基于LSTM网络的实时入库洪水预报方法
Real-Time Reservoir Flood Forecasting Method Based on LSTM Network
DOI: 10.12677/JWRR.2021.103034, PDF,  被引量   
作者: 陈宗让, 殷延军：国网陕西省电力公司安康水力发电厂，陕西 安康；万 飚*, 万 俊：武汉大学水利水电学院，湖北 武汉；于耀翔：武汉大学网络安全学院，湖北 武汉
关键词: 入库洪水；实时预报；LSTM网络；深度学习；Reservoir Flood； Real-Time Forecasting； LSTM Network； Deep Learning
摘要: 随着流域水文气象资料观测手段的进步和数据的不断积累，采用数据驱动的方式来研究水库流域入库径流问题，已成为一种可行的思路。本文建立了一种基于LSTM (Long Short-term Memory)网络深度学习算法的入库洪水预报模型，该模型以水库前期入库流量序列、流域前期降雨序列和上游站前期出库流量序列等多个维度作为模型输入，水库预报入库流量作为输出，进行实时洪水预报。安康水库洪水预报的实例验证表明，LSTM网络模型可以很好地模拟入库洪水过程，并在实时洪水预报中也有较好的表现。本研究可为水库防洪及兴利调度提供技术支撑。
Abstract: With the progress of hydrological and meteorological data observation and the accumulation of data, it has become a feasible way to study the reservoir inflow forecasting by data driven method. This paper established a flood forecasting model based on LSTM (long short term memory) network and depth learning algorithm. The model takes the reservoir early stage inflow, rainfall and upstream sequence as the inputs, and the reservoir inflow as output. The application of Ankang reservoir shows that LSTM network model can simulate the flood hydrograph very well, and has good performance in real-time flood forecasting. This study can provide technique support for reservoir flood control and beneficial operation.
文章引用：陈宗让, 殷延军, 万飚, 万俊, 于耀翔. 基于LSTM网络的实时入库洪水预报方法[J]. 水资源研究, 2021, 10(3): 312-321. https://doi.org/10.12677/JWRR.2021.103034

参考文献

[1] 芮孝芳. 水文学原理[M]. 北京: 高等教育出版社, 2013. RUI Xiaofang. Principles of Hydrology. Beijing: Higher Education Press, 2013. (in Chinese)
[2] 包为民. 水文预报(第4版) [M]. 北京: 中国水利水电出版社, 2009. BAO Weimin. Hydrologic forecast (4th Edition). Beijing: China Water & Power Press, 2009. (in Chinese)
[3] 殷兆凯, 廖卫红, 王若佳, 雷晓辉. 基于长短时记忆神经网络(LSTM)的降雨径流模拟及预报[J]. 南水北调与水利科技, 2019, 17(6): 1-9, 27. YIN Zhaokai, LIAO Weihong, WANG Ruojia and LEI Xiaohui. Rainfall-runoff modelling and forecasting based on long short-term memory (LSTM). South-to-North Water Transfers and Water Science & Technology, 2019, 17(6): 1-9, 27. (in Chinese)
[4] 庞博, 郭生练, 等. 丹江口库周区人工神经网络洪水预报模型研究[J]. 人民长江, 2004, 35(4): 30-31. PANG Bo, GUO Shenglian, et al. Study on artificial neural network flood forecasting model for Danjiangkou reservoir area. Yangtze River, 2004, 35(4): 30-31. (in Chinese)
[5] 庞博, 郭生练, 等. 改进的人工神经网络水文预报模型及应用[J]. 武汉大学学报(工学版), 2007, 40(1): 33-36. PANG Bo, GUO Shenglian, et al. A modified artificial neural network model and its application to flood forecasting. Engi-neering Journal of Wuhan University, 2007, 40(1): 33-36. (in Chinese)
[6] HU, C. H., WU, Q., LI, H., JIAN, S. Q., LI, N. and LOU, Z. Z. Deep learning with a long short-term memory networks approach for rainfall-runoff simulation. Water, 2018, 10(11): 1543. [Google Scholar] [CrossRef] 
[7] LE, X.-H., HO, H. V., LEE, G. and JUNG, S. Application of long short-term memory (LSTM) neural network for flood forecasting. Water, 2019, 11(7): 1387. [Google Scholar] [CrossRef] 
[8] XIANG, Z., YAN, J. and DEMIR, I. A rainfall-runoff model with LSTM-based sequence-to-sequence learning. Water Resources Research, 2020(56): e2019WR025326. [Google Scholar] [CrossRef] 
[9] FANG, Z. C., WANG, Y., PENG, L. and HONG, H. Y. Predicting flood susceptibility using LSTM neural networks. Journal of Hydrology, 2021(594): 125734. [Google Scholar] [CrossRef] 
[10] 胡庆芳, 曹士圯, 杨辉斌, 等. 汉江流域安康站日径流预测的LSTM模型初步研究[J]. 地理科学进展, 2020, 39(4): 636-642. HU Qingfang, CAO Shiyi, YANG Huibin, et al. Daily runoff predication using LSTM at the Ankang Station, Hanjing River. Progress in Geography, 2020, 39(4): 636-642. (in Chinese)
[11] 徐源浩, 邬强, 李常青, 等. 基于长短时记忆神经网络LSTM的降雨径流模拟及预报[J]. 北京师范大学学报(自然科学版), 2020, 56(3): 387-393. XU Yuanhao, WU Qiang, LI Changqing, et al. 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), 2020, 56(3): 387-393. (in Chinese)
[12] 何伟, 万俊, 左园忠, 等. 基于LSTM模型模拟安康水库洪水过程[J]. 水资源研究, 2020, 9(2): 202-210. HE Wei, WAN Jun, ZUO Yuanzhong, et al. Simulation of Ankang Reservoir inflow based on LSTM model. Journal of Water Resources Research, 2020, 9(2): 202-210. (in Chinese)
[13] 中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. 水文情报预报规范(GB/T 22482-2008) [S]. 北京: 中国标准出版社, 2008. General Administration of Quality Supervision, Inspection and Quarantine of the People’s Republic of China, Standardization Administration of the People’s Republic of China. Standard for hydrological information and hydrological forecasting (GB/T 22482-2008). Beijing: Standards Press of China, 2008. (in Chinese)