This study aimed to enhance the accuracy of forest fire susceptibility mapping (FSM) by innovatively applying recursive feature elimination (RFE) with an ensemble of machine learning models, specifically Support Vector Machine (SVM) and Random Forest (RF), to identify key fire factors. The fire zones were derived from MODIS satellite imagery from 2012 to 2017. Further validation of these data has been provided by field surveys and reviews of land records in rangelands and forests; a total of 326 fire points were determined in this study. Seventeen factors involving topography, geomorphology, meteorology, hydrology, and human factors were identified as being effective primary factors in triggering and spreading fires in the selected mountainous case study area. As a first step, the RFE models RF, Extra Trees, Gradient Boosting, and AdaBoost were used to identify important fire factors among all selected primary factors. The SVM and RF models were applied once on all factors and secondly on those derived from the RFE model as the key factors in FSM. Training and testing data were divided tenfold, and the model’s performance was evaluated using cross-validation. Various metrics, including recall, precision, F1 score, accuracy, area under the curve (AUC), Matthew’s correlation coefficient (MCC), and Kappa, were employed to measure the performance of the models. The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones. Notably, the SVM model exhibits significant improvement, achieving an increase of over 10.97% in accuracy and 8.61% in AUC metrics. This improvement underscores the effectiveness of the RFE approach in enhancing the predictive performance of the SVM model.

In developing countries, the interaction between rapid urban expansion and population growth brings forth a host of challenges, particularly concerning essential services like healthcare. While interest in site suitability analysis for identifying optimal hospital locations to ensure equitable and secure healthcare access is on the rise, the absence of a holistic study that encompasses social and environmental aspects in the assessment of hospital site suitability is evident. The objective of this research is to introduce a hybrid methodology that combines Geographic Information Systems (GIS) with Multi-Criteria Decision-Making (MCDM) weighting methods. This methodology aims to create hospital site suitability maps for districts 21 and 22 in Tehran, taking into account socio-environmental factors. In addition to the conventional Analytical Hierarchical Process (AHP) weighting method, this study employs two relatively less-explored methods, the Best-Worst Method (BWM) and Step-wise Weight Assessment Ratio Analysis (SWARA), to enhance the analysis of hospital site suitability. In the SWARA method, there are minimal variations in weights among criteria, indicating that all socio-environmental factors (e.g., distance from existing hospitals, distance from main roads, distance from green spaces) hold significant importance in the decision-making process. Additionally, the findings indicate that the western part of the study area is the most suitable location for the construction of a new hospital. To achieve the average hospital bed availability in Tehran, an additional 2206 beds are required in the studied area, in addition to the existing facilities. Considering the ongoing urban development, population growth, and the potential for natural disasters and epidemics, it becomes essential to enhance the healthcare system by increasing the number of hospitals and available hospital beds. The sensitivity analysis showed that GIS-based SWARA-WLC was the most suitable and stable model for determining hospital site suitability in the study area. This methodology can be adapted for use in other regions and further improved by incorporating additional criteria. In conclusion, the study recommended three specific alternative sites for establishing a new hospital in the study area.

Identifying the underlying factors derived from geospatial and remote sensing data that contribute to forest fires is of paramount importance. It aids experts in pinpointing areas and periods most susceptible to these incidents. In this study, we employ the geographically and temporally weighted regression (GTWR) method in conjunction with a refined continuous invasive weed optimization (CIWO) algorithm to assess certain spatially relevant drivers of forest fires, encompassing both biophysical and anthropogenic influences. Our proposed approach demonstrates theoretical utility in addressing the spatial regression problem by meticulously accounting for the autocorrelation and non-stationarity inherent in spatial data. We leverage tricube and Gaussian kernels to weight the GTWR for two distinct temporal datasets, yielding coefficients of determination (R2) amounting to 0.99 and 0.97, respectively. In contrast, traditional geographically weighted regression (GWR) using the tricube kernel achieved R2 values of 0.87 and 0.88, while the Gaussian kernel yielded R2 values of 0.8138 and 0.82 for the same datasets. This investigation underscores the substantial impact of both biophysical and anthropogenic factors on forest fires within the study areas.