فصلنامه سنجش از دور و سامانه اطلاعات جغرافیایی در منابع طبیعی
سال سیزدهم شماره 4 (زمستان 1401)

 Wetlands are habitats for vegetation and wildlife and because of this, they have a high environmental value. Also, wetlands reduce soil erosion, restore aquifers, store rainwater in a flood event, and provide water for agriculture or livestock. Wetlands are vulnerable to human interventions and changes such as drainage, urban sprawl, infrastructure development, and over-exploitation of groundwater resources. Prediction of the condition of wetlands in the future requires a correct understanding of the evolution of wetlands and identifying their trend of change. Nowadays, Remote Sensing technology is widely used for mapping wetlands, and its ability to monitor the changes in wetlands regardless of the diversity of wetlands has significantly increased the value of this science in this field. Remote Sensing can be an effective means of simulating and predicting wetland degradation processes by providing images at different times and through dynamic spatial modeling. In this study, the changes in the Bakhtegan wetland have been monitored. This wetland has high environmental and tourism importance and its drying affects negatively the living conditions and health of local people as well as tourism in the region. In addition, predictions of precipitation parameters, groundwater level, and temperature have been conducted. For this purpose, the Google Earth Engine platform was used to capture and process images. Google Earth Engine is a platform that can capture and process images in the shortest time and at high speed. In this regard, using Google Earth Engine, changes in the lake water area along with changes in temperature, groundwater level, and precipitation were extracted and monitored. Moreover, a comparison took place between these parameters to determine the changes that have taken place in the lake over the past two decades. To predict the parameters, the changing pattern was predicted and analyzed using the Prophet model. The most important advantage of the Prophet model is its ability to convert discrete data to continuous data to make the best predictions. This method automatically detects the trend of seasonal data and displays the trend of seasonal changes.

 Satellite images were acquired from the Google Earth Engine platform to monitor the wetland. Landsat 7 and 8 images were used for water body extraction, GRACE Data were used for extraction of groundwater level changes, MODIS product was used for extraction of vegetation and wetland surface temperature, and TRMM image product was used to extract precipitation values. An automated water extraction index was used to extract the wetland body water. The groundwater level was extracted from the GRACE sensor. MODIS sensor product was used to obtain the surface temperature time series for the study area. For the extraction of precipitation time series, the monthly cumulative data of the TRMM (3B43V7) satellite with a spatial resolution of 0.25°C was extracted using Google Earth Engine and the trend of changes was evaluated and analyzed. The Mann-Kendall test is one of the most widely used non-parametric tests for detecting meteorological and environmental data trends, which is used to detect a monotonic trend line since this test is a non-parametric method, it does not need that the data follow a normal distribution. The Prophet predictive model is a predictive library developed by Facebook and is available in R and Python programming languages. This library supports additive modeling methods and can properly predict discrete values continuously. This feature is called "Holiday". Another feature of this library is the automatic detection of daily, weekly, seasonal and annual trends. The mean absolute error (MAE), by default, exists in the Prophet library. This error represents a more natural standard than the mean error and unlike the RMSE error, it is unambiguous.

 In the present study, we monitored the Bakhtegan wetland using the Google Earth Engine platform to observe the trend of water level changes in this wetland from 2000 to 2020. In addition, Parameters were also predicted using the Prophet Prediction method which is developed and published by Facebook. By examining this trend, it can be observed that the water level of the wetland has been significantly reduced during two decades. In this regard, the trend of groundwater level, temperature, and precipitation in the area was investigated. Examining these factors, it was found that along with a 58.3% decrease in the water level of the wetland, there was a 260% decrease in the groundwater level of the region, although the amount of rainfall in the region has been less compared to other factors and has been decreased about 29%. Using Mann-Kendall statistical test, the trend of this decline was proved. To predict the parameters, the Prophet model has been able to make predictions for 1500 days as continuous data using discrete data. The output of the model has shown that for rainfall parameters and groundwater level a downward trend is predictable over the next 1500 days which is low intensity for precipitation but with high intensity for groundwater level. Temperature prediction indicated that it has a seasonal trend, and has a high amount of fluctuation within a year, but its annual trend indicates stability in the coming years. The results of the model for the water level of the wetland also show a relatively low upward trend that has a probability of change of ±12.5 Square kilometers. Also, the error of the parameters at the 95% significant level has acceptable accuracy, which indicates the validity of the prediction. An automated water extraction index was used in this study to extract the time series of the water body of the wetland. Using the mean time series extracted, the maximum and minimum wetland’s water body area belongs to 2006 with 629.23 square kilometers and 2014 with 156.82 square kilometers, respectively. The time series of changes in this wetland indicates that the water volume of the wetland has been declining in the last two decades. According to this study, it can be concluded that the trend of changes in the water level of the wetland has been decreasing. The descending changes in the lake based on the trend of changes in groundwater levels indicates a decrease in water volume in the area. Considering that the trend of precipitation changes has been stable, it can have assumed that improper management and excessive use of groundwater may be a reason for lowering the water level of the wetland. Due to the same decrease in the water level of the lake, the temperature has also decreased by about 3°C.

 According to this study, it can be concluded that groundwater levels and precipitation will have a downward trend in the future, which will lead to a decrease in the water level of the wetland, which itself has the potential to fluctuate in the future, and the downward trend continues. With the current trend, the only solution is to plan properly to preserve the wetland. If this trend continues, we will face the destruction of the wetland. Given the monthly trend of the wetland surface, it is suggested not to over-exploit groundwater resources, especially in the summer. For further research, the Google Earth Engine platform can be used without the need to download the images and spend a lot of time and money, to obtain the time series of images. Regarding the prediction, in future studies, the Prophet model can be applied, since it uses discrete data and at the same time provides the desired accuracy.

 Irregular and unplanned urban expansion is known as urban sprawl and is characterized by low-density, transport-driven development, spreading out over large swathes of land towards the fringes of established urban centers. It is generally held that morphological modification of the urban landscape results in rising urban temperatures and the urban heat island (UHI) phenomenon. The biophysical properties of the urban space are determinants of the local urban climate. When there is significant alteration such as the replacement of vegetation and evaporating surfaces with impervious surfaces, the surface energy budget experiences fluxes which leads to warming at the local scale. Most scientists believe that the Earth's temperature has been rising since the 19th century. Meanwhile, a phenomenon called heat island in metropolitan areas (UHI) has caused a faster rise in temperature in these micro-climates, and in the coming years, the rapid urbanization trend will also increase the slope of temperature rise in cities. According to statistics provided by the United Nations, by 2025, more than 80% of the world's population will live in cities, and this will worsen the situation as cities become warmer. Surface temperature (LST) is one of the most important environmental parameters that is affected by land use change. The purpose of this study is to analyze the land use change in the two periods of 1987 and 2019, to estimate and study the changes in LST and NDVI in the same period, and to analyze the impact of land use change in LST and NDVI and the relationship between all three parameters.

In this study, Landsat 8 satellite images were used from the OLI sensor to extract the land use map and vegetation index, and the TIRS sensor was used to extract ground surface temperature for 2019 also Landsat 5 OLI sensor image was used to prepare land use map and vegetation index. Using visible, near-infrared, and infrared bands, the TM sensor was used to extract the surface temperature using thermal bands for 1987. Ecognition software was used to classify the object. Error matrices and related statistics (overall accuracy, kappa coefficient, user and Producer accuracy of each class) were used to evaluate the classification accuracy. Finally, Pearson correlation analysis was used to analyze the correlation between LST and NDVI, and the Contribution index was used to evaluate the impact of land use on surface temperature.

 Investigating land use changes and their relationship with land surface temperature and vegetation index requires determining the type of land use and accurate estimation of land surface temperature and vegetation index. Preparing a satisfied land use map using Landsat satellite images and applying the object classification method Oriented has a relatively high accuracy. The accuracy of land use map classification in 1987, 82.5, and in 2019, 96.1 shows the high accuracy of the land use classification method and land use map. The study of land use changes in 1987 and 2019 in the Givi Chay catchment showed that rangeland use with an area of 1224.18 and 10469.59 square kilometers is the dominant land use, while in 1987, residential use with an area of 66.63 square kilometers and in 2019, water use with an area of 3.77 square kilometers had the lowest area. Also, the most modified use of rangeland use was dryland agriculture (181 square kilometers), which indicates the destruction of rangelands. The results of surface temperature during the 33-year period were evaluated which showed that the average surface temperature in 1987 from 28.39 °C to 38.86 °C and in 2019 from 34.35 °C to 46.62. The temperature has increased so that the average temperature of the whole study area in 33 years has increased by about 7.11 degrees Celsius. This indicates the urban development in the study area. The highest temperature recorded in both periods belongs to dryland agricultural use (38.86 and 46.62 ° C, respectively), which indicates the concentration of heat in these areas. Dryness and harvest at this time can be the main cause of high temperatures of this use. Garden, forest, and water uses showed lower surface temperatures in both periods than other uses. Vegetation areas due to evapotranspiration have a temperature-moderating role and have areas with a minimum temperature in both periods. Water use also has a great effect on reducing the temperature due to its high heat capacity. The use of residential areas compared to rainfed and pasture agricultural uses showed a lower temperature, which can be due to the existence of parks, and gardens that cause evaporation and cooling of the city, as well as factors such as roofing, felt in The reflection of radiant energy has a great share. Rangeland use had high temperatures (36.57 and 44.81 °C, respectively) in both years under study. The reason for the high temperature of this land, according to the study season, which is late June and early July, is an increase in areas free of vegetation or vegetation that is small and scattered. There was also a large negative correlation between LST and NDVI in the two study periods. Rainfed and rangeland agriculture with higher LST have lower NDVI, while vegetation and water have higher NDVI. Aquatic agricultural use, which was mostly observed in the areas around the Givi Chai River, showed lower temperatures due to the presence of moisture and evapotranspiration due to vegetation density. In the study area, suburban areas (gardens) and irrigated arable lands along the Givi Chai River and forests have the highest amount of vegetation index (NDVI) due to their relatively high green biomass, while irrigated areas, rainfed lands, Residential areas, and pastures have the lowest vegetation index. The results of vegetation index analysis for each land use class showed that forests, rainfed agriculture, and rangelands with the highest LST values and the lowest NDVI values while the lowest LST values and higher NDVI values were observed in forest and garden classes. Replacement of vegetation and forests with residential areas causes the conversion of wet soils to impenetrable surfaces, which leads to reduced surface evaporation. Absorbed solar radiation is converted to heat and reflected with higher values of LST. Increased vegetation has reduced the earth's surface temperature, and this is due to the fact that more vegetation leads to more evapotranspiration and transfer of part of the temperature and cooling of the earth's surface. Finally, the calculation of the participation index for each land use class in 1987 and 2019 showed that dryland agricultural use in 1987 and rangeland use in 2019 had the largest share in increasing surface temperature in the study area. According to the time of the selected images, the main reason for this participation can also be attributed to the time of harvest of dryland agricultural products and drying of pastures.

 The results confirm the increase in surface temperature between different land use classes. Rangeland and dry agricultural uses showed higher LST values compared to forests and irrigated agriculture and water areas. High-temperature areas also had low NDVI values. Conversely, low-temperature areas such as vegetation and water had higher NDVI values. In addition, a high negative correlation was observed between LST and NDVI in both study periods. It has also been shown that rangeland and irrigated agriculture have a positive effect on LST, while forests and water have a cooling or moderating effect.

 Fire risk management is a global issue, and urban safety policies must take it seriously. One of the fields of research for controlling urban fires is to identify critical fire points in the region; Insufficient knowledge of these points will cause the occurrence and spread of fire in various areas and uses, delays in controlling it, and causing financial losses and personal injury as well as environmental pollution. Fire risk zoning with the aim of being used in planning and management in urban fire control has not been considered in the study area of this research and no research has been done in this field in the form of research and study plan. The purpose of this study is to determine and identify the criteria for fire risk zoning in the study area, to create a fire risk map based on the logistic regression method and compliance with the fire reality map, and also to present fire management programs and fire crisis management in Kashan.

 The steps and techniques used in this study were performed in six steps. The first step is to identify the effective criteria and indicators. Using library studies, information obtained from authoritative articles, and also through the Delphi method in order to collect the opinions of experts, the Likert scale was used. In the second step, the screening of criteria was done in accordance with the purpose. The effective criteria in this study are vulnerable factors including (population density, industrial units, commercial-warehouse, high-rise buildings, old tissue, and fuel station) as well as the capacity of reducing factors. (Fire station, roads, and hydrant valves). In the next step, the layers were standardized using fuzzy logic. At first, the distance function was performed on the criteria in SELVA IDRISI to determine the distance from each phenomenon. Then, by the fuzzy method, all the criteria determined in the range of zero to 255 were standardized. The type of function used in the fuzzy logic approach is linear, and the selection of the function type and thresholds was based on a review of sources and expert opinion. In order to analyze the spatial relationship between fire incidents that occurred in the city and the role of effective factors in its occurrence, all fire points of the last 10 years in the city from 2010 to 2020 were extracted and turned into a raster map. In the fifth step, a Fire hazard map was prepared using logistic regression. After determining the validity of the logistic regression model using the specified indicators, the fire risk zoning map of Kashan was drawn. In the last step, Chi-Square, ROC, and Pseudo R Square were used to validate the logistic regression model.

Advantages of using the logistic regression model In addition to modeling observations, it is possible to predict the probability of each person belonging to each of the levels of dependent variables and the possibility of directly calculating the odds of variables using the maximum likelihood of maximum model coefficients. Also, compared to other statistical techniques, multivariate such as multiple regression analysis and diagnostic analysis, the dependent variable can have only two variables, one is the probability of an accident and the other is its non-occurrence. In order to analyze the spatial relationship between fire incidents that occurred in the city and the role of effective factors in its occurrence, all fire points of the last 10 years in the city from 2010 to 2020 were extracted and turned into a raster map. The output of the logistic regression model has coefficients between 0 and 1, with a probability higher than 0.5 of a value of one (occurrence of fire) and a probability of less than 0.5 of a value of zero (no occurrence of fire) and thus a boolean map of risk is generated. This logarithmic change causes the predicted probability to be continuous in the range of 0 to 1, and the output of the model to be presented as a spatial prediction map of the probability of destruction. Then, in the logistic regression equation, this layer was introduced as a dependent variable and the effective parameters in fire zoning were introduced as an independent variable. After entering the data into the logistic regression statistical model, model coefficients were extracted using effective parameters in IDRISI software. After determining the validity of the logistic regression model using the specified indicators, a fire risk zoning map of Kashan was drawn. Finally, in terms of fire risk potential, the study area was divided into 5 classes: very low, low risk, medium, very high, and high risk. The area of each of the 5 classes was obtained in hectares and the percentages were 87475.47, 4669.03, 132115, 1116.33, 788.96 hectares, and 90.94, 4.85, 2.19, 1.16, 0.82 percent, respectively.

 The value of 0.95 obtained from ROC indicates a very high correlation between the independent and dependent variables. The value of the qi index is twice equal to 110836.07; Since its value is much higher than the threshold value, then the null hypothesis of all coefficients is also rejected. The value of the PR2 test in this study was 0.47, so the logistic regression model had an acceptable fit.

Mangrove forests are one of the important plant ecosystems established across the intertidal zones and consist of evergreen species. According to Food and Agriculture Organization (FAO) reports, the area of world mangrove forests is almost 14.6 million ha and more than 40% of them are located in Asia. Indonesia has the largest mangrove forests with 2.3 million ha with the highest richness. Moreover, Iran with approximately 10,000 ha of mangrove forests in northern parts of the Persian Gulf and Oman Sea is one of the countries with mangrove ecosystems. The ecological and socio-economic importance of mangrove forests is evident to researchers and managers, however, an annual quantitative and qualitative decrease in these forests happens due to natural (e.g., storm) and anthropogenic (e.g., overexploitation) factors. Therefore, it seems essential to develop a practical approach in order to protect the present sites and improve the management, monitoring, and assessment of mangrove forests. The first step in every management and conservation plan in mangrove forests is mapping their spatial distribution and monitoring the spatial changes. It is important to find efficient methods for mensuration and assessment of temporal and spatial changes of mangrove forests for their efficient management and conservation. Field measurement difficulties in these ecosystems result in the rapid development of remote sensing data in mangrove mapping. However, previous studies have shown that common vegetation indices are not efficient in mangrove classification because of the high greenness and moisture content of leaves. Assessing the spectral signature of mangrove forests, researchers have designed specific indices for mangrove classification on satellite imagery. Since the mangrove indices have been recently developed, their efficiency in similar conditions has not been investigated, while they have been compared to some vegetation indices or individually investigated in case studies. Additionally, the mangrove indices have not been applied in mapping mangrove forests of southern Iran. Therefore, the aim of this study was a comparison of eight mangrove indices in mapping mangrove forests of Nayband Gulf (Bushehr province), Sirik (Hormozgan province), and Govatr Gulf (Sistan-Baluchestan province) on Landsat 8 imagery.

 Previous studies have shown that mangrove forests in Iran are distributed in 21 sites in 10 cities in Bushehr, Hormozgand, and Sistan-Baluchestan provinces. In order to assess the mangrove indices, a region was selected in each province. Mangroves in Nayband Gulf are concentrated in Bidkhun and Basatin Creeks. In Sirik, mangroves are located in the Azini wetland, and in Govatr Gulf, they are established in Baho and Govatr Creeks. Low- and high-tide Landsat imagery of each study area related to 2020 was downloaded. After pre-processing, the images were used to compute MI (Mangrove Index), NDMI (Normalized Difference Mangrove Index), CMRI (Combined Mangrove Recognition Index), MDI (Mangrove Discrimination Index), MMRI (Modular Mangrove Recognition Index), L8MI (Landsat 8 Mangrove Index), and MVI (Mangrove Vegetation Index). Moreover, low- and high-tide images were implemented in making SMRI (Submerged Mangrove Recognition Index). The classification of soil, water, and mangrove was performed by a support vector machine (SVM) algorithm. In addition to common accuracy criteria (i.e., overall accuracy, Kappa coefficient, mangrove producer's and user's accuracies), the results were evaluated by area under the curve (AUC) of receiver operating characteristic (ROC).

 The efficiency of 10 mangrove indices was evaluated in similar conditions. The number of selected indices was eight; however, two of them (i.e., L8MI, MDI) were calculated two times, once with SWIR1 and once with SWIR2, and in total, 10 mangrove indices were used in three regions to classify mangrove forests. Between the indices, SMRI was selected as the most efficient mangrove index. One of the likely reasons for the efficiency of the index can be the application of low- and high-tide imagery to detect mangroves. In addition to PAmangrove and UAmangrove, the overall accuracy and kappa coefficient of soil, water, and mangrove of SMRI were more than other indices. The results of MDI and L8MI showed that they were more efficient with SWIR2 in Nayband Gulf. One of the reasons that likely caused the result can be urban areas and non-mangrove vegetation cover in Nayband Gulf. However, both indices were more accurate in mangrove discrimination when calculated with SWIR1 in Govatr Gulf. Investigation of AUC values proved that SMRI was the most efficient index between all studied indices in mangrove mapping within three study areas. The AUC of mangroves in Nayband Gulf, Sirik, and Govatr Gulf were 0.94, 0.92, and 0.93, respectively. The area of mangrove forests was estimated in Nayband Gulf (260.1 ha), Sirik (1049.2 ha), and Govatr Gulf (649.5 ha) using SMRI.

 In general, the results showed that all mangrove indices were reliable in mangrove discrimination in three study areas and no weak results were achieved. The AUC values of mangroves using SMRI were more than 0.9 in three regions and the index was known as the most reliable index in all regions. The outcome in the study areas revealed that the efficiency of mangrove indices was less in Nayband Gulf compared to two other regions (The AUC of 0.6 for NDMI and L8MI-1). The area of mangrove forests in Nayband Gulf, Sirik, and Govatr Gulf was estimated on Landsat 8 imagery of 2020. The results indicated that between the study sites Sirik (1049.2 ha) and Basatin Creek (43.3 ha) had the highest and the lowest area covered by mangroves. It is suggested to use SMRI in other mangrove forests in southern Iran to approve the achievements of the present study.

A drought crisis is a dry period of climate that can occur anywhere globally and with any climate. Although this crisis starts slowly, it can have a serious impact on health, agricultural products, the economy, energy, and the environment for a long time to come. Drought severely threatens human livelihood and health and increases the risk of various diseases. Therefore, modeling and predicting drought is one of the most important and serious issues in the scientific community. In the past, mathematical and statistical models such as simple regression, Auto-regression (AR), moving average (MA), and ARIMA were used to model the drought. In recent years, machine learning methods and computational intelligence to model and predict drought have been of great interest to scientists. Computational intelligence algorithms that have been previously considered by scientists to model drought include multilayer perceptron neural network, RBF neural network, support vector machine, fuzzy, and ANFIS methods. In this research, the purpose of modeling and predicting drought is by using three neural network algorithms, including multilayer perceptron, RBF neural network, and generalized regression neural. The drought index used in this research is the standardized precipitation index (SPI). In this research, the wavelet technique in combination with artificial neural network algorithms for modeling and predicting drought in 10 synoptic stations in Iran (Abadan, Babolsar, Bandar Abbas, Kerman, Mashhad, Rasht, Saqez, Tehran, Tabriz, and Zahedan) have been used in different climates and with suitable spatial distribution throughout Iran.

This study, initially using monthly precipitation data between 1961 and 2017, SPI drought index in time scales of 3, 6, 12, 18, 24, and 48 months through programming in soft environment MATLAB software implemented. The results of this step were validated using the available scientific software MDM and Drinc. Then, prediction models were designed using the Markov chain. In this study, a total of six computational intelligence models, including three single models of multilayer perceptron neural network (MLP), radial basis function neural network (RBF), and generalized regression neural network (GRNN), and three hybrids wavelet models with these three models (WMLP-WRBF-WGRNN) have been used to model and predict the SPI index in 10 stations of this research. In implementing all these six models, the MATLAB software programming environment has been used. In this study, four types of discrete wavelets were used, including Daubechies, Symlets, Coiflets, and Biorthogonal. Due to the better performance of the Dobbies wavelet, this type of wavelet was used as a final option in the research. In the Daubechies wavelet used between levels 1 to 45, level 3 showed the best performance among different SPI time scales; therefore, the Daubechies level 3 wavelet was used in all hybrid models of this study. After training all six algorithms used, the evaluation criteria of coefficient of determination (R2) and root mean square error (RMSE) was used to measure the difference between actual and estimated values.

The results of this study showed that computational intelligence methods have high accuracy in modeling and predicting the SPI drought index. In the first stage, the results showed that the individual MLP, RBF, and GRNN models, if properly trained, have close results in modeling and predicting the SPI drought index. In the next step, it was observed that the wavelet technique would improve the modeling results. In using the wavelet technique in combination with three single models MLP, RBF, and GRNN, the choice of wavelet type is also more effective in modeling, so in this research, the first of the four types of discrete wavelets Daubechies, Symlet, Qoiflet, and Biorthogonal in combination with Three single models of this research were used and the results of these four types of wavelets showed the relative superiority of the Daubechies wavelet over the other three wavelets. In using the Daubechies wavelet, since this wavelet has 45 times and the choice of order was also effective in modeling, it was observed by testing the wavelet 45 times that the 3rd wavelet, in general, has higher accuracy in all time scales of SPI index, 3, 6, 12, 18, 24 and 48 months and also in all three algorithms MLP, RBF, and GRNN. Therefore, in this research, the third-order Daubechies wavelet was used in all three algorithms of this research, as well as in all time scales. The results showed that combining the wavelet technique with all three models MLP, RBF, and GRNN will improve the results. The research graphs showed that for the quarterly time scale, the values obtained from the single model prediction in MLP and RBF modeling have a somewhat one-month phase difference compared to the hybrid model, while in the GRNN model, this prediction difference is negligible. The modeling results for both single and hybrid modeling modes indicate that there is no phase difference between the single and hybrid modeling methods in time scales of 6, 12, 18, 24, and 48. For the 12- and 24-month time scales, the single GRNN model had more fluctuations and errors in SPI monthly modeling and forecasting, while the hybrid model in these two-time scales had much better behavior in monthly modeling and forecasting. Distribution diagrams of data related to observational SPI of Abadan station showed that the modeling results for single and hybrid modes in 3 and 6-month time scales are less accurate than other time scales and fit line separation, and its uncertainty is higher than others. However, in all neural network models and in all time scales, the hybrid method has shown more accuracy. The numerical results of the study indicate that in all SPIs and stations under study, the differential values of R2 are positive, which indicates higher values of R2 in the hybrid model than in single neural network modeling, which indicates an improvement in hybrid modeling compared to individual models. Also, the differential values of RMSE are negative in all studied models and stations, which indicates that the amount of RMSE in predicting hybrid models is lower than individual neural network models. In the research graphs, it can be seen that the amount of differences in RMSE and R2 indicates a greater difference in time scales 3 and 6 than the time scales 12, 18, 24, and 48, which somehow goes back to the nature of the data of these time scales. The most significant improvement in R2 and RMSE is from the 3-month low to the 48-month high, respectively.

 From the findings of this study, it can be concluded that artificial neural network algorithms are efficient methods for modeling and predicting the SPI drought index. The use of wavelets in all three models of artificial neural networks will also improve the results. It can also be concluded that for better modeling of the SPI drought index, it is necessary to select the optimal wavelet type and order. From the results of this study, it can be concluded that the wavelet technique has a greater impact on the lower time scales, i.e., 3 and 6 months, than the higher scales, i.e., 24 and 48 months.

 In recent decades, with the acceleration of urbanization and the growth of migration to cities, the physical structure of cities has undergone extensive changes. To implement these changes, regardless of the ecological capacities and requirements of sustainable urban development, cities are facing many challenges. One of these challenges is determining the appropriate areas for the physical expansion of the city for the establishment of urban development. One of the most reliable methods to determine the appropriate directions and areas for urban development by considering environmental conditions and characteristics is the land suitability assessment. Such an assessment greatly contributes to sustainable land use and solving environmental problems caused by rapid urban development. Land suitability assessment aims to identify the most appropriate spatial pattern for future land uses considering the ecological potential of the area. Since many criteria need to be considered and analyzed in the selection of appropriate lands for urban development, it is necessary to use the most effective techniques to identify the best locations for future urban expansion. The Geographic Information System is such a technique, having its most useful application in the land suitability assessment method. In setting the importance of the criteria used and computing the weights of factors, GIS tools must be integrated with other methods to improve the results. Given that, the present study attempted to evaluate the land suitability to determine suitable areas for the establishment of urban development of Bam city through the integration of the Multi-Criteria Decision-Making approach, Fuzzy Logic, and Geographic Information System.

 To achieve the objectives of this study, with the help of a group of experts, and an extensive review of the related literature, all the criteria and sub-criteria essential to the establishment of urban development were identified as the first step. To this end, a questionnaire was designed and distributed among the group of experts and they were asked to express their opinions on the identified criteria and sub-criteria. To determine the required sample size and population, Morgan’s sampling table was employed. Consequently, 9 criteria and 13 sub-criteria were selected for the land suitability assessment in this study.Multi-Criteria Decision-Making method and Expert-Choice software were used to compare and weigh the previously determined criteria and sub-criteria. As the next step, all the data layers were standardized by the fuzzy logic method using ArcGIS software. The scale of the maps used in this research is 1:100000 and the resolution of digital layers is 90×90 meters. After assigning calculated weights to each data layer, they were overlaid using the Weighted Linear Combination method and fuzzy sum technique.

The results from MCDM analysis revealed that three sub-criteria namely distance from major faults, distance from drinking water wells, and soil texture had the highest weights among other factors at 0.235, 0.117, and 0.114, respectively. The inconsistency calculated for the pairwise comparison in this study was 0.07, which is below the 0.1 thresholds. Analysis of the final raster suitability map, resulting from overlaying data layers, showed that the highest and the lowest pixel values were 0.481 and 0.07, respectively. To perform a more accurate analysis, the final suitability map was classified into four suitability classes (medium, low, very low, and undevelopable) indicating that 24% of the studied area equivalent to 189965.2 hectares, categorized as having medium suitability, 34% low equivalent to 268854.3 hectares, 22% very low equivalent to 178695.7 hectares, and 20% undevelopable equivalent to 160762/3 hectares for the establishment of urban development. The medium suitable areas are mainly located in the east, northwest, and to a lesser extent in the center, mostly away from the major fault lines, while the areas of very low suitability and undevelopable are mainly located in the west and south of the area studied. Due to their proximityto protected areas, mountainous, fault lines, and hills, these areas do not demonstrate the appropriate suitability for the establishment of urban development.

 This study was conducted to identify and determine suitable areas for the establishment of urban development in Bam city using a combination of the Multi-Criteria Decision-Making approach, Geographic Information System, and Fuzzy Logic technique. All the criteria and sub-criteria, used to conduct this study, have been determined using a questionnaire and considering the environmental conditions and socio-economic characteristics of the studied area. As a result, 9 criteria including water resources, climate, topography, geology, soil, areas under the Department of Environment Management, roads, population centers, and land use, and 13 sub-criteria including distance from surface and groundwater resources, climate, wind speed, slope, altitude, distance from the main faults, geology, soil texture, distance from protected areas, distance from roads, distance from built-up urban areas and land use were selected for this study. Expert Choice and ArcGIS software were employed for pairwise comparison and standardization and overlaying data layers. It was found that 24% of the studied area equivalent to 189965.2 hectares can be categorized as medium suitability for the establishment of urban development. Based on the final results, it is concluded that the integration of the Multi-Criteria Decision-Making approach, Fuzzy Logic, and Geographic Information System can provide sufficient tools to determine the areas suitable for urban development and present a detailed analysis of these areas according to the characteristics of the area for future planning.

Knowing the extent and severity of drought in a region and planning to reduce its effects is one of the most important principles of management in regional planning to combat drought. Drought monitoring and management in an area using remote sensing data and satellite imagery as a suitable tool in temporal and spatial monitoring of agricultural drought has always been the focus of regional managers. The purpose of this study is to investigate the efficiency of remote sensing data and satellite images in the zoning of agricultural drought in the years 2000 to 2021 in Neyriz city. For this purpose, three vegetation condition index (VCI), temperature condition index (TCI), and vegetation health index (VHI) were extracted from MODIS satellite images for the desired time period. The results of these indices were compared with the values of the standard precipitation index (SPI) in time series of 1, 3, 6, 9, 12, 18, 24, and 48 months.

The study area in this study is Neyriz city located in the southeast of Fars province with an area of 10787 Km2 and is part of one of the watersheds of Bakhtegan Lake. The average altitude of the region is 1798 meters, the maximum altitude of the region is 3235 meters and the minimum altitude is 1476 meters above sea level. The average annual rainfall, temperature, and evapotranspiration of the basin are 204.8 mm, 19 °C, and 1058.3 mm, respectively. In this study, the rainfall data of Neyriz synoptic station during the statistical period of 22 years (2000-2021) were used to calculate the SPI index in time series of 1, 3, 6, 9, 12, 18, 24, and 48 months. Then, 3 indices based on satellite imagery including vegetation condition (VCI), temperature condition index (TCI), and plant health index (VHI) were extracted from Modis measured data for May month from 2008 to 2021 and with standard precipitation index (SPI) were compared in time series of 1, 3, 6, 9, 12, 18, 24 and 48 months based on the correlation coefficient. Finally, the most appropriate drought index based on satellite images was selected from the indices and the percentage of drought classes was determined based on the selected index in the study area.

 The results of calculating the values of the SPI index using DIP software in time series of 1, 3, 6, 9, 12, 18, 24, and 48 months in the statistical period of 2000-2021 showed that the trend of curves in some years is decreasing, in some years it has been increasing and in most years it has been almost normal. On average, the incidence of droughts and wetlands according to the SPI index in different time series during the statistical period is 68% in normal conditions, 18% in wet conditions, and 16% in drought conditions. The results of calculating the SPI index in different ground series were analyzed based on data from synoptic stations and remote sensing data. For this purpose, the values obtained from all indices based on satellite images including VCI, TCI, and VHI are extracted and compared and their correlation coefficient with the ground SPI index in time series 1, 3, 6, 9, 12, 18, 24, and 48 became. VCI index values in 2000 have the lowest value (32.1%) and in 2020 have the highest value (41.3%) during May. Therefore, based on the value of the VCI index during the statistical period in 2008, severe drought conditions prevailed in the region, and in 2020, more favorable vegetation and wetting conditions prevailed in the region. The results obtained from the SPI index in different time series also confirm the fact that the most severe drought and wet season during the statistical period studied in the two years 2000 and 2020, respectively, in the region. In addition, the VCI index is most correlated with the SPI index in different series and the SPI relationship is significant with the all-time series. TCI index has no significant correlation with any of the time series and has a weak correlation with the SPI index in different time series. In addition, the VHI index has a significant correlation with time series of one, three, six, and twelve months only at the level of 5% and its correlation with the SPI index in different time series is much less than the VCI index. Spatial distribution of drought intensity based on the values of the studied indices in May 2008 showed that the eastern parts of the region, which is also located at low altitudes, have been more affected by drought. The study of the area affected by drought classes based on the TCI index in 2008 showed that there is no very severe drought in the study area, 11% of the area suffers from moderate drought, 22% of the area suffers from mild drought and 67% has no drought. According to the VCI index, the level of severe drought on the date is 0.14%, severe at 0.33%, moderate at 17%, mild at 77%, and no drought at 6%. Also, according to the VHI index, there is no severe or severe drought in the study area only 9% of the area suffers from moderate drought and 91% does not have a drought. Spatial distribution of drought severity based on the values of the studied indices in May 2020 shows that in the study area according to the TCI index there is no very severe drought on the target date and 5% of the area has moderate drought, 22% drought Mild and 73% lack drought. According to the VCI index on the target date, the percentage of drought is very severe 0.5%, severe 0.8%, moderate 5%, mild 31%, and no drought 62%. Also, according to the VHI index in May 1999, 0.2% of the area has a moderate drought, 30% has a mild drought and 69% has no drought. According to this index, there is no very severe drought in the region.

 Drought is one of the most important natural disasters that affect millions of people and large parts of the world every year. This phenomenon, which starts slowly and has a creeping nature, can cause a lot of damage to agriculture, natural resources, and the environment. Knowing how to occur and preparing drought severity maps based on new methods has a very positive and serious impact on drought management in an area. One of the new and widely used methods in temporal and spatial monitoring of drought is the use of drought indices based on satellite images, which has recently been used in drought-related topics. The results of the SPI index analysis showed that in most time series, the most severe drought and wet season during the study period occurred in 2000 and 2020, respectively. The results also showed that the temperature condition index (TCI) has no significant correlation with any of the time series and has a weak correlation with the SPI index in different time series. The plant health index (VHI) with time series of one, three, six, and twelve months has a significant correlation at the level of 5% and its correlation with the SPI index in different time series is less than the vegetation condition index (VCI). The value of the VCI index in 2008 had the lowest value (32.1%) and in 2020 had the highest value (41.3%) during May, which is consistent with the results obtained from the SPI index in the region. A comparison of the results of this study with the results of other researchers shows the excellent accuracy of remote sensing indices in drought monitoring. Therefore, the use of remote sensing technology in drought monitoring in areas that do not have meteorological stations or have meteorological stations with low density or scattered is recommended.