基于深度学习的河流径流值预测
Deep Learning Based River Runoff Value Prediction
DOI: 10.12677/AAM.2022.1111860, PDF,    科研立项经费支持
作者: 张竞予：成都信息工程大学，四川 成都
关键词: 径流值预测；LSTM；注意力机制；非线性特征；Runoff Value Prediction； LSTM； Attention Mechanisms； Nonlinear Features
摘要: 在传统预测径流值方法中，由于径流序列具有非常复杂的非线性特征，所以无法充分对径流值进行信息提取并进行预测。本文提出一种基于LSTM (长短期记忆网络)和注意力机制的模型来对径流值进行预测。对于气候原因引发的自然灾害——洪水的预测来说，该模型考虑到降雨量与上游水文站径流值对目标地区的径流值的影响，并通过加入注意力机制对各个影响因素添加距离影响。以四川省乐山市五通桥区径流值数据为例，通过对比2015年径流值的预测值和真实值进行对比。验证结果表明：添加了注意力机制的LSTM模型具有误差小，准确度高的特性，可以较为显著提高径流值预测的能力。
Abstract: In the traditional method of predicting runoff values, because the runoff sequence has very complex nonlinear characteristics, it is impossible to fully extract and predict the runoff values. In this paper, a model based on LSTM (Long Short-Term Memory Network) and attention mechanism is proposed to predict runoff values. The model takes into account the effects of rainfall and upstream hydrological station runoff values on the runoff values in the target area, and adds distance effects to each influencing factor by adding attention mechanisms. Taking the runoff value data of Wutongqiao District in Leshan City, Sichuan Province as an example, the predicted and true values of the runoff value in 2015 are compared. The verification results show that the LSTM model with the addition of attention mechanism has the characteristics of small error and high accuracy, which can significantly improve the ability to predict runoff values.
文章引用：张竞予. 基于深度学习的河流径流值预测[J]. 应用数学进展, 2022, 11(11): 8118-8127. https://doi.org/10.12677/AAM.2022.1111860

参考文献

[1] Abaya, S.W. (2008) Floods and Health in Gambella Region, Ethiopia: An Assessment of the Strength and Weakness of the Coping Mechanism. Lund University, Lund, 1-44.
[2] Cirella, G. and Iyalomhe, F. (2018) Flooding Conceptual Review: Sustainability-Focalized Best Practices in Nigeria. Applied Sciences, 8, Article No. 1558. [Google Scholar] [CrossRef] 
[3] Tamiru, H. and Dinka, M.O. (2021) Application of ANN and HEC-RAS Model for Flood Inundation Mapping in Lower Baro Akobo River Basin, Ethiopia. Journal of Hydrology: Regional Studies, 36, 100855. [Google Scholar] [CrossRef] 
[4] Graves, A. and Schmidhuber, J. (2005) Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures. Neural Networks, 18, 602-610. [Google Scholar] [CrossRef] [PubMed]
[5] Mengistu, D.T., Moges, S.A., Sorteberg, A., et al. (2016) Re-visiting Systems Type Black-Box Rainfall-Runoff Models for Flow Forecasting Application. Journal of Water Resource and Protection, 8, 65-83. [Google Scholar] [CrossRef] 
[6] Toth, E., Brath, A. and Montanari, A. (2000) Comparison of Short-Term Rainfall Prediction Models for Real-Time Flood Forecasting. Journal of Hydrology, 239, 132-147. [Google Scholar] [CrossRef] 
[7] 门宝辉, 常溶溶. 基于局部均值分解和最大熵谱估计的径流分析[J]. 水力发电学报, 2021, 40(9): 27-34.
[8] Tegegne, G., Park, D.K. and Kim, Y. (2017) Comparison of Hydrological Models for the Assessment of Water Resources in a Data-Scarce Region, the Upper Blue Nile River Basin. Journal of Hydrology: Regional Studies, 14, 49-66. [Google Scholar] [CrossRef] 
[9] Tamiru, H. and Wagari, M. (2022) Machine-Learning and HEC-RAS Integrated Models for Flood Inundation Mapping in Baro River Basin, Ethiopia. Modeling Earth Systems and Environment, 8, 2291-2303. https://link.springer.com/article/10.1007/s40808-021-01175-8 [Google Scholar] [CrossRef] 
[10] Chen, C., Hui, Q., Xie, W., Wan, S., Zhou, Y. and Pei, Q. (2021) Convolutional Neural Networks for Forecasting Flood Process in Internet-of-Things Enabled Smart City. Computer Networks, 186, Article ID: 107744 [Google Scholar] [CrossRef] 
[11] Grimes, D.I.F., Coppola, E., Verdecchia, M. and Visconti, G. (2003) A Neural Network Approach to Real-Time Rainfall Estimation for Africa Using Satellite Data. Journal of Hy-drometeorology, 4, 1119-1133. [Google Scholar] [CrossRef] 
[12] Dolling, O.R. and Varas, E.A. (2002) Artificial Neural Networks for Streamflow Prediction. Journal of Hydraulic Research, 40, 547-554. [Google Scholar] [CrossRef] 
[13] 石磊, 王毅, 成颖, 魏瑞斌. 自然语言处理中的注意力机制研究综述[J]. 数据分析与知识发现, 2020, 4(5): 1-14.
[14] Wang, Y., Huang, M., Zhu, X. and Zhao, L. (2016) At-tention-Based LSTM for Aspect-Level Sentiment Classification. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, 1-5 November 2016, 606-615. [Google Scholar] [CrossRef] 
[15] Bahremand, A. and De Smedt, F. (2008) Distributed Hydrological Modeling and Sensitivity Analysis in Torysa Watershed, Slovakia. Water Resources Management, 22, 393-408. [Google Scholar] [CrossRef] 
[16] Lv, Z., Zuo, J. and Rodriguez, D. (2020) Predicting of Runoff Using an Optimized SWAT-ANN: A Case Study. Journal of Hydrology: Regional Studies, 29, Article ID: 100688. [Google Scholar] [CrossRef] 

为你推荐