article · Scientific Reports
This study evaluated multiple machine learning and deep learning models to predict groundwater levels in the Bongseong well on Jeju Island, South Korea. The algorithms tested included stochastic gradient boosting, random forest, generalised regression neural networks, group method of data handling, deep echo state networks, and long short-term memory networks. Predictions were structured around three distinct scenarios using meteorological variables alongside neighbouring well levels, groundwater physical properties, or antecedent groundwater levels from one to fifteen days prior. The random forest model using prior groundwater levels alongside weather data yielded the highest predictive accuracy across five statistical measures. Furthermore, sensitivity analysis using the SHapley Additive exPlanations method confirmed that the groundwater level from a one-day lead time was the most significant contributing feature, while statistical testing verified the distribution of predicted values matched measured observations.
Groundwater is a vital source of freshwater, but forecasting its levels is difficult due to changing weather and environmental conditions. Testing various artificial intelligence models and explaining their internal mechanisms helps hydrologists identify the most dependable forecasting methods. Pinpointing the most influential indicators makes monitoring programmes more efficient and aids in reliable water resource planning.
The work presents tested analytical models that could be integrated into operational groundwater management systems by environmental authorities or water resource managers. Because the models were tested on historical monitoring data rather than in live deployment, the technology remains early-stage research that requires integration into practical decision-support software before commercial or operational use.
AI-generated from the published abstract. Always read the original work before citing.
In this research, the groundwater levels (GWLs) were predicted by employing machine learning (i.e., stochastic gradient boosting (SGB), random forest (RF), generalized regression neural networks (GRNN), and group of method data handling (GMDH)) and deep learning (i.e., deep echo state network (Deep ESN) and long short-term memory (LSTM)) based on three predictive scenarios, Jeju Island, South Korea. In scenario 01, GWLs in Bongseong well was calculated utilizing rainfall, air temperature, relative humidity, wind speed, and various GWLs in different wells. Based on scenario 02, GWLs in Bongseong well was calculated using rainfall, air temperature, relative humidity, wind speed, and groundwater data (i.e., temperature, electric conductivity, and pressure). Finally, considering scenario 03, GWLs in Bongseong well were calculated by employing rainfall, air temperature, relative humidity, wind speed, and GWLs from 1-day to 15-day lead time. Five evaluation measures, including root mean squared error (RMSE), correlation coefficient (CC), Nash-Sutcliffe efficiency (NSE), relative error (RE), and root relative squared error (RRSE), were reflected for the predictive accuracy of developed models. Results showed that RF3 (RMSE = 0.053 m, CC = 1.000, NSE = 1.000, RE = 1.114, and RRSE = 0.013) based on scenario 03 performed the best predictive accuracy in GWLs of Bongseong well. Furthermore, the additional contributions of this research were achieved by the enhanced comparative evaluation through the SHapley Additive exPlanations (SHAP) strategy and one-way Analysis of Variance (ANOVA) test. The sensitivity analysis utilizing the SHAP strategy determined the significant feature indicator (i.e., GWL in 1-day lead-time) explaining its contribution to the predictive ability of developed models. The results of one-way ANOVA test provided that the predicted values were extracted from the same population as the measured values based on all models in scenario 03.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1038/s41598-025-19545-y
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
