Prediction of discharge in a tidal river using the LSTM-based sequence-to-sequence models

Zhigao Chen; Yan Zong; Zihao Wu; Zhiyu Kuang; Shengping Wang

doi:10.1007/s13131-024-2343-6

Volume 43 Issue 7

Jul. 2024

Turn off MathJax

Article Contents

Abstract

References

Article Navigation > Acta Oceanologica Sinica > 2024 > 43(7): 40-51

Zhigao Chen, Yan Zong, Zihao Wu, Zhiyu Kuang, Shengping Wang. Prediction of discharge in a tidal river using the LSTM-based sequence-to-sequence models[J]. Acta Oceanologica Sinica, 2024, 43(7): 40-51. doi: 10.1007/s13131-024-2343-6

Citation:

Zhigao Chen, Yan Zong, Zihao Wu, Zhiyu Kuang, Shengping Wang. Prediction of discharge in a tidal river using the LSTM-based sequence-to-sequence models[J]. Acta Oceanologica Sinica, 2024, 43(7): 40-51. doi: 10.1007/s13131-024-2343-6

Citation:

PDF( 1926 KB)

Prediction of discharge in a tidal river using the LSTM-based sequence-to-sequence models

doi: 10.1007/s13131-024-2343-6

Zhigao Chen^{1, 2
,
,},
Yan Zong¹,
Zihao Wu¹,
Zhiyu Kuang¹,
Shengping Wang^{1, 2}

1.
Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake of Ministry of Natural Resources, East China University of Technology, Nanchang 330013, China
2.
School of Surveying and Geoinformation Engineering, East China University of Technology, Nanchang 330013, China

Funds: The National Natural Science Foundation of China under contract Nos 42266006 and 41806114; the Jiangxi Provincial Natural Science Foundation under contract Nos 20232BAB204089 and 20202ACBL214019.

More Information

Corresponding author: E-mail: 531214372@qq.com
Received Date: 2024-02-02
Accepted Date: 2024-04-27

Available Online: 2024-05-08

Publish Date: 2024-07-30

Abstract

Abstract

The complexity of river-tide interaction poses a significant challenge in predicting discharge in tidal rivers. Long short-term memory (LSTM) networks excel in processing and predicting crucial events with extended intervals and time delays in time series data. Additionally, the sequence-to-sequence (Seq2Seq) model, known for handling temporal relationships, adapting to variable-length sequences, effectively capturing historical information, and accommodating various influencing factors, emerges as a robust and flexible tool in discharge forecasting. In this study, we introduce the application of LSTM-based Seq2Seq models for the first time in forecasting the discharge of a tidal reach of the Changjiang River (Yangtze River) Estuary. This study focuses on discharge forecasting using three key input characteristics: flow velocity, water level, and discharge, which means the structure of multiple input and single output is adopted. The experiment used the discharge data of the whole year of 2020, of which the first 80% is used as the training set, and the last 20% is used as the test set. This means that the data covers different tidal cycles, which helps to test the forecasting effect of different models in different tidal cycles and different runoff. The experimental results indicate that the proposed models demonstrate advantages in long-term, mid-term, and short-term discharge forecasting. The Seq2Seq models improved by 6%–60% and 5%–20% of the relative standard deviation compared to the harmonic analysis models and improved back propagation neural network models in discharge prediction, respectively. In addition, the relative accuracy of the Seq2Seq model is 1% to 3% higher than that of the LSTM model. Analytical assessment of the prediction errors shows that the Seq2Seq models are insensitive to the forecast lead time and they can capture characteristic values such as maximum flood tide flow and maximum ebb tide flow in the tidal cycle well. This indicates the significance of the Seq2Seq models.

FullText(HTML)

References(36)

References

Amanambu A C, Mossa J, Chen Yin-Hsuen. 2022. Hydrological drought forecasting using a deep transformer model. Water, 14(22): 3611

Anshuka A, Chandra R, Buzacott A J V, et al. 2022. Spatio temporal hydrological extreme forecasting framework using LSTM deep learning model. Stochastic Environmental Research and Risk Assessment, 36(10): 3467–3485

Bai Longhu, Xu Hang. 2021. Accurate estimation of tidal level using bidirectional long short-term memory recurrent neural network. Ocean Engineering, 235: 108765

Cai Huayang, Li Bo, Garel E, et al. 2023. A data-driven model to quantify the impact of river discharge on tide-river dynamics in the Yangtze River estuary. Journal of Hydrology, 620: 129411

Cho K, Van Merriënboer B, Gulcehre C, et al. 2014. Learning phrase representations using RNN encoder–decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Doha, The State of Qatar: ACL, 1724–1734

Dennis R E, Long E E. 1971. A user’s guide to a computer program for harmonic analysis of data at tidal frequencies. NOAA NOS, 41: 3–11

Foreman M G G. 1977. Manual for tidal heights analysis and prediction. Pacific Marine Science Report. Sidney, BC, Canada: Institute of Ocean Sciences, Patricia Bay, 77–10

Foreman M G G, Henry R F. 1989. The harmonic analysis of tidal model time series. Advances in Water Resources, 12(3): 109–120

Gan Min, Chen Yongping, Pan Haidong, et al. 2024. Study on the spatiotemporal variation of the Yangtze estuarine tidal species. Estuarine, Coastal and Shelf Science, 298: 108637

Harris D L, Pore N A, Cummings R A. 2015. Tide and tidal current prediction by high speed digital computer. The International Hydrographic Review, 42(1): 95–103

Hidayat H, Hoitink A J F, Sassi M G, et al. 2014. Prediction of discharge in a tidal river using artificial neural networks. Journal of Hydrologic Engineering, 19(8): 04014006

Hochreiter S, Schmidhuber J. 1997. Long short-term memory. Neural Computation, 9(8): 1735–1780

Jain M, Saihjpal V, Singh N, et al. 2022. An overview of variants and advancements of PSO algorithm. Applied Sciences, 12(17): 8392

Ji Zhong, Xiong Kailin, Pang Yanwei, et al. 2020. Video summarization with attention-based encoder–decoder networks. IEEE Transactions on Circuits and Systems for Video Technology, 30(6): 1709–1717

Kao I-Feng, Zhou Yanlai, Chang Li-Chiu, et al. 2020. Exploring a long short-term memory based encoder-decoder framework for multi-step-ahead flood forecasting. Journal of Hydrology, 583: 124631

Kennedy J, Eberhart R. 1995. Particle swarm optimization. In: Proceedings of ICNN’95 - International Conference on Neural Networks. Perth: IEEE, 1942–1948

Kratzert F, Herrnegger M, Klotz D, et al. 2019. NeuralHydrology—Interpreting LSTMs in hydrology. In: Samek W, Montavon G, Vedaldi A, et al, eds. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. Cham: Springer, 347–362

Kratzert F, Klotz D, Brenner C, et al. 2018. Rainfall–runoff modelling using long short-term memory (LSTM) networks. Hydrology and Earth System Sciences, 22(11): 6005–6022

Lee T L. 2004. Back-propagation neural network for long-term tidal predictions. Ocean Engineering, 31(2): 225–238

Lees T, Reece S, Kratzert F, et al. 2022. Hydrological concept formation inside long short-term memory (LSTM) networks. Hydrology and Earth System Sciences, 26(12): 3079–3101

Matte P, Jay D A, Zaron E D. 2013. Adaptation of classical tidal harmonic analysis to nonstationary tides, with application to river tides. Journal of Atmospheric and Oceanic Technology, 30(3): 569–589

Olah C. 2015. Understanding LSTM networks. https://colah.github.io/posts/2015-08-Understanding-LSTMs/[2015-08]

Pan Haidong, Jiao Shengyi, Xu Tengfei, et al. 2022. Investigation of tidal evolution in the Bohai Sea using the combination of satellite altimeter records and numerical models. Estuarine, Coastal and Shelf Science, 279: 108140

Pan Haidong, Lv Xianqing, Wang Yingying, et al. 2018. Exploration of tidal-fluvial interaction in the columbia river estuary using S_TIDE. Journal of Geophysical Research: Oceans, 123(9): 6598–6619

Pan Haidong, Xu Tengfei, Wei Zexun. 2023. A modified tidal harmonic analysis model for short-term water level observations. Ocean Modelling, 186: 102251

Pawlowicz R, Beardsley B, Lentz S. 2002. Classical tidal harmonic analysis including error estimates in MATLAB using T_TIDE. Computers & Geosciences, 28(8): 929–937

Rumelhart D E, Hinton G E, Williams R J. 1986. Learning representations by back-propagating errors. Nature, 323(6088): 533–536

Sahoo B B, Jha R, Singh A, et al. 2019. Long short-term memory (LSTM) recurrent neural network for low-flow hydrological time series forecasting. Acta Geophysica, 67(5): 1471–1481

Shin M J, Moon S H, Kang K G, et al. 2020. Analysis of groundwater level variations caused by the changes in groundwater withdrawals using long short-term memory network. Hydrology, 7(3): 64

Sutskever I, Vinyals O, Le Q V. 2014. Sequence to sequence learning with neural networks. In: Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal: MIT Press, 3104–3112

Yin Hanlin, Guo Zilong, Zhang Xiuwei, et al. 2021a. Runoff predictions in ungauged basins using sequence-to-sequence models. Journal of Hydrology, 603: 126975

Yin Hanlin, Zhang Xiuwei, Wang Fandu, et al. 2021b. Rainfall-runoff modeling using LSTM-based multi-state-vector sequence-to-sequence model. Journal of Hydrology, 598: 126378

Yuan Xiaohui, Chen Chen, Lei Xiaohui, et al. 2018. Monthly runoff forecasting based on LSTM–ALO model. Stochastic Environmental Research and Risk Assessment, 32(8): 2199–2212

Zhang E F, Savenije H H G, Chen S L, et al. 2012. An analytical solution for tidal propagation in the Yangtze Estuary, China. Hydrology and Earth System Sciences, 16(9): 3327–3339

Zhang Min, Townend I, Zhou Yunxuan, et al. 2016. Seasonal variation of river and tide energy in the Yangtze Estuary, China. Earth Surface Processes and Landforms, 41(1): 98–116

Zhao Jianhu, Chen Zhigao, Zhang Hongmei, et al. 2016. Multiprofile discharge estimation in the tidal reach of Yangtze Estuary. Journal of Hydraulic Engineering, 142(12): 04016056

Relative Articles

Relative Articles

Supplements(0)

Cited By

Cited by

Periodical cited type(1)

Aparna M. Deulkar, Pradnya R. Dixit, Shreenivas N. Londhe, et al. Comparative Assessment of Artificial Neural Networks (ANNs), Long Short Term Memory Network (LSTM) and Hydrologic Engineering Centre-Hydrologic Modelling System (HEC-HMS) for Runoff Modelling. Water Resources Management, 2025. doi:10.1007/s11269-024-04055-9