Development of stacking algorithm for bias-correcting the precipitation projections using a multi-model ensemble of CMIP6 GCMs in a semi-arid basin, India

• Published in: Theoretical and applied climatology Vol. 156; no. 2; p. 129
• Main Authors: Shanmugam, Hemanandhini, Lakshmanan, Vignesh Rajkumar
• Format: Journal Article
• Language: English
• Published: Vienna Springer Vienna 01.02.2025; Springer Nature B.V
• Subjects: Algorithms; Annual precipitation; Aquatic Pollution; atmospheric precipitation; Atmospheric Protection/Air Quality Control/Air Pollution; Atmospheric Sciences; basins; Bias; climate; Climate action; Climate change; Climatology; decision support systems; Decision trees; Drought; Earth and Environmental Science; Earth Sciences; Environmental impact; Future climates; Future precipitation; General circulation models; Hydrologic cycle; Hydrological cycle; India; Learning algorithms; Machine learning; model validation; Multilayer perceptrons; Multilayers; Precipitation; Precipitation variations; regression analysis; Regression models; River basins; Root-mean-square errors; Support vector machines; Sustainable development; Sustainable Development Goals; Waste Water Technology; Water Management; Water Pollution Control; watersheds; India
• ISSN: 0177-798X; 1434-4483
• DOI: 10.1007/s00704-024-05321-x

Climate change affects the hydrological cycle, leading to extreme events such as droughts and floods. Projection of climate change is necessary to understand the variability of future climate parameters for mitigating the impacts of climate change. The research aims to project the future precipitation over Amaravathi River Basin (ARB), Tamil Nadu, India considering as MME (Multi-Model Ensemble) CMIP6 (Coupled Model Inter comparison Project Phase-6) GCMs (General Circulation Models). The uncertainties and biases in the MME CMIP6 GCM precipitation were corrected and projected using the Empirical Quantile Mapping (EQM) employing the individual multiple Machine Learning (ML) and integrating algorithms through Stacking Regression (SR). Multiple machine learning algorithms used for bias-correction are Linear Regression (LR), Decision-Tree (DT) Regression, Random Forest (RF) Regression, Support-Vector Machine (SVM) Regression and Multi-Layer Perceptron (MLP) Regression with HyperParameter Tuning (HPT). Each machine learning algorithm with optimized hyperparameter was integrated into the SR to improve the model performance. The proposed SR showed better than the individual algorithms, with a RMSE (Root Mean Square Error) ranging from 37.14 to 66.28. The SR-based precipitation projection changes were analyzed as three periods: 2025–2050 (2040, near-future year), 2051–2075 (2065, mid-future year) and 2076–2100 (2090, far-future year) under SSP (Shared Socioeconomic Pathway) 1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5 emission scenarios. The projected annual precipitation variations are in the range of 0.81–67.33% under the SSP1, followed by -4.51–72.13% (SSP2), -1.62–60.84% (SSP3) and − 0.71–65.75% under the SSP5 over the ARB. The precipitation was projected to be higher in magnitude in the southeast and lesser magnitude in the top northern part of ARB. The projection findings will be helpful in formulating strategies for addressing the climate impact and achieving the Sustainable Development Goal (SDG 13: Climate Action).