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.

The ongoing glacier shrinking in the Himalayan region causes a significant threat to freshwater sustainability and associated future runoff. However, data on the spatial climatic contribution of glacier retreat is scanty in this region. To investigate the spatially distributed glacier surface energy and mass fluxes, a two-dimensional mass balance model was developed and applied to the selected glaciers of the Chandra basin, in the Upper Indus Basin, Western Himalaya. This model is driven by the remote sensing data and meteorological variables measured in the vicinity of the Chandra basin for six hydrological years (October 2013 to September 2019). The modelled variables were calibrated/validated with the in-situ observation from the Himansh station in the Chandra basin. We have derived air temperature (T a) spatially using the multivariate statistical approach, which indicates a relative error of 0.02-0.05 C with the observed data. Additionally, the relative error between the modelled and observed radiation fluxes was <10.0 W m −2. Our study revealed that the Chandra basin glaciers have been losing its mass with a mean annual mass balance of −0.59 ± 0.12 m w.e. a −1 for the six hydrological years. Results illustrated that the mean surface melt rate of the selected glaciers ranged from −5.1 to −2.5 m w.e. a −1 that lies between 4500 and 5000 m a.s.l. The study revealed that the net radiation (R N) contributes $75% in total energy (F M) during the melt season while sensible heat (H S), latent heat (H l), and ground heat (H G) fluxes shared 15%, 8%, and 2%, respectively. Sensitivity analysis of the energy balance components suggested that the mass balance is highly sensitive to albedo and surface radiations in the study area. Overall, the proposed model performed well for glacier-wide energy and mass balance estimation and confirms the utility of remote sensing data, which may help in reducing data scarcity in the upper reaches of the Himalayan region.

No abstract

No abstract

No abstract