Landslide susceptibility is significant for disaster mitigation and sustainable land-use planning in geologically unstable areas, like Kodaikanal, South India. This present study examined the predictive capabilities of five machine-learning algorithms, Random Forest (RF), Gradient Boosting (GB), k-Nearest Neighbors (k-NN), Extra Trees (ET), and stacking ensemble model, along with a Frequency Ratio (FR) method, to create a landslide susceptibility map. The 70% of landslide and non-landslide points were used for training, and the remaining 30% testing to evaluate the model accuracy. The final susceptibility map was divided the area into five categories: very low, low, moderate, high, and very high. Zones with very high (7%), high (8%) were mainly located on steep slopes. The model performance was evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and receiver operating characteristic (ROC) curves. Overall, the GB showed the lowest MSE, RMSE, and MAE values, indicating the highest prediction accuracy, and RF also performed strongly, ET had moderate performance, and k-NN had weaker prediction. The Stacking ensemble has higher predictive accuracy with an AUC-ROC of 0.96%. This integrated approach supports early warning system, and sustainable land management in landslide-prone areas of Kodaikanal.

The study developed the Agricultural Performance Index (API) by applying Sentinel-1, C-band, Synthetic Aperture Radar, Ground Range Detected, log scaling (SAR-GRD-LS) for crop monitoring. The parameters like normalized crop growth (0.81–0.85), normalized crop health (0.24–0.83), and normalized soil moisture (0.73–0.89) are estimated by the SAR using the cloud platform Google Earth Engine (GEE), and the result of the API is 0.62–0.83. The validation has been done by ground-based Kharif yield data using ROC-AUC (0.93) and correlation (0.84), and cross-checking is done by flood index and ground photographs; along with that, the sensitivity analysis has been performed for understanding the influencer. API helps farmers with crop health monitoring and customizes their fertility utilization, which will be cost-effective precision agriculture.

The transportation sector is a significant contributor to global CO2 emissions, driving the urgent need for innovative approaches to reduce environmental impact. This study explores the application of machine learning (ML) models, specifically Random Forest and XGBoost, to predict vehicular CO2 emissions using openly available data from the Canadian Government Open Data Portal. Key vehicle attributes—such as engine size, fuel consumption, and transmission type—were analyzed to identify the primary drivers of emissions. Through exploratory data analysis and feature selection, eight critical features with the highest correlation to CO2 emissions were identified and used in model training. Both ML models demonstrated high predictive accuracy, with R2 values of 0.98, explaining 98

Flooding is the most pervasive hydro-meteorological hazard in South Asia, with climate change amplifying both frequency and severity. This study integrates Participatory Geographic Information Systems (PGIS) with remote-sensing and geospatial datasets to assess village-scale flood risk in two highly affected blocks, Nagrakata and Dhupguri, within Jalpaiguri District, West Bengal, India. Using community-derived data from 48 households across 24 villages after the October 2025 floods, the research combines lived experiences with modelled flood hazard and exposure data. The PGIS survey revealed that 100% of households experienced post-flood challenges, averaging 5.2 per household, with unsafe drinking water, sanitation failure, and housing damage as dominant issues. Statistical hotspot analysis (Getis-Ord Gi*) identified a high-burden cluster along the Jaldhaka–Diana river corridor, while bivariate mapping demonstrated that high impact was not limited to river-proximate villages but also occurred where poor drainage and inadequate protection intensified vulnerability. Integrating PGIS indicators with population density and modelled hazard produced an Exposure-Adjusted Priority Index, delineating five priority classes and highlighting critical zones for intervention. The results show that participatory GIS provides a robust complement to model-based flood assessments, revealing micro-scale heterogeneity, social vulnerability, and infrastructural gaps invisible in remote sensing data. The study underscores PGIS as an analytical bridge between top-down flood models and community realities, supporting evidence-based local resilience planning and more inclusive flood governance in the Himalayan piedmont region.

Landslides pose a recurring threat to human settlements, infrastructure, and ecosystems in the seismically active Chamoli district of Uttarakhand, India. This study presents a comparative landslide susceptibility assessment using three distinct models: Frequency Ratio (FR), Shannon Entropy (SE), and Analytical Hierarchy Process (AHP). Twenty-four geo-environmental and anthropogenic conditioning factors were integrated to develop landslide susceptibility maps (LSMs) tailored to the region’s complex terrain. Multicollinearity analysis was conducted to ensure statistical robustness, and model performance was validated using the Receiver Operating Characteristic (ROC) curve and the Area Under the Curve (AUC) metric. The FR model achieved the highest predictive accuracy (AUC = 0.819), followed by AHP (0.789) and SE (0.594). While FR demonstrated superior data-driven reliability, AHP offered interpretability grounded in expert judgment. Thematic analysis revealed slope, geology, rainfall, proximity to roads, and land use changes as key landslide triggers. Susceptibility zonation showed significant spatial variability across models, with high-risk zones concentrated near road corridors, riverbanks, and deforested slopes. The study underscores the value of methodological triangulation in landslide prediction and recommends FR as a reliable framework for future hazard planning. These findings provide actionable insights for disaster mitigation, infrastructure planning, and sustainable land use management in Himalayan regions.

Human survival depends on ecosystems, which are an essential component of the earth’s environment. Researchers and professionals are increasingly interested in ecosystem health issues and their nature-based solutions, but disparities persist. A total of 1273 research articles were used after screening and cleaning procedures, ranging from 1st January, 2015, to 31st December, 2024, from the Dimension Core Collection database, and VOSviewer was utilized for scientometric analysis of the development of ecosystem health research and their nature-based solutions after SDGs’ 17 goals were adopted by the UNO to pinpoint the research development. The reviewed findings showed that ecosystem health assessment research is multidisciplinary. The two most influential journals were “The Science of the Total Environment” and “Sustainability”. The main research forces were Chinese, United States, Australian, and United Kingdom researchers and institutions. The University of Chinese Academy of Sciences was the most productive university, followed by Wageningen University Research and the Institute of Geographic Sciences and Natural Resources Research. The ecosystem health assessment review is showing three development trends: (1) Gradually increased phase (2015–2019); (2) Phase of development (2020–2022); and (3) Phase of fast development (2023–2024). The present study offers useful insights for assessing the effectiveness of ecosystem health studies and assists in identifying relevant research works on ecological health research and, ultimately, determines future study directions.

Agricultural drought has become a significant concern for Assam’s Tinsukia district, where climate variability and extreme weather events increasingly threaten crop productivity and rural livelihoods. Traditional drought assessments often lack spatial and temporal precision, which remote sensing indices can address, providing timely and region-specific drought insights. This study employs the Vegetation Condition Index (VCI), Temperature Condition Index (TCI), and Vegetation Health Index (VHI) to evaluate drought conditions from Landsat imagery for the years 2000, 2010, and 2022. The VCI indicated fluctuating vegetation health, with extreme drought conditions covering 41

Access to safe drinking water is vital for human health, as it reduces the risk of waterborne diseases, enhances hydration, and supports overall well-being. This study evaluates health improvements before and after the Jal Jeevan Mission (JJM) across the Community Development (CD) blocks of Murshidabad district. The study identifies significant variation in arsenicosis prevalence, reflecting disparities in exposure and vulnerability. It further assesses perceived health outcomes among implemented and non-implemented JJM households using the Health Belief Model (HBM). The findings show no significant differences in perceived susceptibility and benefits, but notable differences in barriers and health outcomes between JJM-implemented and non-implemented households, indicating potential health improvement with access to safe drinking water. Increased health awareness and adoption of preventive behaviours are associated with perceived health outcomes, as households become increasingly attentive to water-related risks and adaptive practices. This study could benefit stakeholders, regional planners, and policymakers.

Forest fires are among the most severe natural hazards threatening ecological sustainability in the Eastern Mediterranean, with Syria being a prominent example where ongoing conflict has undermined forest management and monitoring systems. Despite numerous global studies on forest fire susceptibility, conflict-affected areas in the Eastern Mediterranean remain underrepresented in the scientific literature due to limited data and complex environmental and social conditions. In particular, few studies have systematically compared multiple machine learning algorithms for predicting forest fire susceptibility in these regions. To address this gap, this study evaluates the performance of six machine learning algorithms—Extreme Gradient Boost (XGBoost), Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), K-Nearest Neighbor (KNN), and Linear Regression (LR)—using 3,589 fire events and 13 conditioning factors in the Latakia governorate, western Syria. Results indicate excellent predictive performance for all models, with XGBoost achieving the highest AUC of 0.993, followed by RF (0.992), KNN (0.977), MLP (0.975), SVM (0.968), and LR (0.963). These findings provide a robust basis for supporting fire management and mitigation strategies in Syria and offer insights applicable to other conflict-affected regions of the Eastern Mediterranean.

Understanding rainfall variability and its relationship with the ENSO (El Niño Southern Oscillation) and IOD (Indian Ocean Dipole) is crucial for enhancing regional climate predictions and agricultural planning. ENSO is driven by unusual Sea Surface Temperature (SST) anomalies in the equatorial zone of the Pacific Ocean, while IOD arises due to the discrepancy in temperature in the western and eastern Indian Ocean. Both phenomena exert significant influence on the Indian monsoon system. However, their effects on rainfall vary across regions and seasons, making it challenging to establish straightforward correlations. Hence, the Partial Correlation co-efficient is used to assess the influence of ENSO and IOD on Indian rainfall. The findings reveal that ENSO and IOD collectively modulate the Indian monsoon. For instance, El Niño events typically weaken monsoon rainfall, while La Niña events tend to enhance it. Similarly, a positive IOD phase strengthens the monsoon, whereas a negative IOD phase reduces rainfall. To explore the characteristics of Indian rainfall, various methodologies such as Innovative Trend Analysis (ITA), Mann–Kendall (MK), modified Mann–Kendall (mMK), Percent Bias (PBIAS), Sen’s slope estimator ( Q_ij ), Precipitation Concentration Index (PCI), and Rainfall Seasonality Index (RSI) are employed. These tools offer a comprehensive insight into rainfall trends and variability. The teleconnection between ENSO, IOD, and Indian rainfall has significant implications for agriculture, disaster management and efforts to mitigate the negative impacts of climate variability on water resources and food security. Improved predictions of rainfall variability, concerning ENSO and IOD, can help formulate strategies to cope with water stress and enhance food production, especially in regions heavily dependent on monsoon rains.

The global water shortage highlights the importance of groundwater as a vital freshwater source, though its distribution is influenced by various surface and subsurface factors. This study investigates the Bankura Sadar Subdivision in West Bengal, covering 2598 sq. km, to identify groundwater potential zones (GWPZs) using GIS-based techniques. The region faces groundwater stress, with declining levels in certain areas, particularly as it is located in a semi-arid region. Twenty-one parameters, including groundwater depth, elevation, slope, geology, geomorphology, drainage density, land use and land cover, long-term average annual rainfall etc. were analysed using two Multi-Criteria Decision Analysis (MCDA) models: the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and Combined Compromise Solution (CoCoSo). TOPSIS was chosen for its ability to rank multiple alternatives based on conflicting criteria, while CoCoSo provided an alternative aggregation approach. TOPSIS classified the region into five zones: very low, low, moderate, high and very high groundwater potentiality, covering 2.43

This study focuses on the sustainable management of non-timber forest products (NTFPs) in the Narmada, Dang, and Panchmahal districts of Gujarat, India, emphasizing carbon sequestration and carbon credits. NTFPs such as medicinal plants, fruits, nuts, and resins play a crucial role in the local economy and biodiversity conservation. Accurate mapping and assessment of these resources are essential for implementing sustainable management and conservation strategies. Advanced spatial analysis techniques, including geographic information systems (GIS), remote sensing, and logistic regression models, were employed to analyze the spatial distribution of NTFPs. High-resolution Sentinel-2 satellite imagery and field survey data were integrated to create detailed spatial maps while, logistic regression models evaluated environmental factors like soil type, elevation, and climatic conditions affecting NTFPs distribution. The study identified that environmental variables such as litter cover, elevation, and NTFPs type are critical in determining the distribution of NTFPs, with NTFPs type accounting for 68

There are growing indications that Northeast India is feeling the effects of climate change, but in-depth studies on temperature shifts across the region are still quite limited. In this work, we looked at how both annual and seasonal mean temperatures have changed at 14 different locations between 1990 and 2024, using satellite data. To get a well-rounded understanding, we applied several statistical methods to capture not just long-term warming but also any sudden changes in temperature patterns. The Mann-Kendall and modified Mann-Kendall tests pointed to noticeable warming in number of locations, and Sen’s slope helped us measure how quickly these changes are taking place. We also used the innovative trend analysis to catch more complex, non-linear trends, and the percent bias method showed that recent decades have generally been warmer than the earlier ones. Among the 14 sites, places like Guwahati, Dibrugarh, and Cherrapunji stood out for clear warming trends, especially during the monsoon and winter months. Change point detection tools like the Pettitt and Buishand tests highlighted major shifts around 2012–2013 in several areas. At the same time, stations such as Agartala and Aizawl showed more gradual warming, but the upward trend was still evident. These results make it clear that warming is unfolding in different ways across the region sometimes gradually, sometimes in sharp jumps. Understanding these local patterns is essential for developing effective responses to climate-related risks in this ecologically and climatically sensitive part of India.