View in EDS

Developing river water quality prediction model incorporating reliable indexing approach.

Saved in:
Bibliographic Details
Title: Developing river water quality prediction model incorporating reliable indexing approach.
Authors: Olbert, Agnieszka I.1,2,3,4 (AUTHOR), Diganta, Mir Talas Mahammad1,2,3,4 (AUTHOR), Bamal, Apoorva1,2,3,4 (AUTHOR), Burke, William1,2,3,4 (AUTHOR), Sajib, Abdul Majed1,2,3,4 (AUTHOR), Abioui, Mohamed5,6 (AUTHOR), Ashekuzzaman, S.M.7 (AUTHOR), Rahman, Azizur8,9 (AUTHOR), Uddin, Md Galal1,2,3,4,7 (AUTHOR) mdgalal.uddin@universityofgalway.ie
Source: Journal of Environmental Sciences (Elsevier). Jun2026, Vol. 164, p581-598. 18p.
Subject Terms: *Water quality, *River pollution, *Water quality management, Machine learning, Regression trees, Artificial intelligence
Abstract: • Integrated advanced RMS-WQI model with ML/AI algorithms for river waters modelling. • Developed fifty prediction models using the combinations of ten ML/AI with five optimizers. • Gradient boosting regression (GBR) -Optuna (OPT) prediction model (combination) outperformed. • Results shows the OPT could be effective to optimize best set of hyperparameters for predicting river waters. • The findings of the research reveals that the existing approach of the EPA, Ireland's should be updated. Hyperparameter optimization techniques can influence the prediction model(s) capabilities in terms of delivering reliable results. As a part of the development of the data-driven water quality (WQ) model(s), this research evaluated five hyperparameter optimization techniques and their impacts on WQ prediction model(s) using machine learning (ML)/artificial intelligence (AI) techniques to predict the WQI scores through the root mean squared (RMS)-WQI approach. For developing the ML/AI models the research utilized the ten ML algorithms by comparing fifty models. To evaluate the ML-AI model(s), the study used five widely used metrics including Root Mean Squared Error (RMSE), Mean Squared Error (MSE), Mean Absolute Error (MAE), Percentage of Absolute Bias Error (PABE), Nash Sutcliffe Efficiency (NSE) while the coefficient of determination (R 2) utilized for sensitivity assessment. The results indicated that the gradient boosting (GBR) model with the OPTUNA (OPT) optimization technique outperformed others in predicting WQI score during both training (RMSE = 0.84, MSE = 0.71, MAE = 0.74, PABE = 1.00) and testing (RMSE = 0.45, MSE = 0.20, MAE = 0.30, PABE = 0.41) phase. Additionally, the study also revealed that the GBR-OPT demonstrated higher sensitivity (R 2 for the year 2021 = 0.99 and testing R 2 for the year 2022 = 0.98) and the highest efficiency (an average NSE for the year 2021 = 0.71 and an average NSE for the year 2022 = 0.60) compared to other models. Overall, the findings of the research reveal that the study outcomes could be effective in developing more efficient and accurate WQ prediction model(s) that would be helpful for sustainable WQ management. [Display omitted] [ABSTRACT FROM AUTHOR]
Copyright of Journal of Environmental Sciences (Elsevier) is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: GreenFILE
Description
Abstract:• Integrated advanced RMS-WQI model with ML/AI algorithms for river waters modelling. • Developed fifty prediction models using the combinations of ten ML/AI with five optimizers. • Gradient boosting regression (GBR) -Optuna (OPT) prediction model (combination) outperformed. • Results shows the OPT could be effective to optimize best set of hyperparameters for predicting river waters. • The findings of the research reveals that the existing approach of the EPA, Ireland's should be updated. Hyperparameter optimization techniques can influence the prediction model(s) capabilities in terms of delivering reliable results. As a part of the development of the data-driven water quality (WQ) model(s), this research evaluated five hyperparameter optimization techniques and their impacts on WQ prediction model(s) using machine learning (ML)/artificial intelligence (AI) techniques to predict the WQI scores through the root mean squared (RMS)-WQI approach. For developing the ML/AI models the research utilized the ten ML algorithms by comparing fifty models. To evaluate the ML-AI model(s), the study used five widely used metrics including Root Mean Squared Error (RMSE), Mean Squared Error (MSE), Mean Absolute Error (MAE), Percentage of Absolute Bias Error (PABE), Nash Sutcliffe Efficiency (NSE) while the coefficient of determination (R 2) utilized for sensitivity assessment. The results indicated that the gradient boosting (GBR) model with the OPTUNA (OPT) optimization technique outperformed others in predicting WQI score during both training (RMSE = 0.84, MSE = 0.71, MAE = 0.74, PABE = 1.00) and testing (RMSE = 0.45, MSE = 0.20, MAE = 0.30, PABE = 0.41) phase. Additionally, the study also revealed that the GBR-OPT demonstrated higher sensitivity (R 2 for the year 2021 = 0.99 and testing R 2 for the year 2022 = 0.98) and the highest efficiency (an average NSE for the year 2021 = 0.71 and an average NSE for the year 2022 = 0.60) compared to other models. Overall, the findings of the research reveal that the study outcomes could be effective in developing more efficient and accurate WQ prediction model(s) that would be helpful for sustainable WQ management. [Display omitted] [ABSTRACT FROM AUTHOR]
ISSN:10010742
DOI:10.1016/j.jes.2025.07.038