The present study applies three Machine Learning Algorithms, namely, Bi-directional Long Short-Term Memory (Bi-LSTM), Wavelet Neural Network (WNN), and eXtreme Gradient Boosting (XGBoost), to assess their suitability for streamflow projections of the Lower Godavari Basin. Historical data for 39 years of daily rainfall, evapotranspiration, and discharge are used, of which 80% were for the model training and 20% for validation. A Random Search method is used for hyperparameter tuning. XGBoost performs better than WNN, and Bi-LSTM with an R2, RMSE, NSE, and PBIAS of 0.88, 1.48, 0.86, and 29.3% during training, with corresponding values of 0.86, 1.63, 0.85, and 28.5%, respectively, during validation indicate consistency. Therefore, it is used further for projecting streamflow from a climate change perspective. Global Climate Model, Ec-Earth3 is used because of its potentiality, as observed from previous studies. Four Shared Socioeconomic Pathways (SSPs) are considered. Downscaling of future climate variables is based on Empirical Quantile Mapping. Eight decadal streamflow projections are computed – D1 to D8 (2021–2030 to 2091–2099) – exhibiting more pronounced changes within the warming range. They are compared with three historic time horizons of H1 (1982–1994), H2 (1995–2007), and H3 (2008–2020). The highest daily streamflow is observed in D1, D3, D4, D5, and D8 in SSP245; these are D6 and D7 in SSP585 as per XGBoost analysis.
The present work aims to identify the best hydrological model structure suitable for the Lower Godavari River Basin, India, that forecasts streamflows. An extended version of the Framework for Understanding Structural Errors (FUSE), termed E-FUSE, is developed for this purpose. It consists of 1248 model structures. K means cluster analysis (KCA), and Davies Bouldin Cluster Validation Index (DBCVI) are used for identifying optimal clusters, whereas Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is employed for the best model structure. Correlation coefficient (r), normalized root mean square error (NRMSE), and mean bias error (MBE) are employed as evaluation criteria. The best model structure obtained exhibits r, NRMSE & MBE of 0.734, 0.74 & -0.09 respectively during calibration and 0.69, 0.802 & -0.28 respectively during validation. The best model structure is then used to forecast discharges for a global climate model, EC-Earth3, and four Shared Socioeconomic Pathways, SSP126, SSP245, SSP370, and SSP585 scenarios. Analysis was made for three-time horizons, namely, the near-future scenario (2021–2046), mid-future scenario (2047–2072), and far future scenario (2073–2099). It is observed that the July–September months contribute majorly to total runoff for four SSPs and three-time horizons.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.