Abstract
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.
Highlights
Drought refers to an extended water shortage period
It was developed for the assessment of drought characterization in the Indus, Ganga, and Brahmaputra river basins by utilizing hydro-metrological variables, i.e., precipitation (P) and potential evapotranspiration (PET), as well as gravity data, i.e., Gravity Recovery and Climate Experiment (GRACE) terrestrial water storage anomalies (TWSAs) [24]
The Combined Terrestrial Evapotranspiration Index (CTEI) was derived using the GRACE TWSA data and meteorological variables for 2003–2016. This index was developed by Dharpure et al [24] using hydrological and climatological conditions in the Indus, Ganga, and Brahmaputra river basins and which highlighted that the CTEI was positively correlated with the ground observation wells
Summary
Drought refers to an extended water shortage period. In terms of water resource imbalance or excess evapotranspiration and moisture deficiency, the adverse impacts can be magnified due to extreme event dry conditions [1,2,3,4,5]. More than 150 indices have been developed for drought assessment, classification, and monitoring [12] These include the Palmer Drought Severity Index (PDSI) [13]; the Standardized Precipitation Index (SPI) [14]; the Standardized Precipitation Evapotranspiration Index (SPEI) [15,16]; the Rainfall Anomaly Index (RAI) [17]; the Precipitation Evapotranspiration Difference Condition Index (PEDCI) [18], the Reconnaissance Drought Index (RDI) [19,20]; and many others, as can be found in the review by Mishra and Singh [21]. ANNs and SVMs are the most commonly applied techniques in developing drought prediction models [42,43,44,45]. Khan et al [6] developed drought prediction models for Pakistan by applying the SVM, ANN, and KNN techniques. They reported four deficit years (2004, 2009, 2014, and 2015) between 2003 and 2016
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
