Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item Improving multiple model ensemble predictions of daily precipitation and temperature through machine learning techniques(Nature Research, 2022) Jose, D.M.; Vincent, A.M.; Dwarakish, G.S.Multi-Model Ensembles (MMEs) are used for improving the performance of GCM simulations. This study evaluates the performance of MMEs of precipitation, maximum temperature and minimum temperature over a tropical river basin in India developed by various techniques like arithmetic mean, Multiple Linear Regression (MLR), Support Vector Machine (SVM), Extra Tree Regressor (ETR), Random Forest (RF) and long short-term memory (LSTM). The 21 General Circulation Models (GCMs) from National Aeronautics Space Administration (NASA) Earth Exchange Global Daily Downscaled Projections (NEX-GDDP) dataset and 13 GCMs of Coupled Model Inter-comparison Project, Phase 6 (CMIP6) are used for this purpose. The results of the study reveal that the application of a LSTM model for ensembling performs significantly better than models in the case of precipitation with a coefficient of determination (R2) value of 0.9. In case of temperature, all the machine learning (ML) methods showed equally good performance, with RF and LSTM performing consistently well in all the cases of temperature with R2 value ranging from 0.82 to 0.93. Hence, based on this study RF and LSTM methods are recommended for creation of MMEs in the basin. In general, all ML approaches performed better than mean ensemble approach. © 2022, The Author(s).Item Comparison of the Multiple Imputation Approaches for Imputing Rainfall Data: A Humid Tropical River Basin Case Study(Springer Nature, 2025) Kumar, G.P.; Dwarakish, G.S.Accurate rainfall data is crucial for agriculture, hydrology, and climate research as it guides water management, crop planning, and disaster preparedness. Missing data affects reliability, requiring effective imputation. The purpose of this study is to address the critical challenge of imputing missing daily rainfall data, which is especially important given rainfall’s nonlinear distribution and variability in missingness patterns. This research aims to develop and evaluate advanced imputation algorithms to improve data completeness and integrity in humid tropical regions. This study evaluates ten imputation algorithms: K-nearest neighbors (KNN), classification and regression trees (CART), predictive mean matching (pmm), random forest (rf), mean method, and Bayesian methods (norm. boot, lasso. norm, norm, norm. nob, midastouch) for addressing missing daily rainfall data. Using 37 years of data from thirteen stations in the Kali River Basin, the methods leverage descriptive statistics to enhance accuracy in humid tropical regions. The proposed algorithms incorporate descriptive statistics of the rainfall time series and are evaluated using 37 years of daily data from thirteen selected rainfall stations in the Kali River Basin, a humid tropical region. Model performance was assessed at four missingness levels (1%, 5%, 10%, and 20%) and evaluated with accuracy metrics root mean square error (RMSE), mean absolute error (MAE), index of agreement (d), and RMSE-observations standard deviation ratio (RSR). Among the evaluated methods, KNN consistently demonstrated superior performance across all levels of missingness (RMSE = 13.22 to 15.42; MAE = 4.68 to 6.08; d = 0.87 to 0.90; RSR = 0.57 to 0.61), followed closely by CART (RMSE = 16.48 to 20.77; MAE = 6.20 to 8.31; d = 0.81 to 0.86; RSR = 0.71 to 0.79). Overall, KNN, CART, pmm, and rf emerged as reliable methods for imputing missing rainfall data of varying lengths, contributing to more accurate weather forecasting and climate change analyses. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.Item Machine learning-based ensemble of Global climate models and trend analysis for projecting extreme precipitation indices under future climate scenarios(Springer Science and Business Media Deutschland GmbH, 2025) Kumar, G.P.; Dwarakish, G.S.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.Item Multi-criteria decision-making and machine learning-based CMIP6 general circulation model ensemble for climate projections in a tropical river basin in India(Springer Science and Business Media Deutschland GmbH, 2025) Kumar, G.P.; Vinod, D.; Dwarakish, G.S.; Mahesha, A.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.