Author(s)

Wei Guo

Affiliation(s)

Institute of Hydrogeology and Environmental Geology, Chinese Academy of Geosciences, Shijiazhuang 5050061, Hebei, China.

Corresponding Author

Wei Guo

ABSTRACT

This study applies a Long Short-Term Memory (LSTM) neural network to model daily groundwater level variations at four monitoring wells in the piedmont plain of Baoding City, Hebei Province, China. Using daily data from January 1, 2018 to August 31, 2019, the LSTM model is trained and tested under a one-step rolling prediction framework. The results demonstrate that the LSTM model accurately fits groundwater time series across various hydrogeological conditions, with testing-phase RMSE values ranging from 0.08 to 0.45 meters and R2 values exceeding 0.90. The model performs exceptionally well for both stable and fluctuating groundwater level conditions, capturing seasonal decline and recovery patterns without requiring explicit seasonal indicators. It also reveals the model’s ability to learn long-term trends and nonlinear dynamics inherent in groundwater systems. Despite its high short-term prediction accuracy, challenges remain regarding multi-step forecasting and responses to extreme events outside the training data. The study concludes that LSTM offers strong potential for groundwater simulation in data-limited environments and recommends further integration of hydro-meteorological variables for enhanced model robustness.

KEYWORDS

Groundwater level; LSTM; Time series modeling; Baoding; Deep learning

CITE THIS PAPER

Wei Guo. Groundwater level fitting of monitoring wells in the baoding region based on long short-term memory (LSTM) neural networks. Frontiers in Environmental Research. 2025, 3(2): 7-12. DOI: https://doi.org/10.61784/fer3024.

REFERENCES

[1] Wang K, Chen H, Fu S, et al. Analysis of exploitation control in typical groundwater over-exploited area in North China Plain. Hydrological Sciences Journal, 2021, 66(5): 851-861. DOI: 10.1080/02626667.2021.1900575.

[2] Kratzert F, Klotz D, Brenner C, et al. Rainfall–runoff modelling using long short-term memory (LSTM) networks. Hydrology and Earth System Sciences, 2018, 22(11): 6005-6022. DOI: 10.5194/hess-2018-247-sc1.

[3] Lees T, Buechel M, Anderson B, et al. Benchmarking data-driven rainfall–runoff models in Great Britain: a comparison of long short-term memory (LSTM)-based models with four lumped conceptual models. Hydrology and Earth System Sciences, 2021, 25(10): 5517-5534. DOI: 10.5194/hess-25-5517-2021.

[4] Yang S, Yang D, Chen J, et al. A physical process and machine learning combined hydrological model for daily streamflow simulations of large watersheds with limited observation data. Journal of Hydrology, 2020, 590: 125206. DOI: 10.1016/j.jhydrol.2020.125206.

[5] Zounemat-Kermani M, Batelaan O, Fadaee M, et al. Ensemble machine learning paradigms in hydrology: A review. Journal of Hydrology, 2021, 598: 126266. DOI: 10.1016/j.jhydrol.2021.126266.

[6] Nearing G S, Kratzert F, Sampson A K, et al. What role does hydrological science play in the age of machine learning?. Water Resources Research, 2021, 57(3): e2020WR028091. DOI: 10.31223/osf.io/3sx6g.

[7] Bai T, Tahmasebi P. Graph neural network for groundwater level forecasting. Journal of Hydrology, 2023, 616: 128792. DOI: 10.1016/j.jhydrol.2022.128792.

[8] Yin W, Fan Z, Tangdamrongsub N, et al. Comparison of physical and data-driven models to forecast groundwater level changes with the inclusion of GRACE–A case study over the state of Victoria, Australia. Journal of Hydrology, 2021, 602: 126735. DOI: 10.1016/j.jhydrol.2021.126735.

[9] Vu T D, Ni C F, Li W C, et al. Predictions of groundwater vulnerability and sustainability by an integrated index-overlay method and physical-based numerical model. Journal of Hydrology, 2021, 596: 126082. DOI: 10.1016/j.jhydrol.2021.126082.

[10] Baizhong Y, Jian S, Xinzhou W, et al. Multivariable LSTM neural network model for groundwater levels prediction.Journal of Jilin University (Earth Science Edition), 2020, 50(1): 208-216. DOI: 10.13278/j.cnki.jjuese.20190055.

[11] Hongjie S, Zhenhua Z, Linxian H, et al. Application of Multi-Variable LSTM Neural Network Model for Groundwater Levels Prediction. Yellow River, 2022, 44(8). DOI: 10.3969 /j.issn.1000-1379.2022.08.014.

[12] Sun J, Hu L, Li D, et al. Data-driven models for accurate groundwater level prediction and their practical significance in groundwater management. Journal of Hydrology, 2022, 608: 127630. DOI: 10.1016/j.jhydrol.2022.127630.

[13] Zhang C, Duan Q, Yeh P J F, et al. Sub-regional groundwater storage recovery in North China Plain after the South-to-North water diversion project. Journal of Hydrology, 2021, 597. DOI: 10.1016/j.jhydrol.2021.126156.

[14] Rajaee T, Ebrahimi H, Nourani V. A review of the artificial intelligence methods in groundwater level modeling. Journal of hydrology, 2019, 572, 336-351. DOI: 10.21203/rs.3.rs-2915223/v1.

[15] Wai K P, Chia M Y, Koo C H, et al. Applications of deep learning in water quality management: A state-of-the-art review. Journal of Hydrology, 2022,613, 128332. DOI: 10.1016/j.jhydrol.2022.128332.

[16] Van Thieu N, Barma S D, Van Lam T, et al. Groundwater level modeling using augmented artificial ecosystem optimization. Journal of Hydrology,2023, 617, 129034. DOI: 10.1016/j.jhydrol.2022.129034.