Multi-criteria decision-making and machine learning-based CMIP6 general circulation model ensemble for climate projections in a tropical river basin in India

Abstract

General circulation models (GCMs) are vital for accurate climate prediction and informing strategic water resource planning. The investigation explores the performance of five machine learning (ML) algorithms for ensembling the GCMs for top-5 and least-5 ranked models in multi-criteria decision-making (MCDM) in addition to 28 GCMs applicable to a tropical river basin in India and the performance of their ensemble using statistical metrics. The gridded datasets from the India Meteorological Department (IMD) are used as observed data. From the statistical metrics, an entire 28 GCMs ensemble showed superiority over top-5 and least-5 ranked ensembles for three meteorological variables. The random forest (RF) algorithm consistently demonstrated high accuracy and reliability in ensembling the GCMs for the three meteorological variables, followed by support vector machine (SVM) and multiple linear regression (MLR). By implementing the proposed approach, researchers can minimize biases, enable resource-efficient modeling, and deliver practical insights through robust and reliable climate projections. These results highlight the importance of thoughtful ensemble design, advocating using multi-model ensembles (MMEs) in comprehensive climate studies to ensure accurate predictions across diverse climate indices. The findings provide valuable insights into local climate conditions, supporting ecosystem management and informing policy decisions. © The Author(s) under exclusive licence to Institute of Geophysics, Polish Academy of Sciences 2025.