IDEAS home Printed from https://ideas.repec.org/a/spr/nathaz/v121y2025i8d10.1007_s11069-025-07187-2.html
   My bibliography  Save this article

A spatiotemporal watershed-scale machine-learning model for hourly and daily flood-water level prediction: the case of the tidal Beigang River, Taiwan

Author

Listed:
  • Wen-Dar Guo

    (National Science and Technology Center for Disaster Reduction)

  • Wei-Bo Chen

    (National Science and Technology Center for Disaster Reduction)

  • Chih-Hsin Chang

    (National Science and Technology Center for Disaster Reduction)

Abstract

Previous studies have employed the water level information at the individual flood gauging stations to perform predictions. However, it is widely recognized that the water levels at downstream stations are correlated with those at upstream stations. Therefore, the innovation and contribution of this study is the proposal of a new spatiotemporal watershed-scale machine learning (ML) model for hourly and daily water level prediction in the tidal Beigang River, Taiwan, considering the correlation between flood gauging stations. The proposed new model is based on a novel integration of a primary learner of a spatial–temporal graph convolutional network, an enhancing learner, and residual error corrections. By extracting spatiotemporal features from a hydrological network, the measured ten-year hydrological data (2012–2022) were employed. Three multioutput (MO)-based ML models were presented and utilized as benchmarks, including extra tree regression (MO-ETR), light gradient boosting machine regression (MO-LGBMR), and support vector regression (MO-SVR). The SHapley Additive exPlanations (SHAP) method was used to investigate the global contribution of inputs to the water level predictions. Two existing encoder-decoder (ED)-based deep learning (DL) models, namely gated recurrent units (ED-GRU) and long short‐term memory (ED-LSTM), were employed to examine the improved prediction performance of proposed model. Compared to the three MO-based and two ED-based DL models, the proposed model is more feasible, deterministic, and accurate. Regarding the hourly water level prediction performance, the proposed model exhibited a notable improvement in the total-averaged Nash–Sutcliffe efficiency (NSE) performance when compared to the MO-ETR, MO-LGBMR, MO-SVR, ED-LSTM, and ED-GRU models, with a percentage enhancement of 49.2%, 31.4%, 29.2%, 33.3%, and 32.2%, respectively. This study further provided a test study with insights from an additional Cho-Shui River basin, with the objective of better investigating the applicability of the proposed model. Satisfactory and reliable results suggest that the proposed model significantly contributes to and serves as a reference for forecasting the evolution of river floods.

Suggested Citation

  • Wen-Dar Guo & Wei-Bo Chen & Chih-Hsin Chang, 2025. "A spatiotemporal watershed-scale machine-learning model for hourly and daily flood-water level prediction: the case of the tidal Beigang River, Taiwan," Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, Springer;International Society for the Prevention and Mitigation of Natural Hazards, vol. 121(8), pages 9563-9611, May.
    • Handle: RePEc:spr:nathaz:v:121:y:2025:i:8:d:10.1007_s11069-025-07187-2
    DOI: 10.1007/s11069-025-07187-2
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s11069-025-07187-2
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.
    File URL: https://libkey.io/10.1007/s11069-025-07187-2?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Gianluca Bontempi & Souhaib Ben Taieb & Yann-Aël Le Borgne, 2013. "Machine learning strategies for time series forecasting," ULB Institutional Repository 2013/167761, ULB -- Universite Libre de Bruxelles.
    2. Hanifi, Shahram & Cammarono, Andrea & Zare-Behtash, Hossein, 2024. "Advanced hyperparameter optimization of deep learning models for wind power prediction," Renewable Energy, Elsevier, vol. 221(C).
    3. Mohammed Majeed Hameed & Mohamed Khalid AlOmar & Faidhalrahman Khaleel & Nadhir Al-Ansari, 2021. "An Extra Tree Regression Model for Discharge Coefficient Prediction: Novel, Practical Applications in the Hydraulic Sector and Future Research Directions," Mathematical Problems in Engineering, Hindawi, vol. 2021, pages 1-19, September.
    4. Wu, Qiang & Zheng, Hongling & Guo, Xiaozhu & Liu, Guangqiang, 2022. "Promoting wind energy for sustainable development by precise wind speed prediction based on graph neural networks," Renewable Energy, Elsevier, vol. 199(C), pages 977-992.
    5. van Zyl, Corne & Ye, Xianming & Naidoo, Raj, 2024. "Harnessing eXplainable artificial intelligence for feature selection in time series energy forecasting: A comparative analysis of Grad-CAM and SHAP," Applied Energy, Elsevier, vol. 353(PA).
    6. Khan, Waqas & Walker, Shalika & Zeiler, Wim, 2022. "Improved solar photovoltaic energy generation forecast using deep learning-based ensemble stacking approach," Energy, Elsevier, vol. 240(C).
    7. Namal Rathnayake & Upaka Rathnayake & Tuan Linh Dang & Yukinobu Hoshino, 2023. "Water level prediction using soft computing techniques: A case study in the Malwathu Oya, Sri Lanka," PLOS ONE, Public Library of Science, vol. 18(4), pages 1-21, April.
    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. Spiliotis, Evangelos & Makridakis, Spyros & Kaltsounis, Anastasios & Assimakopoulos, Vassilios, 2021. "Product sales probabilistic forecasting: An empirical evaluation using the M5 competition data," International Journal of Production Economics, Elsevier, vol. 240(C).
    2. Khan, Waqas & Somers, Ward & Walker, Shalika & de Bont, Kevin & Van der Velden, Joep & Zeiler, Wim, 2023. "Comparison of electric vehicle load forecasting across different spatial levels with incorporated uncertainty estimation," Energy, Elsevier, vol. 283(C).
    3. Ashkan Safari & Hamed Kheirandish Gharehbagh & Morteza Nazari Heris, 2023. "DeepVELOX: INVELOX Wind Turbine Intelligent Power Forecasting Using Hybrid GWO–GBR Algorithm," Energies, MDPI, vol. 16(19), pages 1-22, September.
    4. Wang, Pengfei & Liu, Yide & Li, Yuchen & Tang, Xianlin & Ren, Qinlong, 2024. "Power prediction for salinity-gradient osmotic energy conversion based on multiscale and multidimensional convolutional neural network," Energy, Elsevier, vol. 313(C).
    5. Chen, Xin & Ye, Xiaoling & Shi, Jian & Zhang, Yingchao & Xiong, Xiong, 2024. "A spatial transfer-based hybrid model for wind speed forecasting," Energy, Elsevier, vol. 313(C).
    6. Boudy Bilal & Kaan Yetilmezsoy & Mohammed Ouassaid, 2024. "Benchmarking of Various Flexible Soft-Computing Strategies for the Accurate Estimation of Wind Turbine Output Power," Energies, MDPI, vol. 17(3), pages 1-36, February.
    7. Zheng, Lingwei & Su, Ran & Sun, Xinyu & Guo, Siqi, 2023. "Historical PV-output characteristic extraction based weather-type classification strategy and its forecasting method for the day-ahead prediction of PV output," Energy, Elsevier, vol. 271(C).
    8. Yang, Yanru & Liu, Yu & Zhang, Yihang & Shu, Shaolong & Zheng, Junsheng, 2025. "DEST-GNN: A double-explored spatio-temporal graph neural network for multi-site intra-hour PV power forecasting," Applied Energy, Elsevier, vol. 378(PA).
    9. Wang, Chao & Lin, Hong & Yang, Ming & Fu, Xiaoling & Yuan, Yue & Wang, Zewei, 2024. "A novel chaotic time series wind power point and interval prediction method based on data denoising strategy and improved coati optimization algorithm," Chaos, Solitons & Fractals, Elsevier, vol. 187(C).
    10. Anastasios Petropoulos & Vassilis Siakoulis & Konstantinos P. Panousis & Loukas Papadoulas & Sotirios Chatzis, 2023. "Macroeconomic forecasting and sovereign risk assessment using deep learning techniques," Papers 2301.09856, arXiv.org.
    11. Pei, Jingyin & Dong, Yunxuan & Guo, Pinghui & Wu, Thomas & Hu, Jianming, 2024. "A Hybrid Dual Stream ProbSparse Self-Attention Network for spatial–temporal photovoltaic power forecasting," Energy, Elsevier, vol. 305(C).
    12. Wang, Yong & Yang, Zhongsen & Zhou, Ying & Liu, Hao & Yang, Rui & Sun, Lang & Sapnken, Flavian Emmanuel & Narayanan, Govindasami, 2025. "A novel structure adaptive new information priority grey Bernoulli model and its application in China's renewable energy production," Renewable Energy, Elsevier, vol. 239(C).
    13. Li, Jianfang & Jia, Li & Zhou, Chengyu, 2024. "Probability density function based adaptive ensemble learning with global convergence for wind power prediction," Energy, Elsevier, vol. 312(C).
    14. Voyant, Cyril & Notton, Gilles & Duchaud, Jean-Laurent & Gutiérrez, Luis Antonio García & Bright, Jamie M. & Yang, Dazhi, 2022. "Benchmarks for solar radiation time series forecasting," Renewable Energy, Elsevier, vol. 191(C), pages 747-762.
    15. Mohammad Mehdi Sharifi Nevisi & Mehrdad Shoeibi & Francisco Hernando-Gallego & Diego Martín & Sarvenaz Sadat Khatami, 2025. "An Evolutionary Deep Reinforcement Learning-Based Framework for Efficient Anomaly Detection in Smart Power Distribution Grids," Energies, MDPI, vol. 18(10), pages 1-35, May.
    16. Gupta, Priya & Singh, Rhythm, 2023. "Combining simple and less time complex ML models with multivariate empirical mode decomposition to obtain accurate GHI forecast," Energy, Elsevier, vol. 263(PC).
    17. Raeesi, Ramin & Sahebjamnia, Navid & Mansouri, S. Afshin, 2023. "The synergistic effect of operational research and big data analytics in greening container terminal operations: A review and future directions," European Journal of Operational Research, Elsevier, vol. 310(3), pages 943-973.
    18. Yifei Chen & Zhihan Fu, 2023. "Multi-Step Ahead Forecasting of the Energy Consumed by the Residential and Commercial Sectors in the United States Based on a Hybrid CNN-BiLSTM Model," Sustainability, MDPI, vol. 15(3), pages 1-21, January.
    19. repec:ers:journl:v:xxiv:y:2021:i:special2:p:513-522 is not listed on IDEAS
    20. Xiao, Yulong & Zou, Chongzhe & Chi, Hetian & Fang, Rengcun, 2023. "Boosted GRU model for short-term forecasting of wind power with feature-weighted principal component analysis," Energy, Elsevier, vol. 267(C).
    21. Vladimir Franki & Darin Majnarić & Alfredo Višković, 2023. "A Comprehensive Review of Artificial Intelligence (AI) Companies in the Power Sector," Energies, MDPI, vol. 16(3), pages 1-35, January.

    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:spr:nathaz:v:121:y:2025:i:8:d:10.1007_s11069-025-07187-2. 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: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.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.