A machine learning framework for multi-step-ahead prediction of groundwater levels in agricultural regions with high reliance on groundwater irrigation

• Published in: Environmental modelling & software : with environment data news 2024-09, Vol.180, p.106146, Article 106146
• Main Authors: Zhu, Feilin, Han, Mingyu, Sun, Yimeng, Zeng, Yurou, Zhao, Lingqi, Zhu, Ou, Hou, Tiantian, Zhong, Ping-an
• Format: Article
• Language: English
• Subjects: Agricultural regions; computer software; GBDT model; groundwater; Groundwater level prediction; humans; Hyperparameter optimization; Input variable selection; irrigation; mathematical models; Multi-core parallel computing; prediction; water table; watersheds
• ISSN: 1364-8152
• DOI: 10.1016/j.envsoft.2024.106146

This study presents a machine learning framework for multi-step-ahead prediction of groundwater levels in agricultural regions heavily reliant on groundwater irrigation. The framework utilizes a comprehensive set of predictive factors, including meteorological, hydrological, and human activity data. An optimal combination of input variables and their temporal delays was determined using a novel selection method. To address overfitting, a mathematical model for hyperparameter optimization was developed, leveraging sample subset cross-validation and an improved differential evolution algorithm. Numerical experiments on the YingGuo region in the Huaihe River Basin demonstrated that the hyperparameter optimization resulted in an 11.6%–38.5% increase in the Nash-Sutcliffe Efficiency (NSE) indicator. Additionally, fine-tuned temporal scales, from monthly to five-day resolution, significantly improved predictive performance, with NSE increasing from 0.629 to 0.952 (33.9% enhancement). However, longer forecasting horizons led to a 29.4% reduction in NSE. The study also implemented a multi-core parallel computing framework, which achieved a 15.35-fold improvement in computational efficiency while maintaining predictive precision. The integration of external factors enhanced the predictive performance across various observation wells. These findings contribute to a better understanding of groundwater dynamics and highlight the potential of machine learning models in improving groundwater depth predictions in agricultural regions with high reliance on groundwater irrigation. [Display omitted] •Achieving accurate predictions with optimal combination of input variables and delays.•Overfitting reduced by optimizing hyperparameters, NSE increase: 11.6%–38.5%.•Enhanced efficiency with multi-core parallel computing: 15.35-fold speedup.•Fine-tuned time scales boost performance: Monthly to Five-day, NSE increase: 33.9%.•Decreased accuracy for longer horizons: NSE reduced by 29.4% at Five-day time scale.