Machine learning-based ensemble of Global climate models and trend analysis for projecting extreme precipitation indices under future climate scenarios
No Thumbnail Available
Date
2025
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Springer Science and Business Media Deutschland GmbH
Abstract
Monitoring changes in climatic extremes is vital, as they influence current and future climate while significantly impacting ecosystems and society. This study examines trends in extreme precipitation indices over an Indian tropical river basin, analyzing and ranking 28 Coupled Model Intercomparison Project Phase 6 (CMIP6) Global Climate Models (GCMs) based on their performance against India Meteorological Department (IMD) data. The top five performing GCMs were selected to construct multi-model ensembles (MMEs) using Machine Learning (ML) algorithms, Random Forest (RF), Support Vector Machine (SVM), Multiple Linear Regression (MLR), and the Arithmetic Mean. Statistical metrics reveal that the application of an RF model for ensembling performs better than other models. The analysis focused on six IMD-convention indices and eight indices recommended by the Expert Team on Climate Change Detection and Indices (ETCCDI). Future projections were examined for three timeframes: near future (2025–2050), mid-future (2051–2075), and far future (2076–2100) for SSP245 and SSP585 scenarios. Statistical trend analysis, the Mann-Kendall test, Sen’s Slope estimator, and Innovative Trend Analysis (ITA), were applied to the MME to assess variability and detect changes in extreme precipitation trends. Compared to SSP245, in the SSP585 scenario, Total Precipitation (PRCPTOT) shows a significant decreasing trend in the near future, mid-future, and far future and Moderate Rain (MR) shows a decreasing trend in the near future and far future of monsoon season. The findings reveal significant future trends in extreme precipitation, impacting Sustainable Development Goals (SDGs) achievement and providing crucial insights for sustainable water resource management and policy planning in the Kali River basin. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.
Description
Keywords
Climate change, Climate models, Learning algorithms, Linear regression, Rain, River basin projects, Support vector regression, Sustainable development, Sustainable development goals, Change indexes, Climate change detection, Coupled Model Intercomparison Project, Coupled model intercomparison project phase 6, Expert team on climate change detection and index, Expert teams, Innovative trend analyze, Innovative trends, Machine-learning, Multi-model ensemble, Project phasis, Random forests, Trend analysis, Learning systems, algorithm, climate modeling, climate prediction, CMIP, comparative study, ensemble forecasting, extreme event, future prospect, global climate, machine learning, performance assessment, policy approach, precipitation assessment, trend analysis, water management, water resource, arithmetic, article, benchmarking, climate, climate change, climate model, controlled study, epidemiology, multiple linear regression analysis, precipitation, rain, rainy season, random forest, river basin, support vector machine, sustainable development goal, water supply, environmental monitoring, forecasting, India, pattern analysis (machine learning), procedures, Sharda Basin, Climate Change, Climate Models, Environmental Monitoring, Forecasting, Machine Learning, Pattern Analysis, Machine
Citation
Environmental Monitoring and Assessment, 2025, 197, 9, pp. -