IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v16y2024i2p653-d1317468.html
   My bibliography  Save this article

Comparison of Multiple Machine Learning Methods for Correcting Groundwater Levels Predicted by Physics-Based Models

Author

Listed:
  • Guanyin Shuai

    (School of Water Resources and Environment, China University of Geosciences (Beijing), Beijing 100083, China)

  • Yan Zhou

    (School of Water Resources and Environment, China University of Geosciences (Beijing), Beijing 100083, China)

  • Jingli Shao

    (School of Water Resources and Environment, China University of Geosciences (Beijing), Beijing 100083, China)

  • Yali Cui

    (School of Water Resources and Environment, China University of Geosciences (Beijing), Beijing 100083, China)

  • Qiulan Zhang

    (School of Water Resources and Environment, China University of Geosciences (Beijing), Beijing 100083, China)

  • Chaowei Jin

    (School of Water Resources and Environment, China University of Geosciences (Beijing), Beijing 100083, China)

  • Shuyuan Xu

    (Department of Geology and Surveying and Mapping, Shanxi Institute of Energy, Jinzhong 030600, China)

Abstract

Accurate groundwater level (GWL) prediction is crucial in groundwater resource management. Currently, it relies mainly on physics-based models for prediction and quantitative analysis. However, physics-based models used for prediction often have errors in structure, parameters, and data, resulting in inaccurate GWL predictions. In this study, machine learning algorithms were used to correct the prediction errors of physics-based models. First, a MODFLOW groundwater flow model was created for the Hutuo River alluvial fan in the North China Plain. Then, using the observed GWLs from 10 monitoring wells located in the upper, middle, and lower parts of the alluvial fan as the test standard, three algorithms—random forest (RF), extreme gradient boosting (XGBoost), and long short-term memory (LSTM)—were compared for their abilities to correct MODFLOW’s predicted GWLs of these 10 wells under two sets of feature variables. The results show that the RF and XGBoost algorithms are not suitable for correcting predicted GWLs that exhibit continuous rising or falling trends, but the LSTM algorithm has the ability to correct them. During the prediction period, the LSTM2 model, which incorporates additional source–sink feature variables based on MODFLOW’s predicted GWLs, can improve the Pearson correlation coefficient ( PR ) for 80% of wells, with a maximum increase of 1.26 and a minimum increase of 0.02, and can reduce the root mean square error ( RMSE ) for 100% of the wells with a maximum decrease of 1.59 m and a minimum decrease of 0.17 m. And it also outperforms the MODFLOW model in capturing the long-term trends and short-term seasonal fluctuations of GWLs. However, the correction effect of the LSTM1 model (using only MODFLOW’s predicted GWLs as a feature variable) is inferior to that of the LSTM2 model, indicating that multiple feature variables are superior to a single feature variable. Temporally and spatially, the greater the prediction error of the MODFLOW model, the larger the correction magnitude of the LSTM2 model.

Suggested Citation

  • Guanyin Shuai & Yan Zhou & Jingli Shao & Yali Cui & Qiulan Zhang & Chaowei Jin & Shuyuan Xu, 2024. "Comparison of Multiple Machine Learning Methods for Correcting Groundwater Levels Predicted by Physics-Based Models," Sustainability, MDPI, vol. 16(2), pages 1-18, January.
  • Handle: RePEc:gam:jsusta:v:16:y:2024:i:2:p:653-:d:1317468
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/16/2/653/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2071-1050/16/2/653/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Seyed Amir Naghibi & Kourosh Ahmadi & Alireza Daneshi, 2017. "Application of Support Vector Machine, Random Forest, and Genetic Algorithm Optimized Random Forest Models in Groundwater Potential Mapping," Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), Springer;European Water Resources Association (EWRA), vol. 31(9), pages 2761-2775, July.
    2. Markus Reichstein & Gustau Camps-Valls & Bjorn Stevens & Martin Jung & Joachim Denzler & Nuno Carvalhais & Prabhat, 2019. "Deep learning and process understanding for data-driven Earth system science," Nature, Nature, vol. 566(7743), pages 195-204, February.
    3. J. S. Famiglietti, 2014. "The global groundwater crisis," Nature Climate Change, Nature, vol. 4(11), pages 945-948, November.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Madhumita Sahoo & Aman Kasot & Anirban Dhar & Amlanjyoti Kar, 2018. "On Predictability of Groundwater Level in Shallow Wells Using Satellite Observations," Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), Springer;European Water Resources Association (EWRA), vol. 32(4), pages 1225-1244, March.
    2. Licheng Liu & Wang Zhou & Kaiyu Guan & Bin Peng & Shaoming Xu & Jinyun Tang & Qing Zhu & Jessica Till & Xiaowei Jia & Chongya Jiang & Sheng Wang & Ziqi Qin & Hui Kong & Robert Grant & Symon Mezbahuddi, 2024. "Knowledge-guided machine learning can improve carbon cycle quantification in agroecosystems," Nature Communications, Nature, vol. 15(1), pages 1-15, December.
    3. Rozenstein, Offer & Fine, Lior & Malachy, Nitzan & Richard, Antoine & Pradalier, Cedric & Tanny, Josef, 2023. "Data-driven estimation of actual evapotranspiration to support irrigation management: Testing two novel methods based on an unoccupied aerial vehicle and an artificial neural network," Agricultural Water Management, Elsevier, vol. 283(C).
    4. Jonathan O. Hernandez, 2022. "Ecophysiological Effects of Groundwater Drawdown on Phreatophytes: Research Trends during the Last Three Decades," Land, MDPI, vol. 11(11), pages 1-18, November.
    5. Le Duc Anh & Ho Huu Loc & Kim N. Irvine & Tran Thanh & Luong Quang Tuong, 2021. "The waterscape of groundwater exploitation for domestic uses in District 12, Ho Chi Minh City, Vietnam," Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, Springer, vol. 23(5), pages 7652-7669, May.
    6. Jiang, Hou & Lu, Ning & Huang, Guanghui & Yao, Ling & Qin, Jun & Liu, Hengzi, 2020. "Spatial scale effects on retrieval accuracy of surface solar radiation using satellite data," Applied Energy, Elsevier, vol. 270(C).
    7. Zappa, Luca & Dari, Jacopo & Modanesi, Sara & Quast, Raphael & Brocca, Luca & De Lannoy, Gabrielle & Massari, Christian & Quintana-Seguí, Pere & Barella-Ortiz, Anais & Dorigo, Wouter, 2024. "Benefits and pitfalls of irrigation timing and water amounts derived from satellite soil moisture," Agricultural Water Management, Elsevier, vol. 295(C).
    8. Rathore, Vijay Singh & Nathawat, Narayan Singh & Bhardwaj, Seema & Yadav, Bhagirath Mal & Santra, Priyabrata & Kumar, Mahesh & Shekhawat, Ravindra Singh & Reager, Madan Lal & Yadav, Shish Ram & Lal, B, 2022. "Alternative cropping systems and optimized management practices for saving groundwater and enhancing economic and environmental sustainability," Agricultural Water Management, Elsevier, vol. 272(C).
    9. Hrozencik, R. Aaron, 2018. "Energy, Food, and Water; Electricity Cooperative Pricing and Groundwater Irrigation Decisions," 2018 Annual Meeting, August 5-7, Washington, D.C. 274322, Agricultural and Applied Economics Association.
    10. Wen Zhang & Jing Li & Yunhao Chen & Yang Li, 2019. "A Surrogate-Based Optimization Design and Uncertainty Analysis for Urban Flood Mitigation," Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), Springer;European Water Resources Association (EWRA), vol. 33(12), pages 4201-4214, September.
    11. Feng, Jiaojiao & Wang, Weizhen & Xu, Feinan & Wang, Shengtang, 2024. "Evaluating the ability of deep learning on actual daily evapotranspiration estimation over the heterogeneous surfaces," Agricultural Water Management, Elsevier, vol. 291(C).
    12. Viet-Tien Nguyen & Trong Hien Tran & Ngoc Anh Ha & Van Liem Ngo & Al-Ansari Nadhir & Van Phong Tran & Huu Duy Nguyen & Malek M. A. & Ata Amini & Indra Prakash & Lanh Si Ho & Binh Thai Pham, 2019. "GIS Based Novel Hybrid Computational Intelligence Models for Mapping Landslide Susceptibility: A Case Study at Da Lat City, Vietnam," Sustainability, MDPI, vol. 11(24), pages 1-24, December.
    13. Xiukang Wang, 2022. "Managing Land Carrying Capacity: Key to Achieving Sustainable Production Systems for Food Security," Land, MDPI, vol. 11(4), pages 1-21, March.
    14. Mohanad A. Deif & Ahmed A. A. Solyman & Mohammed H. Alsharif & Seungwon Jung & Eenjun Hwang, 2021. "A Hybrid Multi-Objective Optimizer-Based SVM Model for Enhancing Numerical Weather Prediction: A Study for the Seoul Metropolitan Area," Sustainability, MDPI, vol. 14(1), pages 1-17, December.
    15. Zhang, Shuangyi & Li, Xichen, 2021. "Future projections of offshore wind energy resources in China using CMIP6 simulations and a deep learning-based downscaling method," Energy, Elsevier, vol. 217(C).
    16. Florian Reiner & Martin Brandt & Xiaoye Tong & David Skole & Ankit Kariryaa & Philippe Ciais & Andrew Davies & Pierre Hiernaux & Jérôme Chave & Maurice Mugabowindekwe & Christian Igel & Stefan Oehmcke, 2023. "More than one quarter of Africa’s tree cover is found outside areas previously classified as forest," Nature Communications, Nature, vol. 14(1), pages 1-10, December.
    17. Schmitt, Rafael Jan Pablo & Rosa, Lorenzo, 2024. "Dams for hydropower and irrigation: Trends, challenges, and alternatives," Renewable and Sustainable Energy Reviews, Elsevier, vol. 199(C).
    18. Anna Boser & Kelly Caylor & Ashley Larsen & Madeleine Pascolini-Campbell & John T. Reager & Tamma Carleton, 2024. "Field-scale crop water consumption estimates reveal potential water savings in California agriculture," Nature Communications, Nature, vol. 15(1), pages 1-10, December.
    19. Sears, Louis S. & Lawell, C.Y. Cynthia Lin & Torres, Gerald & Walter, M. Todd, 2022. "Moment-based Markov Equilibrium Estimation of High-Dimension Dynamic Games: An Application to Groundwater Management in California," 2022 Annual Meeting, July 31-August 2, Anaheim, California 322187, Agricultural and Applied Economics Association.
    20. Wang, Yukuan & Liu, Jingxian & Liu, Ryan Wen & Wu, Weihuang & Liu, Yang, 2023. "Interval prediction of vessel trajectory based on lower and upper bound estimation and attention-modified LSTM with bayesian optimization," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 630(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:16:y:2024:i:2:p:653-:d:1317468. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.