Author(s)

Xiaoya Zhang ¹, Xin Liao ^2,3, Yun Shi ^2,3, Yonghong Xue ¹

Affiliation(s)

¹ School of Science, University of Emergency Management, Beijing, 101601, China
² School of Environmental and Disaster Management, University of Emergency Management, Beijing, 101601, China
³ Hebei Key Laboratory of Resource and Environmental Disaster Mechanism and Risk Monitoring, Sanhe, 065201, China; Hebei Key Laboratory of Earthquake Dynamics, Sanhe, 065201, China

Corresponding Author

Yonghong Xue

ABSTRACT

Groundwater level dynamics are shaped by the coupled influences of multiple hydrogeological factors and human activities, exhibiting pronounced nonlinearity and spatiotemporal heterogeneity. To address the limitations of traditional models in effectively capturing spatiotemporal features and parameter optimization difficulties, this study proposes a Bayesian optimization-based spatiotemporal attention bidirectional long short-term memory model (STA-BiLSTM). The proposed model integrates adaptive spatial neighborhood construction with a hybrid spatiotemporal attention mechanism, effectively fusing spatial correlations among multiple monitoring wells with temporal dependencies across time steps. Furthermore, Bayesian optimization is employed for global, automated hyperparameter and structural parameter tuning. To gain deeper insight into the hydrophysical significance underlying the model’s internal mechanisms, experiments were conducted in the Beijing–Tianjin region, selecting groundwater-level rising and declining zones with markedly different evolutionary characteristics. Results demonstrate that the STA-BiLSTM model achieves higher predictive accuracy than comparative models under both evolution patterns. Compared with the baseline LSTM model, the root mean square error (RMSE) decreased by 38.4% and 7.9%, and the coefficient of determination (R²) increased to 0.945 and 0.940 for the Beijing and Tianjin wells, respectively. 

KEYWORDS

Bayesian optimization; BiLSTM; Groundwater level prediction; Spatio-temporal attention mechanism

CITE THIS PAPER

Xiaoya Zhang, Xin Liao, Yun Shi, Yonghong Xue. Bayesian Optimization-based STA-BiLSTM Groundwater Level Prediction Model and Its Application in Beijing-Tianjin Area. Journal of Artificial Intelligence Practice (2026). Vol. 9, No. 2, 1-14. DOI: http://dx.doi.org/10.23977/jaip.2026.090201.

REFERENCES

[1] Liu Y, Wu G, Ma B et al (2024) Revealing climatic and groundwater impacts on the spatiotemporal variations in vegetation coverage in marine sedimentary basins of the North China Plain, China. Sci Rep 14:10085. https://doi.org/10.1038/s41598-024-60838-5
[2] Long D, Xu Y, Cui Y et al (2025) Unprecedented large-scale aquifer recovery through human intervention. Nat Commun 16:7296. https://doi.org/10.1038/s41467-025-62719-5
[3] Su G, Xiong C, Zhang G, Wang Y, Shen Q, Chen X, An H, Qin L (2023) Coupled processes of groundwater dynamics and land subsidence in the context of active human intervention: a case in Tianjin, China. Sci Total Environ 903:166803. https://doi.org/10.1016/j.scitotenv.2023.166803
[4] Zhang R, Wang T, Liu G, Shama A, Liu A, Wang X, Deng L, Mao W (2025) Ground subsidence evolution and groundwater variation in the middle route of South-to-North Water Diversion Project. Sci Rep 15:19220. https://doi.org/10.1038/s41598-025-04307-7
[5] Long D, Yang W, Scanlon BR, Zhao J, Liu D, Burek P, Pan Y, You L, Wada Y (2020) South-to-North Water Diversion stabilizing Beijing's groundwater levels. Nat Commun 11:3665. https://doi.org/10.1038/s41467-020-17428-6
[6] Wunsch A, Liesch T, Broda S (2021) Groundwater level forecasting with artificial neural networks: a comparison of long short-term memory (LSTM), convolutional neural networks (CNNs), and non-linear autoregressive networks with exogenous input (NARX). Hydrol Earth Syst Sci 25:1671–1687. https://doi.org/10.5194/hess-25-1671-2021
[7] Thakur A, Chandel A, Shankar V (2025) Prediction of groundwater levels using a long short-term memory (LSTM) technique. J Hydroinform 27(1):51–68. https://doi.org/10.2166/hydro.2024.239
[8] Zhang X, Dong F, Chen G, Dai Z (2023) Advance prediction of coastal groundwater levels with temporal convolutional and long short-term memory networks. Hydrol Earth Syst Sci 27:83–96. https://doi.org/10.5194/hess-27-83-2023
[9] Liu J, Shen C, O’Donncha F, Song Y, Zhi W, Beck HE, Bindas T, Kraabel N, Lawson K (2025) From RNNs to Transformers: benchmarking deep learning architectures for hydrologic prediction. Hydrol Earth Syst Sci 29:6811–6828. https://doi.org/10.5194/hess-29-6811-2025
[10] Nazari A, Jamshidi M, Roozbahani A, Golparvar B (2025) Groundwater level forecasting using empirical mode decomposition and wavelet-based long short-term memory (LSTM) neural networks. Groundw Sustain Dev 28:101397. https://doi.org/10.1016/j.gsd.2024.101397
[11] Nourani V, Khodkar K, Gebremichael M (2022) Uncertainty assessment of LSTM-based groundwater level predictions. Hydrol Sci J 67(5):773–790. https://doi.org/10.1080/02626667.2022.2046755
[12] Zhao Y, Yang L, Pan H, Li Y, Shao Y, Li J, Xie X (2025) Spatio-temporal prediction of groundwater vulnerability based on CNN-LSTM model with self-attention mechanism: a case study in Hetao Plain, northern China. J Environ Sci 153:128–142. https://doi.org/10.1016/j.jes.2024.03.052
[13] Chen Q, Jiang L, Qin H, Kontar RA (2025) Multi-agent collaborative Bayesian optimization via constrained Gaussian processes. Technometrics 67:32–45. https://doi.org/10.1080/00401706.2024.2365732
[14] Liu X-D, Zhang H-Y, Rui X-P, Sun W (2025) Multi-factor LSTM groundwater level prediction model with attention mechanism. Hydrology 45(02):73–79. https://doi.org/10.19797/j.cnki.1000-0852.20240161(in Chinese)
[15] Ding Y, Zhu Y, Feng J, Zhang P, Cheng Z (2020) Interpretable spatio-temporal attention LSTM model for flood forecasting. Neurocomputing 403:348–359. https://doi.org/10.1016/j.neucom.2020.04.110
[16] Ouyang S, Xu C, Xu W, Zhou M, Zhang J, Zhang G, Pan Z (2025) Intelligent decoupling of hydrological effects in Han River cascade dam system: spatial heterogeneity mechanisms via an LSTM-attention-SHAP interpretable framework. Hydrology 12(8):217. https://doi.org/10.3390/hydrology12080217
[17] Wang L, Jiang Z, Song L, Yu X, Yuan S, Zhang B (2024) A groundwater level spatiotemporal prediction model based on graph convolutional networks with a long short-term memory. J Hydroinform 26(11):2962–2979. https://doi.org/10.2166/hydro.2024.226
[18] Zhao X, Dong S, Rao H, Ming W (2025) Water flow forecasting model based on bidirectional long- and short-term memory and attention mechanism. Water 17(14):2118. https://doi.org/10.3390/w17142118
[19] Han Z, Li F, Zhao Y, Liu C (2025) Investigation into groundwater level prediction within a deep learning framework: incorporating the spatial dynamics of adjacent wells. J Hydrol 657:133097. https://doi.org/10.1016/j.jhydrol.2025.133097
[20] Shen C (2018) A transdisciplinary review of deep learning research and its relevance for water resources scientists. Water Resources Research 54:8558–8593. https://doi.org/10.1029/2018WR022643
[21] Belete DM, Huchaiah MD (2022) Grid search in hyperparameter optimization of  machine learning models for prediction of HIV/AIDS test results. Int J Comput Appl 44:875–886. https://doi.org/10.1080/1206212X.2021.1974663
[22] Luo G (2016) A review of automatic selection methods for machine learning algorithms and hyper-parameter values. Netw Model Anal Health Inform Bioinform 5:18. https://doi.org/10.1007/s13721-016-0125-6
[23] Wu J, Chen XY, Zhang H, Xiong LD, Lei H, Deng SH (2019) Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology 17:26–40. 
[24] Yegin AE, Karcioglu AA (2025) Dam water levels prediction using advanced hybrid deep learning model based on Bayesian optimization approach. Egypt Inform J 31:100760. https://doi.org/10.1016/j.eij.2025.100760
[25] Hochreiter S, Schmidhuber J (1997) Long Short-Term Memory. Neural Computation 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
[26] Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw 18:602–610. https://doi.org/10.1016/j.neunet.2005.06.042
[27] Siami-Namini S, Tavakoli N, Siami Namin A (2019) The performance of LSTM and BiLSTM in forecasting time series. 2019 IEEE International Conference on Big Data (Big Data), pp 3285–3292. https://doi.org/10.1109/BigData47090.2019.9005997
[28] Vaswani A, Shazeer N, Parmar N, et al. (2017) Attention is all you need. Advances in Neural Information Processing Systems 30 (NIPS 2017), pp 5998–6008.
[29] Shahriari B, Swersky K, Wang Z, Adams RP, de Freitas N (2016) Taking the human out of the loop: a review of Bayesian optimization. Proc IEEE 104:148–175. https://doi.org/10.1109/JPROC.2015.2494218
[30] Chen C, Zhu X, Kang X, Zhou H (2021) A deep learning algorithm for groundwater level prediction based on spatial-temporal attention mechanism. 2021 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), AB, Canada, 2021, pp 716–723. https://doi.org/10.1109/DASC-PICom-CBDCom-CyberSciTech52372.2021.00119
[31] Cui J, Yang B (2018) Review of Bayesian optimization methods and applications. Journal of Software Science 29(10):3068–3090. https://doi.org/10.13328/j.cnki .jos.005607(in Chinese)
[32] Patro, S Gopal & Sahu, Dr-Kishore Kumar. (2015) Normalization: A Preprocessing Stage. IARJSET. http://doi.org/10.17148/IARJSET.2015.2305
[33] Franceschi L, Donini M, Perrone V, Klein A, Archambeau C, Seeger M, Pontil M, Frasconi P (2025) Hyperparameter optimization in machine learning. Foundations and Trends in Machine Learning 18(6):975–1109. https://doi.org/10.1561/2200000088

Sponsors, Associates, and Links

---

• Power Systems Computation
  
  
• Internet of Things (IoT) and Engineering Applications
  
  
• Computing, Performance and Communication Systems
  
  
• Advances in Computer, Signals and Systems
  
  
• Journal of Network Computing and Applications
  
  
• Journal of Web Systems and Applications
  
  
• Journal of Electrotechnology, Electrical Engineering and Management
  
  
• Journal of Wireless Sensors and Sensor Networks
  
  
• Journal of Image Processing Theory and Applications
  
  
• Mobile Computing and Networking
  
  
• Vehicle Power and Propulsion
  
  
• Frontiers in Computer Vision and Pattern Recognition
  
  
• Knowledge Discovery and Data Mining Letters
  
  
• Big Data Analysis and Cloud Computing
  
  
• Electrical Insulation and Dielectrics
  
  
• Crypto and Information Security
  
  
• Journal of Neural Information Processing
  
  
• Collaborative and Social Computing
  
  
• International Journal of Network and Communication Technology
  
  
• File and Storage Technologies
  
  
• Frontiers in Genetic and Evolutionary Computation
  
  
• Optical Network Design and Modeling
  
  
• Journal of Virtual Reality and Artificial Intelligence
  
  
• Natural Language Processing and Speech Recognition
  
  
• Journal of High-Voltage
  
  
• Programming Languages and Operating Systems
  
  
• Visual Communications and Image Processing
  
  
• Journal of Systems Analysis and Integration
  
  
• Knowledge Representation and Automated Reasoning
  
  
• Review of Information Display Techniques
  
  
• Data and Knowledge Engineering
  
  
• Journal of Database Systems
  
  
• Journal of Cluster and Grid Computing
  
  
• Cloud and Service-Oriented Computing
  
  
• Journal of Networking, Architecture and Storage
  
  
• Journal of Software Engineering and Metrics
  
  
• Visualization Techniques
  
  
• Journal of Parallel and Distributed Processing
  
  
• Journal of Modeling, Analysis and Simulation
  
  
• Journal of Privacy, Trust and Security
  
  
• Journal of Cognitive Informatics and Cognitive Computing
  
  
• Lecture Notes on Wireless Networks and Communications
  
  
• International Journal of Computer and Communications Security
  
  
• Journal of Multimedia Techniques
  
  
• Automation and Machine Learning
  
  
• Computational Linguistics Letters
  
  
• Journal of Computer Architecture and Design
  
  
• Journal of Ubiquitous and Future Networks