Abstract
The downstream water level of a reservoir is influenced by its own discharge, changes in external hydraulic conditions, and the value of the previous period’s downstream water level, and is very sensitive to hourly changes. However, the influence mechanisms of this change and an accurate prediction method have yet to be investigated. In this study, the downstream water level of Xiangjiaba reservoir in China’s Jinsha river was used as a case study to analyze the impact of backwater effects caused by river rising during the flood season and the effect of sharp fluctuations caused by the peak regulation flow during the non-flood season. Moreover, an accurate prediction method at short-term two hourly scale is proposed. This study quantified the backwater effect caused by the rising tributaries of Hengjiang and Minjiang rivers. The random forest algorithm (RF) was used to downscale and rank multidimensional feature data, build different model factor sets, and build a downstream water level prediction model using five different methods. The results showed that the data mining model had the best fit and good prediction ability for the downstream water level of the Xiangjiaba reservoir under the influence of complicated hydraulic factors during the flood season, and can effectively control the fluctuation error during the peak regulation period. The research findings can be applied to other similar basins to improve the reservoir’s short-term refined operational levels.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of Data and Material
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
References
Ahmed AN, Yafouz A, Birima AHl, et al (2022) Water level prediction using various machine learning algorithms: a case study of Durian Tunggal river, Malaysia. Eng Appl Comput Fluid Mech 16(1):422–440. https://doi.org/10.1080/19942060.2021.2019128
Asadi S, Shahrabi J, Abbaszadeh P, Tabanmehr S (2013) A new hybrid artificial neural networks for rainfall–runoff process modeling. Neurocomputing 121:470–480. https://doi.org/10.1016/j.neucom.2013.05.023
Birgand F, Lellouche G, Appelboom TW (2013) Measuring flow in non-ideal conditions for short-term projects: uncertainties associated with the use of stage-discharge rating curves. J Hydrol 503:186–195. https://doi.org/10.1016/j.jhydrol.2013.09.007
Chen X, Zhou J, Jia B et al (2022) Novel and robust outflow forecasting methods for upstream large hydropower stations. J Hydrol 609:127742. https://doi.org/10.1016/j.jhydrol.2022.127742
Frings RM, Berbee BM, Erkens G, Kleinhans MG, Gouw MP (2009) Human-induced changes in bed shear stress and bed grain size in the River Waal (The Netherlands) during the past 900 years. Earth Surf Proc Land 34(4):503–514. https://doi.org/10.1002/esp.1746
Generoso TN, da Silva DD, Amorim RS et al (2022) Methodology for estimati-ng streamflow by water balance and rating curve methods based on logist-icregression. Water Resour Manag 36(11):4389–4402. https://doi.org/10.1007/s11269-022-03259-1
Hamitouche M, Molina J-L (2022) A review of AI methods for the prediction of high-flow extremal hydrology. Water Resour Manag 36(10):3859–3876. https://doi.org/10.1007/s11269-022-03240-y
Huang S, Xia J, Yl Wang et al (2022) Coupling machine learning into hydrodynamic models to improve river modeling with complex boundary conditions. Water Resour Res 58(10):e2022WR032183. https://doi.org/10.1029/2022WR032183
International Organization for Standardization (2020) Hydrometry — Measurement of liquid flow in open channels — Determination of the stage–discharge relationship (ISO Standard No. 18320:2020). https://www.iso.org/standard/62154.html
Jamei M, Ali M, Al M et al (2022) Forecasting daily flood water level using hybrid advanced machine learning based time-varying filtered hmpiri-cal mode decomposition approach. Water Resour Manag 36(12):4637–4676. https://doi.org/10.1007/s11269-022-03270-6
Korsic SA, Notarnicola C, Quirno MU, Cara L (2023) Assessing a data-driven approach for monthly runoff prediction in a mountain basin of the Central Andes of Argentina. Environ Chall 10:100680. https://doi.org/10.1016/j.envc.2023.100680
Li FF, Cao H, Hao CF et al (2021) Daily streamflow forecasting based on flowpattern recognition. Water Resour Manag 35(13):4601–4620. https://doi.org/10.1007/s11269-021-02971-8
Liro M, Ruiz-Villanueva V, Pl MikuĹ› et al (2020) Changes in the hydrodynamics of a mountain river induced by dam reservoir backwater. Sci Total Environ 744:140555. https://doi.org/10.1016/j.scitotenv.2020.140555
Liro M, Nones M, Mikuś P, Plesiński K (2022) Modelling the effects of dam reservoir backwater fluctuations on the hydrodynamics of a small mountain stream. Water 14(19):3166. https://doi.org/10.3390/w14193166
Ma X, Hu H, Ren Y (2023) A hybrid deep learning model based on feature capture of water level influencing factors and prediction error correction for water level prediction of cascade hydropower stations under multiple time scales. J Hydrol 617:129044. https://doi.org/10.1016/j.jhydrol.2022.129044
Manfreda S (2018) On the derivation of flow rating curves in data-scarce environments. J Hydrol 562:151–154. https://doi.org/10.1016/j.jhydrol.2018.04.058
Ming B, Liu P, Cheng L et al (2018) Optimal daily generation scheduling of large hydro–photovoltaic hybrid power plants. Energy Convers Manag 171:528–540. https://doi.org/10.1016/j.enconman.2018.06.001
Napolitano G, See L, Calvo B et al (2010) A conceptual and neural network model for real-time flood forecastingof the Tiber River in Rome. Phys Chem Earth 35(3–5):187–194. https://doi.org/10.1016/j.pce.2009.12.004
Pan M, Zhou H, Cao J et al (2020) Water level prediction model based on GRU and CNN. IEEE Access 8:60090–60100. https://doi.org/10.1109/access.2020.2982433
Rajesh M, Anishka S, Viksit PS et al (2022) Improving short-range reservoir inflow forecasts with machine learning model combination. Water Resour Manag 37(1):75–90. https://doi.org/10.1007/s11269-022-03356-1
Shang Y, Xu Y, Shang L et al (2019) A method of direct, real-time forecasting of downstream water levels via hydropower station reregulation: a case study from Gezhouba Hydropower Plant, China. J Hydrol 573:895–907. https://doi.org/10.1016/j.jhydrol.2019.04.017
Shao Q, Dutta D, Karim F, Petheram C (2018) A method for extending stage-discharge relationships using a hydrodynamic model and quantifying the associated uncertainty. J Hydrol 556:154–172. https://doi.org/10.1016/j.jhydrol.2017.11.012
Sung J, Lee J, Chung I-M, Heo J-H (2017) Hourly water level forecasting at tributary affected by Main River Condition. Water 9(9):644. https://doi.org/10.3390/w9090644
Tofiq YM, Latif SD, Ahmed AN et al (2022) Optimized model inputs selectionsfor enhancing river streamflow forecasting accuracy using different artifici-al intelligence techniques. Water Resour Manage 36(15):5999–6016. https://doi.org/10.1007/s11269-022-03339-2
Tsai CW (2005) Flood routing in mild-sloped rivers-wave characteristics and downstream backwater effect. J Hydrol 308(1–4):151–167. https://doi.org/10.1016/j.jhydrol.2004.10.027
Wang X, Yan X, Duan H, Liu X, Huang E (2019) Experimental study on the influence of river flow confluences on the open channel stage–discharge relationship. Hydrol Sci J 64(16):2025–2039. https://doi.org/10.1080/02626667.2019.1661415
Yang Y, Zhang M, Zhu L et al (2017) Influence of large reservoir operation on water-levels and flows in reaches below dam: case study of the Three Gorges Reservoir. Sci Rep 7(1):15640. https://doi.org/10.1038/s41598-017-15677-y
Zhang J, Chen X, Khan A et al (2021) Daily runoff forecasting by deep recu-rsive neural network. J Hydrol 596:126067. https://doi.org/10.1016/j.jhydrol.2021.126067
Funding
This work is supported by the National Key Research and Development Program of China (2021YFC3200303, 2021YFC3200301) and the National Natural Science Foundation of China (No. 52039004), and special thanks to the anonymous reviewers and editors for their constructive comments.
Author information
Authors and Affiliations
Contributions
Jingwei Huang, Hui Qin and Yongchuan Zhang: Conceptualization, Methodology, Supervision, Writing, Investigation, Funding acquisition, Programming. Dongkai Hou, Sipeng Zhu, Pingan Ren: Reviewing, Formal analysis and Visualization.
Corresponding author
Ethics declarations
Ethical Approval
All authors kept the “Ethical Responsibilities of Authors”.
Consent to Participate
All authors gave explicit consent to participate in this study.
Consent to Publish
All authors agree to publish.
Competing Interests
The authors declare no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Huang, J., Qin, H., Zhang, Y. et al. Short-term Prediction Method of Reservoir Downstream Water Level Under Complicated Hydraulic Influence. Water Resour Manage 37, 4475–4490 (2023). https://doi.org/10.1007/s11269-023-03570-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11269-023-03570-5