Abstract
Due to rapid development, the occurrence of flood has become more and more frequent. However, due to the complex nature and limited knowledge, the conventional hydrological model for flood forecasting purposes faces drawbacks in terms of technical difficulties. Hence, it is essential to have a model which can provide a considerably high level of accuracy for flood forecasting. This study selected the area between the Xiangtan station and Changsha station, located in Xiangjiang River as the study area. Recurrent neural network (RNN), gated recurrent unit (GRU) and long short-term memory (LSTM) were applied for model development purposes. The models were used to forecast the flood disasters occurring in 2017, 2019, 2020 and 2022 for 1h, 6h and 12h in advance. A series of statistical analyses have been conducted to evaluate the model performance. The LSTM model outperformed than the RNN and GRU models. In terms of the overall analysis, the LSTM model achieved relatively good accuracy with a NSE of above 0.98, and RMSE of lower than 0.2 m. In addition, the model with a 6h in advance is the most suitable model to predict the peak flood arrival time with an absolute error of less than 3 hours.
Similar content being viewed by others
References
Cheng HY (2020) Flood forecasting system and its role in project scheduling. China Water Resources 17:11–13, DOI: https://doi.org/10.3969/j.issn.1000-1123.2020.17.014
Chin RJ, Lai SH, Shaliza I, Wan Zurina WJ, Ahmed Elshafie AH (2019) New approach to mimic rheological actual shear rate under wall slip condition. Engineering with Computers 35(4):1409–1418, DOI: https://doi.org/10.1007/s00366-018-0670-y
Chin RJ, Lai SH, Shaliza I, Wan Zurina WJ, Elshafie A (2020) ANFIS-based model for predicting actual shear rate associated with wall slip phenomenon. Soft Computing 24:9639–9649, DOI: https://doi.org/10.1007/s00500-019-04475-5
Cho M, Kim C, Jung K, Jung H (2022) Water level prediction model applying a short-term memory (LSTM)- gated recurrent unit (GRU) method for flood prediction. Water 14(14):2221–2241, DOI: https://doi.org/10.3390/w14142221
Deng B, Lai SH, Jiang C, Kumar P, El-Shafie A, Chin RJ (2021) Advanced water level prediction for a large-scale river-lake system using hybrid soft computing approach: A case study in Dongting Lake, China. Earth Science Informatics 14:1987–2001, DOI: https://doi.org/10.1007/s12145-021-00665-8
Dong YP, Yuan JX (2008) Review and prospect of watershed hydrological model. Hydroelectric Power 3:20–23, DOI: https://doi.org/10.3969/j.issn.0559-9342.2008.03.006
Ebert EE, Janowiak JE, Kidd C (2007) Comparison of near-real-time precipitation estimates from satellite observations and numerical models. Bulletin of the American Meteorological Society 88(1):47–64, DOI: https://doi.org/10.1175/BAMS-88-1-47
Elman JL (1990) Finding structure in time. Cognitive Science 14(2):179–211, DOI: https://doi.org/10.1207/s15516709cog1402_1
Feng J, Pan F (2018) A LSTM-BP multi-model combined hydrological forecasting method. Computer and Modernization 7:82–85, DOI: https://doi.org/10.3969/j.issn.1006-2475.2018.07.017
Guo Y, Lai XJ (2020) Water level prediction of Poyang Lake based on long short-term memory neural network. Journal of Lake Sciences 32(3):865–876, DOI: https://doi.org/10.18307/2020.0325
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Computation 9(8):1735–1780, DOI: https://doi.org/10.1162/neco.1997.9.8.1735
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Networks 2:359–366, DOI: https://doi.org/10.1016/0893-6080(89)90020-8
Hrnjica B, Bonacci O (2019) Lake level prediction using feed forward and recurrent neural networks. Water Resources Management 33:2471–2484, DOI: https://doi.org/10.1007/s11269-019-02255-2
Kim D, Lee J, Kim J, Lee M, Wang W, Kim HS (2022) Comparative analysis of long short-term memory and storage function model for flood water level forecasting of Bokha stream in NamHan River, Korea. Journal of Hydrology 606:127415, DOI: https://doi.org/10.1016/j.jhydrol.2021.127415
Kong W, Dong ZY, Jia Y, Hill DJ, Xu Y, Zhang Y (2017) Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Transactions on Smart Grid 10(1):841–851, DOI: https://doi.org/10.1109/TSG.2017.2753802
Kratzert F, Klotz D, Brenner C, Schulz K, Herrnegger M (2018) Rainfall-runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrology and Earth System Sciences 22:6005–6022, DOI: https://doi.org/10.5194/hess-22-6005-2018
Loh WS, Chin RJ, Ling L, Lai SH, Soo EZS (2021) Application of machine learning model for the prediction of settling velocity of fine sediments. Mathematics 9(23):3141, DOI: https://doi.org/10.3390/math9233141
Nguyen DH, Bae D-H (2020) Correcting mean areal precipitation forecasts to improve urban flooding predictions by using long short-term memory network. Journal of Hydrology 584:124710, DOI: https://doi.org/10.1016/j.jhydrol.2020.124710
Sahoo BB, Jha R, Singh A, Kumar D (2019a) Application of support vector regression for modeling low flow time series. KSCE Journal of Civil Engineering 23(2):923–934, DOI: https://doi.org/10.1007/s12205-018-0128-1
Sahoo BB, Jha R, Singh A, Kumar D (2019b) Long short-term memory (LSTM) recurrent neural network for low-flow hydrological time series forecasting. Acta Geophysica 67:1471–1481, DOI: https://doi.org/10.1007/s11600-019-00330-1
Sankalp S, Sahoo BB, Sahoo SN (2023) Uncertainty and sensitivity analysis of deep learning models for diurnal temperature range (DTR) forecasting over five Indian cities. Environmental Monitoring and Assessment 195:291, DOI: https://doi.org/10.1007/s10661-022-10844-9
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 15(1):1929–1958, DOI: https://doi.org/10.5555/2627435.2670313
Xu Y, Wu Q, Li C, Chen Y, Zhang L, Ran G, Hu C (2020) Simulation of the flood process in the middle reaches of the Yellow River by a long-short term memory (LSTM) neuro network. Journal of Beijing Normal University (Natural Science) 56(3):387–393, DOI: https://doi.org/10.12202/j.0476-0301.2020156
Zhang D, Lin J, Peng Q, Wang D, Yang T, Sorooshian S, Liu X, Zhuang J (2018) Modeling and simulating of reservoir operation using the artificial neural network, support vector regression, deep learning algorithm. Journal of Hydrology 565:720–736, DOI: https://doi.org/10.1016/j.jhydrol.2018.08.050
Zhao R, Yan R, Chen Z, Mao K, Wang P, Gao RX (2019) Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing 115:213–237, DOI: https://doi.org/10.1016/j.ymssp.2018.05.050
Zhong ZY, Wang XY (1999) Flood evolution method in the middle and lower reaches of the Yangtze River. Journal of Water Resources and Hydropower Letters 19:32–34, DOI: https://doi.org/10.15974/j.cnki.slsdkb.1999.19.009
Zhou X (2017) A kind of variable coefficient regression model and its application in hydrological forecast. MSc Thesis. Changsha University of Science and Technology, Changsha, China
Acknowledgments
The authors would like to express the highest gratitude for financial support from Changsha Municipal Natural Science Foundation (# kq2014103), and partial support from National Natural Science Foundation of China (#52109006), National Science Foundation of Hunan Province, China (#2021JJ40589) and Universiti Tunku Abdul Rahman Research Fund (IPSR/RMC/UTARRF/2022-C2/C04). The authors would like to thank Department of Water Resources of Hunan Province for sharing the hydrological data (http://yzt.hnswkcj.com:9090/#/).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liu, Y., Yang, Y., Chin, R.J. et al. Long Short-Term Memory (LSTM) Based Model for Flood Forecasting in Xiangjiang River. KSCE J Civ Eng 27, 5030–5040 (2023). https://doi.org/10.1007/s12205-023-2469-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12205-023-2469-7