Drought is a fundamental physical feature of the climate pattern worldwide. Over the past few decades, a natural disaster has accelerated its occurrence, which has significantly impacted agricultural systems, economies, environments, water resources, and supplies. Therefore, it is essential to develop new techniques that enable comprehensive determination and observations of droughts over large areas with satisfactory spatial and temporal resolution. This study modeled a new drought index called the Combined Terrestrial Evapotranspiration Index (CTEI), developed in the Ganga river basin. For this, five Machine Learning (ML) techniques, derived from artificial intelligence theories, were applied: the Support Vector Machine (SVM) algorithm, decision trees, Matern 5/2 Gaussian process regression, boosted trees, and bagged trees. These techniques were driven by twelve different models generated from input combinations of satellite data and hydrometeorological parameters. The results indicated that the eighth model performed best and was superior among all the models, with the SVM algorithm resulting in an R² value of 0.82 and the lowest errors in terms of the Root Mean Squared Error (RMSE) (0.33) and Mean Absolute Error (MAE) (0.20), followed by the Matern 5/2 Gaussian model with an R² value of 0.75 and RMSE and MAE of 0.39 and 0.21 mm/day, respectively. Moreover, among all the five methods, the SVM and Matern 5/2 Gaussian methods were the best-performing ML algorithms in our study of CTEI predictions for the Ganga basin.

Snow and glacier melt provide freshwater to millions of people in the Indus basin. However, the unprecedented increase in demand for freshwater and depleting resources due to climate warming has put the region's water resources at risk. Therefore, quantifying water mass variation and anticipating changes in hydrological regimes that affect downstream freshwater supply are of utmost importance. To address this, we used Gravity Recovery and Climate Experiment (GRACE) and GRACE Follow‐On derived terrestrial water storage anomaly (TWSA) data from April 2002 to May 2023 over the Indus basin. Several gaps in these data, totaling 33 months, significantly impact regional trends and predictions of water mass changes. We apply a machine learning‐based MissForest algorithm to fill these gaps and compare our results with four previous studies. Annual TWSA shows a declining trend (−0.65 cm/yr) before 2015/16, with a significantly higher (−2.16 cm/yr) after 2015/16. Based on the estimate for the annual groundwater storage anomaly (GWSA), a major portion (83.7%) of the basin is experiencing a significant declining trend (>−0.15 cm/yr, p < 0.05). Glaciated region has a less severe decreasing trend (−0.78 cm/yr) compared to the non‐glaciated region (−1.44 cm/yr). Among sub‐basins, the upper Indus shows the lowest decline (−0.42 cm/yr), while Panjnad exhibits the highest (−1.70 cm/yr). Annual precipitation and runoff are decreasing, while temperature shows no trend. However, evapotranspiration is increasing might be due to a significant increase in vegetation (0.23%/yr) over the basin. The trends of hydroclimatic variables, vegetation, and anthropogenic factors, indicate a consistently decreasing GWSA in the region.

Bhaga Basin has complex mountainous terrain; little study has been done on the spatial and temporal characteristics of snow cover in the region. The Moderate Resolution Imaging Spectroradiometer (MODIS) 8-day snow cover products between 2001 and 2012 for winter period (November–April) have been used to study the variation in snow cover area (SCA). The statistical analysis based on non-parametric Mann Kendall and Sen’s slope methods have been used for detecting and estimating trends for climatic variables (temperature and snowfall) and SCA for winter period. Results of statistical analysis indicate rise in minimum temperature (0.02 °C year⁻¹) and fall in maximum temperature (0.17 °C year⁻¹). It also shows decrease in mean seasonal snowfall (0.07 cm year⁻¹). The seasonal SCA was found to decrease at the rate of 0.002% year⁻¹. This study indicates that the climate change is probably one of the major causes for depleting SCA.

Monitoring of snow cover variability is crucial because it is closely linked with mountain water resources, ecosystems, and climate change. For this, moderate-resolution imaging spectroradiometer (MODIS) daily snow cover products (SCPs, version 6) were used over the Chenab river basin (CRB) during 2001–2017. In these data, cloud cover is a significant problem that produces a discontinuity in spatial and temporal scale for long-term snow cover monitoring. Therefore, a sequential non-spectral composite methodology (with five successive steps) was applied to reduce cloud obscuration. Further, the cloud gap-filled SCPs were validated with the indirect method as well as high-resolution satellite data (Landsat-8). Results indicate that the cloud-removed SCPs show an overall efficiency of 92.8 $\pm$ 1.6% with an indirect approach, while an overestimation (9.3%) was observed between Landsat and MODIS snow cover area (SCA) along with higher correlation (R = 0.99, p < 0.001). The result shows an increasing trend (0.25% $\mathrm{y}\mathrm{r}-1$) of mean annual SCA during 2001–2017, while it is slightly decreasing since 2009 and was statistically insignificant. Moreover, the Snow Cover Day and nine indexes (from snow depletion curves) were derived for snow cover characterization, indicating that a shift or change in the snow accumulation period in terms of the seasonal snow cover in the recent decade. Furthermore, the linear relationships between SCA and climatic variables were established to identify the influence of snow cover distribution and its related snowmelt onset. The analysis demonstrated that the precipitation and net shortwave radiation (SWN) were increasing in the north-eastern region of the basin. However, the air temperature ( ${\mathrm{T}}_{\mathrm{a}}$) and wind speed showed a declining trend. Furthermore, associated uncertainty and sensitivity analyzes were performed, suggesting that the SCA is more sensitive to ${\mathrm{T}}_{\mathrm{a}}$. However, it may be less susceptible to precipitation during the melt season. Overall, this finding indicates the potential importance of climatic variables on the snow cover distribution that is essential for proper management of the hydrological system.

Snow cover plays an important role in hydrological modelling and influences the energy balance. Daily Moderate Resolution Imaging Spectroradiometer (MODIS) snow products are widely used for snow cover monitoring; however, the cloud cover causes a discontinuity in spatial and temporal scale. Therefore, we have implemented a composite (five-step) methodology for cloud removal over the Karakoram and Himalayan (KH) region during 2000–2019. The cloud-gap-filled snow cover area (SCA) was compared with Landsat-8 data, and the relationship with in situ observations (snowfall and temperature) was examined. The annual SCA illustrates an increasing trend for the entire KH except in the eastern Himalayas. The snow cover day and nine snow cover timing indices were assessed to explore the snow cover characteristics. The relationships between SCA and meteorological variables were evaluated, suggesting a higher correlation with temperature and shortwave radiation. A sensitivity analysis was performed, indicating higher sensitivity of SCA to radiation than to other selected variables.

Drought is a recurring natural disaster, which significantly affects the economy and environment of diverse geographical area worldwide. Therefore, it is imperative to develop a new technique that enables comprehensive identification and monitoring of drought over a large spatial extent. In this study, a new drought index called Combined Terrestrial Evapotranspiration Index (CTEI) is developed by using a combination of Gravity Recovery and Climate Experiment (GRACE) data and meteorological parameters, i.e., precipitation (P) and potential evapotranspiration (PET) over the Indus, Ganga, and the Brahmaputra (IGB) river basins. Further, the results of CTEI are compared with pre-existing drought indices, which highlighted good correlation with GRACE Groundwater Drought Index (GGDI) (ρ = 0.88), Water storage deficit index (WSDI) (ρ = 0.96), Combined Climatologic Deviation Index (CCDI) (ρ = 0.97) and Standardized Precipitation-Evapotranspiration Index (SPEI) (ρ = 0.49). It also compared with In-situ Groundwater Drought Index (IGDI) derived by groundwater observation wells. The mean annual CTEI exhibited a strong correlation with IGDI (0.49 to 0.77) and climatic parameters (P, PET, and land surface temperature). Outcomes illustrated a significant potential of CTEI index and extended the utility of GRACE derived Terrestrial Water Storage observations for drought characterization as well as quantification of its severity.