This study aims to evaluate the effectiveness of machine learning techniques for predicting groundwater fluctuations in arid and semi-arid regions using data from the Gravity Recovery and Climate Experiment satellite mission. The primary objective is to develop accurate predictive models for groundwater level changes by leveraging the unique capabilities of GRACE satellite data in conjunction with advanced machine learning algorithms. Three widely-used machine learning models, namely DT, SVM and RF, were employed to analyze and model the relationship between GRACE satellite data and groundwater fluctuations in South Khorasan Province, Iran. The study utilized 151 months of GRACE data spanning from 2002 to 2017, which were correlated with piezometer well data available in the study area. The JPL model was selected based on its strong correlation (R² = 0.9368) with the observed data. The machine learning models were trained and validated using a 70/30 split of the data, and their performance was evaluated using various statistical metrics, including RMSE, R² and NSE. The results demonstrated the suitability of machine learning approaches for modeling groundwater fluctuations using GRACE satellite data. The DT model exhibited the best performance during the calibration stage, with an R² value of 0.95, RMSE of 0.655, and NSE of 0.96. The SVM and RF models achieved R² values of 0.79 and 0.65, and NSE values of 0.86 and 0.71, respectively. For the prediction stage, the DT model maintained its high efficiency, with an RMSE of 1.48, R² of 0.87, and NSE of 0.90, indicating its robustness in predicting future groundwater fluctuations using GRACE data. The study highlights the potential of machine learning techniques, particularly Decision Trees, in conjunction with GRACE satellite data, for accurate prediction and monitoring of groundwater fluctuations in arid and semi-arid regions. The findings demonstrate the effectiveness of the DT model in capturing the complex relationships between GRACE data and groundwater dynamics, providing reliable predictions and insights for sustainable groundwater management strategies.

Air pollution is a significant concern for both managers and disaster decision-makers in megacities. Considering the importance of having access to correct and up to date spatial data, it goes without saying that designing and implementing an environmental alerting and monitoring system is quite necessary. A standard infrastructure is needed to utilize sensor observations so as to be ready in case of critical conditions. The use of sensor web is regarded a fundamental solution to control and manage air quality in megacities. The proposed system uses the SWE framework of OGC, the reference authority in spatial data, to integrate both sensors and their observations, while utilizing them in the spatial data infrastructure. The developed system provides the capability to collect, transfer, share, and process the sensor observations, calculate the air quality condition, and report real-time critical conditions. For this purpose, a four-tier architectural structure, including sensor, web service, logical, and presentation layer, has been designed. Using defined routines and subsystems, the system applies web sensor data to a set of web services to produce alerting information. The developed system, which is assessed through sensor observation, measures the concentration of carbon monoxide, ozone, and sulfur dioxide in 20 stations in Tehran. In this way, the real-time air quality index is calculated, and critical conditions are sent through email to those users, who have been registered in the system. In addition, interpolation maps of the observations along with time diagrams of sensors’ observations can be obtained through a series of processes, carried out by the process service.

Detection of aquifer vulnerable areas can highlight preventive actions for groundwater contamination. Different models have been presented for the evaluation of vulnerability that one of the most regular and well-known models of the overlapping index as the SINTACS-LU (Soggiacence, actual infiltration, non saturated zone, typology of overburden, hydrogeological characteristics of the aquifer, hydraulic conductivity, topographic Slope) model was considered in this research. In fact, this model has been extended based on the impact of land use parameters in the vulnerability evaluation. Purpose of this study is the qualitative evaluation of Birjand plain aquifer vulnerability using the SINTACS-LU model. For this, the Birjand plain aquifer in the statistical periods of 2013-2018 has been evaluated. According to the results of this assessment, the SINTACS-LU vulnerability zoning map reveals that 15 percent of the studied region has the vulnerability of medium to high, 75 percent of the area has a high vulnerability, and 10 percent has the too high vulnerability. In order to the verification of the SINTACS-LU model, the relationship between the vulnerability index and the obtained nitrate concentration values from 21 groundwater samples were assessed. The correlation coefficient between the SINTACS-LU vulnerability index and the nitrate concentration was 75 percent, which indicates the appropriate correlation of this model with the nitrate concentration as the indicator of the groundwater contamination.

The occurrence of landslides has always been a problem in spatial planning as an environmental threat. The aim of the present study was to zoning landslide sensitive areas in the Urmia Lake Basin and to investigate the correlation between the characteristics of the region and the amount of landslide. To achieve these purposes, the situation of landslide sensitive areas in the Lake Urmia Basin was investigated using a combination of Fuzzy and Analytical Network Process (ANP) methods. The criteria' weight is obtained using the ANP, fuzzy Membership command, linear function, the fuzzy weight of the sub-criteria, and their fuzzy membership degree (between 0 and 1) are calculated. The weighted raster layers were combined using the Gamma overlay function. As a result of this operation, a classified map has been obtained which shows that 16.6% of the area has a very high landslide susceptibility, and the highest area of the study area, i.e., 27.32%, has a relatively high landslide susceptibility. The results of the present study were compared with the data recorded using field observations at landslide sites. The results showed that out of 182 points collected, 148 points (equivalent to 81.31%) correspond to class 6 (very high landslide susceptibility) and class 7 (extremely probable). The results of this research can be used in crisis management, identifying the suitability of the region in terms of geomorphological features, identifying environmental and natural hazards.