Predicting Groundwater Level Based on Machine Learning: A Case Study of the Hebei Plain
In recent years, the groundwater level (GWL) and its dynamic changes in the Hebei Plain have gained increasing interest. The GWL serves as a crucial indicator of the health of groundwater resources, and accurately predicting the GWL is vital to prevent its overexploitation and the loss of water qual...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/4/823 |
| _version_ | 1797617697590083584 |
|---|---|
| author | Zhenjiang Wu Chuiyu Lu Qingyan Sun Wen Lu Xin He Tao Qin Lingjia Yan Chu Wu |
| author_facet | Zhenjiang Wu Chuiyu Lu Qingyan Sun Wen Lu Xin He Tao Qin Lingjia Yan Chu Wu |
| author_sort | Zhenjiang Wu |
| collection | DOAJ |
| description | In recent years, the groundwater level (GWL) and its dynamic changes in the Hebei Plain have gained increasing interest. The GWL serves as a crucial indicator of the health of groundwater resources, and accurately predicting the GWL is vital to prevent its overexploitation and the loss of water quality and land subsidence. Here, we utilized data-driven models, such as the support vector machine, long-short term memory, multi-layer perceptron, and gated recurrent unit models, to predict GWL. Additionally, data from six GWL monitoring stations from 2018 to 2020, covering dynamical fluctuations, increases, and decreases in GWL, were used. Further, the first 70% and remaining 30% of the time-series data were used to train and test the model, respectively. Each model was quantitatively evaluated using the root mean square error (RMSE), coefficient of determination (R<sup>2</sup>), and Nash–Sutcliffe efficiency (NSE), and they were qualitatively evaluated using time-series line plots, scatter plots, and Taylor diagrams. A comparison of the models revealed that the RMSE, R<sup>2</sup>, and NSE of the GRU model in the training and testing periods were better than those of the other models at most groundwater monitoring stations. In conclusion, the GRU model performed best and could support dynamic predictions of GWL in the Hebei Plain. |
| first_indexed | 2024-03-11T07:59:29Z |
| format | Article |
| id | doaj.art-31b8f2451b544d4c8842b3be647a0955 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-11T07:59:29Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-31b8f2451b544d4c8842b3be647a09552023-11-16T23:53:58ZengMDPI AGWater2073-44412023-02-0115482310.3390/w15040823Predicting Groundwater Level Based on Machine Learning: A Case Study of the Hebei PlainZhenjiang Wu0Chuiyu Lu1Qingyan Sun2Wen Lu3Xin He4Tao Qin5Lingjia Yan6Chu Wu7State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaIn recent years, the groundwater level (GWL) and its dynamic changes in the Hebei Plain have gained increasing interest. The GWL serves as a crucial indicator of the health of groundwater resources, and accurately predicting the GWL is vital to prevent its overexploitation and the loss of water quality and land subsidence. Here, we utilized data-driven models, such as the support vector machine, long-short term memory, multi-layer perceptron, and gated recurrent unit models, to predict GWL. Additionally, data from six GWL monitoring stations from 2018 to 2020, covering dynamical fluctuations, increases, and decreases in GWL, were used. Further, the first 70% and remaining 30% of the time-series data were used to train and test the model, respectively. Each model was quantitatively evaluated using the root mean square error (RMSE), coefficient of determination (R<sup>2</sup>), and Nash–Sutcliffe efficiency (NSE), and they were qualitatively evaluated using time-series line plots, scatter plots, and Taylor diagrams. A comparison of the models revealed that the RMSE, R<sup>2</sup>, and NSE of the GRU model in the training and testing periods were better than those of the other models at most groundwater monitoring stations. In conclusion, the GRU model performed best and could support dynamic predictions of GWL in the Hebei Plain.https://www.mdpi.com/2073-4441/15/4/823groundwater level predictiondata-driven modelsgated recurrent unitsmodel performanceHebei Plain |
| spellingShingle | Zhenjiang Wu Chuiyu Lu Qingyan Sun Wen Lu Xin He Tao Qin Lingjia Yan Chu Wu Predicting Groundwater Level Based on Machine Learning: A Case Study of the Hebei Plain Water groundwater level prediction data-driven models gated recurrent units model performance Hebei Plain |
| title | Predicting Groundwater Level Based on Machine Learning: A Case Study of the Hebei Plain |
| title_full | Predicting Groundwater Level Based on Machine Learning: A Case Study of the Hebei Plain |
| title_fullStr | Predicting Groundwater Level Based on Machine Learning: A Case Study of the Hebei Plain |
| title_full_unstemmed | Predicting Groundwater Level Based on Machine Learning: A Case Study of the Hebei Plain |
| title_short | Predicting Groundwater Level Based on Machine Learning: A Case Study of the Hebei Plain |
| title_sort | predicting groundwater level based on machine learning a case study of the hebei plain |
| topic | groundwater level prediction data-driven models gated recurrent units model performance Hebei Plain |
| url | https://www.mdpi.com/2073-4441/15/4/823 |
| work_keys_str_mv | AT zhenjiangwu predictinggroundwaterlevelbasedonmachinelearningacasestudyofthehebeiplain AT chuiyulu predictinggroundwaterlevelbasedonmachinelearningacasestudyofthehebeiplain AT qingyansun predictinggroundwaterlevelbasedonmachinelearningacasestudyofthehebeiplain AT wenlu predictinggroundwaterlevelbasedonmachinelearningacasestudyofthehebeiplain AT xinhe predictinggroundwaterlevelbasedonmachinelearningacasestudyofthehebeiplain AT taoqin predictinggroundwaterlevelbasedonmachinelearningacasestudyofthehebeiplain AT lingjiayan predictinggroundwaterlevelbasedonmachinelearningacasestudyofthehebeiplain AT chuwu predictinggroundwaterlevelbasedonmachinelearningacasestudyofthehebeiplain |