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...

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.

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.

Extended Abstract Background: Human activities, climate variability, and environmental stress have strongly affected forest ecosystems worldwide. Forest fires are among the major factors of global ecosystem destruction. Fires in the forest, whether of human or natural origin, have been raised as a serious crisis in recent years. Hence, fire risk assessment plays an important role in forest fire management because knowing where the highest risk is essential to minimize threats to resources, lives, and property. Integration of spatial information from different sources using statistical analysis in the GIS environment is a suitable tool for managing and spreading forest fires, which is one of the main natural hazards in northern Iran. Therefore, it is necessary to prepare a fire risk assessment map for the planning and protection of forests. Methods: The current practical research concerning its nature is a combination of documentary, descriptive, and quantitative model-based methods regarding the research method. In this study, fuzzy and hierarchical (AHP) logic models were combined to investigate the risk of forest fire in Mazandaran province in five classes, very high, high, medium, low, and very low, respectively, using four main criteria and nine sub-criteria, namely topography (height, slope, direction, and rivers), climatic factors (peak temperature and precipitation), human factors (residential areas and the network of communication roads), and biological factors (vegetation). To obtain the net vegetation cover, the Normalized Difference Vegetation Index (NDVI) was applied to the Sentinel-2 satellite image set in a 5-year period (2017-2022) in the GEE web system. The height, slope, and slope direction maps of the study area were prepared from the digital elevation model (DEM) of 12.5 m from the ALOS AVNIR-2 dataset. The distance from rivers, residential areas, and the road network was calculated using the Euclidean distance tool in ArcMAP software. The geographic location of meteorological synoptic stations was obtained from the Meteorological Organization, and its information was used as meteorological input data. In the ArcMap environment, a map of average annual precipitation and maximum temperature was prepared from synoptic stations through interpolation for the period from 2007 to 2021. Based on this modeling method, experts' opinions were used for the relative importance and priority of criteria and sub-criteria in the risk of forest fire in the study area to obtain the fuzzy weight of criteria and sub-criteria. Based on the weighting coefficients applied in the present plan, the final weights of the criteria and sub-criteria affecting forest fire from the highest to the lowest weights belong to the topographical, biological, climatic, and human criteria. Among the sub-criteria, the highest and lowest weights belong to vegetation and slope, respectively. The consistency rate (CR) for the matrices of the affecting factors is equal to 6.25%, which is less than 10%, actually indicating that the weight of the criteria is proportionate and reliable. The highest weights were obtained for the vegetation cover and the slope direction, and the lowest weights belonged to the distance from the river and the slope. Finally, the fire risk assessment map was prepared by combining the fuzzy maps of the sub-criteria in GIS. Results: Overall, medium to very high fire risk potential was found in 72% of the studied area. From a total area of about 2373189 hectares, very low (8.4%), low (18.3%), medium (23.66%), high (25.62), and very high (24%) vulnerability rates were identified in Mazandaran province. Higher fire potential was detected in the East and Southeast parts than in other parts of the study area. The aforementioned fuzzy layers clearly show that the height, slope, and amount of precipitation are low and the density of residential areas and the network of communication roads are high in these parts, with high temperatures. In fact, these factors have increased the risk of fire in these areas. In the present study, the highest fire potential was observed at low altitudes, which could have resulted from the concentration of human activities at low altitudes. Moreover, most fires occurred on low slopes in the studied area. The distance layer from waterways also plays a dual role in the occurrence of fire. The results of the model show an inverse correlation between the distance from roads and fire potential. Based on the results of the fuzzy AHP model, the probability of fire increased with the decrease in precipitation and the increase in annual temperature. A decrease in the amount of precipitation causes a decrease in soil moisture and vegetation, elevating the possibility of fire. On the other hand, the increase in temperature causes the drying of vegetation and reduces humidity, thereby increasing the possibility of fire. Conclusion: It can be concluded that preparing a fire risk assessment map can help managers and planners in identifying areas with high potential and in crisis management in vulnerable areas. The obtained fire risk assessment map can be used as a decision-making support system to predict future fires in the study area.

Forest fire causes devastating destruction of forest as an important part of human environment, releases damaging atmospheric emissions and can be a threat to public health. It is one of the instances of natural crises and how to cope with it is an example of crisis management. Identifying the influential factors in the occurrence and propagation of forest fire and allocating resources in a proper manner considering risk zone mapping and their relationship with geographical and vegetation aspects are crucial for fire prevention and preparedness policies. Therefore, analytical process hierarchy (APH), geographic information systems (GIS), and remote sensing (RS) methods were applied to prepare fire risk maps for 30000-hectare-wide protected area of Manesht and Ghalarang in Ilam province. Investigating high risk zones and geographical aspects of the region, several naturally occurring fire breaks were recognized and used to divide this area into 33 subdivisions in order to decide about proper action plans on fire times. Results showed that human-started fires were the major cause of forest fire in this region. Among the many factors considered, vegetation thickness had very dominant effects on fire propagation. The findings were used to give some instructions on fire crisis management in the protected area including the three phases of preliminary action or activity before occurrence (prevention scheme), action during on occurrence (collation scheme), and action after occurrence (renovation scheme).

A study was conducted to evaluate fire risk using environmental- and human-induced factors in District Three of Neka-Zalemroud forests. For this purpose, a range of effective sub-criteria including physiographic, biological, climatic and human variables were applied. The historical fire map in study area was additionally used. It was overlaid on the spatial map of each sub-criterion to explore the correlation of the weighted high-risk classes with the historical fire occurrences. Fire risk potential map was provided based on weighted overlay of all effective sub-criteria in five classes. The historical fire map was consequently overlaid on fire risk potential map. Results showed that vegetation type and density, distance from river and the averaged relative annual humidity were associated with the highest effects in fire occurrence. Results also demonstrated the agreement of high-risk areas in the potential fire risk map with the historical fires, which supports the high validity of the applied method to assess the fire risk across the study area.

Fire in natural resources is one of the crises that causes irreparable damage to ecosystems and the environment every year. The purpose of this research is to attempt to study areas of risk aversion and to prepare a map of forest fire hazard area by integrating topographic data and other additional information from a GIS system for Golestan province. In order to carry out this research, firstly, with the removal of the recorded data related to the situation of fires occurred in 2009 and 2010, the domain of all natural resources of Golestan province was carried out. In order to identify areas with high fire potential, static parameters were used to control the burning of forest forests (elevation, slope, slope direction, land use / land cover, evaporation rate). Each of the static parameters is divided into different classes And to each class, using bachelor's knowledge and review of research, ground data and the results of the above studies are weighted from one to ten. In the following, by using overlap of these layers with different weights, areas with high fire potential were identified for the forests of Golestan province. Finally, all weights were summed up, the final weight was obtained and a fire hazard map was prepared. The Arctic GIS9. 2 software has been used to generate a fire hazard map. Also, The fire risk index (FRSI), the Normalized Difference Vegetation Index(NDVI), and the zoning map, have a fire hazard in the risk category (very low to high) ). The results showed that most of the fires occurred in hardy and covered with forested areas, as well as in the forested areas with a crown and an intermediate cover, and in the next stage, in the woods and shrubland areas. In calculating the calculation of fire density in altitudes, the results showed that approximately 90 percent of fires occurred in average altitudes between 700 and 1500 meters. Overall, the findings showed that 90 percent of burns occurred continuously in areas With fire hazard, 30% in hazardous areas and 60% in extreme areas, so that its Galikesh, Minoodasht, , Azadshahr has high risk of high fire.

Fires, in the forests and parks become causative to fall away to natural resources largeness of locale sector Kohgiluyeh and Boyer-Ahmad forests. The purpose of this research is, Forest fire risk zone mapping using utilization from of topography criteria and sub criteria (slope, distance from the river, height, direction of inclination), Physical (type of vegetation, vegetation density, soil moisture), human (distance from roads, distance from the village), and climate (average annual temperature, precipitation, relative humidity, and windiness direction), that criterions connection became distinctive relationship between criteria Fuzzy DEMATEL technique. Network analysis process, was used to weighting all parameters in Super Decision software. by fuzzy logic method, maps is fuzzed, and in the GIS environment getting Forest fire risk zone final mapping. results of this study expressing that among of the criteria, was the topographic criteria (0.423) and the between sub-criteria's t slope map is high weight and human criteria, biological and climatic getting from right to left value of%0.257, %0.194 and%0.124. the percentage area classification mapping forest fire potential by Boolean operator for is in series, PRODUCT PROCESSOR value of 5%, AND 35.68%, Gamma 34.82%, and SUM 34.84%. Too model FIRE RISK using images Landsat 8, digital elevation model, slope and windiness direction provide for the region. Fire classification map was prepared using fire point data for 4 years (93-96).Comparing its results with the results of the FUZZY ANP model and FIRE RISK indicates a high degree of compliance in areas with high fire risk.

Forest fires in Iran and particularly in the northern forests had destructive effects on the physiognomy of these forests. Recognition, prevention and controlling the Socio-economic destroys caused by natural hazard are the main objectives of administrative and educational organizations. One of the methods for prevention of forest fires is mapping the probability risk zones. In this study, map of fire probability risk for Golestan national park was prepared using regression logistic method and GIS. The effective factors on fires including climate, topography, vegetation and human factors were prepared in the GIS environment by different methods and sources. The occurred forest fires map was gathered and generated as a Boolean map. The logistic regression modelling was done using effective factors as independent variables and the occurred forest fire map as dependent variable. The obtained Pseudo R2= 0.3121 and ROC= 0.9132 from model indicate that regression logistic could modeled forest fire probabilities on the study area. The probability fire map was classified to four low, medium, high and sever dangerous classes. The obtained forest fire probability map was assessed using the some unused occurred fire points. The assessment results showed that more of occurred forest fire points were in the medium and high dangerous classes.

Fires, in the forests and parks become causative to fall away to natural resources largeness of locale sector Kohgiluyeh and Boyer-Ahmad forests. The purpose of this research is, Forest fire risk zone mapping using utilization from of topography criteria and sub criteria (slope, distance from the river, height, direction of inclination), Physical (type of vegetation, vegetation density, soil moisture), human (distance from roads, distance from the village), and climate (average annual temperature, precipitation, relative humidity, and windiness direction), that criterions connection became distinctive relationship between criteria Fuzzy DEMATEL technique. Network analysis process, was used to weighting all parameters in Super Decision software. by fuzzy logic method, maps is fuzzed, and in the GIS environment getting Forest fire risk zone final mapping. results of this study expressing that among of the criteria, was the topographic criteria (0.423) and the between sub-criteria's t slope map is high weight and human criteria, biological and climatic getting from right to left value of%0.257, %0.194 and%0.124. the percentage area classification mapping forest fire potential by Boolean operator for is in series, PRODUCT PROCESSOR value of 5%, AND 35.68%, Gamma 34.82%, and SUM 34.84%. Too model FIRE RISK using images Landsat 8, digital elevation model, slope and windiness direction provide for the region. Fire classification map was prepared using fire point data for 4 years (93-96).Comparing its results with the results of the FUZZY ANP model and FIRE RISK indicates a high degree of compliance in areas with high fire risk.