in terms of fire risk, 11% of the rangelands were in the very low category, 16% in the low category, 35% in the medium risk category, 17% in the high risk category and 21% in the very high risk category are located. Conclusion: High slopes and heights with maximum vegetation (suitable fuel source) in the area and lower grazing intensity have the highest incidence of fire. While in low cover due to insufficient fuel and in low slopes due to change of Rangelands to agriculture, fire is less likely to occur. The area to the south also provides suitable fuel for the fire by receiving more solar heat, dominant cover of Astragalus and dense cover of annual grasses. Among the selected models, the vector support machine model had better performance in zoning and fire risk prediction than the random forest model, which is due to its ability to integrate many input variables without changing them, and Establishing nonlinear relationships between variables identifies effective factors and can provide valuable information for fire control and prevention to rangeland managers.