Climate change may cause severe hydrological droughts, leading to water shortages which will require to be assessed using high-resolution data. Gravity Recovery and Climate Experiment (GRACE) satellite Terrestrial Water Storage (TWSA) estimates offer a promising solution to monitor hydrological drought, but its coarse resolution (1°) limits its applications to small regions of the Indus Basin Irrigation System (IBIS). Here we employed machine learning models such as Extreme Gradient Boosting (XGBoost) and Artificial Neural Network (ANN) to downscale GRACE TWSA from 1° to 0.25°. The findings revealed that the XGBoost model outperformed the ANN model with Nash Sutcliff Efficiency (NSE) (0.99), Pearson correlation (R) (0.99), Root Mean Square Error (RMSE) (5.22 mm), and Mean Absolute Error (MAE) (2.75 mm) between the predicted and GRACE-derived TWSA. Further, Water Storage Deficit Index (WSDI) and WSD (Water Storage Deficit) were used to determine the severity and episodes of droughts, respectively. The results of WSDI exhibited a strong agreement when compared with the Standardized Precipitation Evapotranspiration Index (SPEI) at different time scales (1-, 3-, and 6-months) and self-calibrated Palmer Drought Severity Index (sc-PDSI). Moreover, the IBIS had experienced increasing drought episodes, e.g., eight drought episodes were detected within the years 2010 and 2016 with WSDI of −1.20 and −1.28 and total WSD of −496.99 mm and −734.01 mm, respectively. The Partial Least Square Regression (PLSR) model between WSDI and climatic variables indicated that potential evaporation had the largest influence on drought after precipitation. The findings of this study will be helpful for drought-related decision-making in IBIS.

The purpose of this study was to investigate the taxonomic diversity, richness, and distribution patterns of Poaceae in relation to abiotic factors in the Jhelum district of the Pakistan Himalayas. We used a random sampling technique from 80 grids within 240 sites with a rich diversity of wild grasses and 720 quadrates in triplets from each site across the Jhelum district between 2019 and 2021 to collect data on grass species and the associated environmental factors and conditions. After evaluating the important value index for each plant taxa and for the environmental data, we analyzed the data using ordination and cluster analysis techniques. Fifty-two Poaceae taxa from twenty-nine genera were recorded within the study area. From a total of 52 recorded Poaceae species, 45 were native and 7 were invasive species. The life form (biological) showed the dominancy of 27 therophyte species, followed by 24 hemicryptophyte species, and 1 geophyte species. Microphyll had the leading leaf size spectra (27 species), followed by nanophyll (12 species), macrophyll (10 species), and leptophyll (3 species). The trend of the life cycle was the maximum (27 spp.) during the monsoon season, followed by spring (11 spp.), winter (8 spp.), and summer (6 spp.). The leading genera were Setaria with 9.61% of the species, followed by Panicum, Cenchrus, and Brachiaria with 7.69% of the species. Aristida and Echinochloa made up 5.76% of the species while Chrysopogon, Digitaria, Eragrostis, Pennisetum, and Poa made up 3.84% of the species. Other genera recorded single species. The leaf size spectra of grasses were dominated by microphylls (50%) followed by nanophylls (23.07%), macrophylls (19.23%), and leptophylls (7.69%). On the basis of the importance value index, the most dominant species was Cynodon dactylon (68), followed by Dichanthium annulatum (58), Brachiaria ramose (38), Dactyloctenium aegyptium (37), Eleusine indica (35), Saccharum bengalense (33), and Cenchrus biflorus (28). Two-way cluster analyses classified the grasses into three plant community associations based on the indicator plant species. Soil parameters as subsamples were tested for moisture, pH, EC, OM, macronutrients (CaCO₃, N, P, and K), and saturation while the ordination analysis revealed that they had a significant (p ≤ 0.002) effect on vegetation associations. Overall, this study contributes to a better understanding of the influence of environmental factors on the composition and associations of grass species and the development of scientifically informed management solutions for the ecological restoration of degraded habitats in this Himalayan region.

This study presents a novel multi-model fusion approach for enhancing land surface temperature (LST) recovery and spatial resolution improvement. We compare and integrate linear Ridge regression and non-linear Random Forest (RF) ensemble models to retrieve high-resolution LST from thermal infrared (TIR) remote sensing data. Initially, LST is computed using a single-channel (SC) algorithm at 30m (SCLST-30m) and 90m (SCLST-90m). The SCLST-90m is then enhanced through a multi-model fusion framework that combines both ensemble models with high-resolution predictor features, including surface reflectance, multiple indices (SAVI, NDVI, NDWI, NDBI, and UI), and Digital Elevation Model (DEM). The fusion approach integrates the complementary strengths of both models, with RF capturing non-linear relationships and Ridge regression providing stability in linear patterns. Cross-validation between SCLST-30m and the fused LST demonstrates superior performance, with the integrated approach achieving higher accuracy than individual models. Validation against in-situ LST confirms the effectiveness of the fusion framework, yielding R² values of 0.89 and 0.84 for RF and Ridge models respectively. The RMSE values for SCLST-30m, RF-DLST, and Ridge-DLST are 0.37 K, 0.38 K, and 0.45 K, respectively. These results demonstrate the effectiveness of our multi-model fusion approach in achieving accurate recovery and resolution enhancement of LST, offering valuable insights for environmental monitoring and urban planning applications.

Sustainable land-use planning and catastrophe risk reduction depend critically on landslide susceptibility mapping. The complex, nonlinear interconnections of environmental and human elements cause terrain instability and challenge conventional prediction methods. In this work, we offer a DeepLabV3+-based deep learning framework coupled with Geographic Information Systems (GIS) and Multi-Criteria Decision Making (MCDM) methods for spatial prediction of landslide risk, over the Dubai coastal and urban region (covering approximately 4,000 km²). The approach uses an annotated dataset for semantic segmentation and high-resolution satellite images from the Mohammed Bin Rashid Space Center (MBRSC). On Google Colab with GPU acceleration, the model is trained and verified and then further improved for computational efficiency on a Mac M1 machine. Our results show an Overall Accuracy (OA) of 91.3%, a Mean Intersection over Union (IoU) of 82.5%, and an F1-score of 88.4%, demonstrating strong classification performance throughout a range of land cover types. The Confusion Matrix analysis highlights strong segmentation accuracy for water bodies (94.2%) and structures (92.4%). Considerable misclassification between roadways and unpaved terrain results from spectral similarities. Furthermore, the perclass Dice Coefficient analysis confirms that the model can efficiently discriminate intricate topographical patterns. Especially in fast-expanding areas like Dubai, UAE, it provides a scalable solution for landslide susceptibility mapping, catastrophe risk management, and sustainable urban design. Future work will explore multi-sensor data fusion, real-time inference, and applying explainable artificial intelligence (XAI) techniques to enhance model interpretability in dynamic terrain settings.

In many areas of the world, particularly in arid and semi-arid regions, groundwater is the primary source of fresh water, and it supplies around one-third of the world's fresh water. Agriculture is the primary economic sector on the coast in the southern district (Nowshera). More food productivity is required due to the expanding population and diminishing agricultural lands, which increases the use of chemical pesticides and fertilizers in farming. The current study was conducted in northwestern parts of Pakistan to evaluate the impacts of the frequent use of pesticides and fertilizers in agricultural fields. Nine hydrogeological Parameters were considered, and the GIS-based DRASTIC index was used to generate the final groundwater vulnerability map. The index map (ranging from 220 to 1980) was further classified into five classes based on index vulnerability: very low (220 - 345), low (346 - 670), moderate (671 - 730), high (731 - 1239), and very high 1240 - 1980). Nitrate and TDS, the two reliable and recognized scientific water quality measurements, have been used to validate the model. By regulating and controlling anthropogenic and agricultural pollution, the danger of contamination can be decreased. This research will aid in understanding the possible dangers and risks related to the usage of pesticides in agriculture and other industries. Furthermore, it will help identify the specific pesticides causing the contamination, assess the extent and severity of the contamination, and develop strategies to protect public health and the environment.