考虑气象因素和BP神经网络的中长期径流预报
Medium and Long Term Runoff Forecast Considering Meteorological Factors and BP Neural Network
DOI: 10.12677/JWRR.2021.104042, PDF,    科研立项经费支持
作者: 王 伟, 金新峰, 刘 洋, 余 豪, 胡朋瑞：中国电建集团中南勘测设计研究院有限公司，湖南 长沙；尹华政：水电水利规划设计总院，北京
关键词: 径流预报；中长期；BP神经网络；Runoff Forecast； Medium and Long Term； BP Neural Network
摘要: 中长期径流预报结果对中长期发电计划制定至关重要，为了提高中长期径流预报精度，提出了考虑气象因素与BP神经网络相结合的预报方法。首先根据偏互信息法获得影响中长期入库流量变化的关键因子，并根据模糊聚类方式对其影响径流的相关因子进行聚类分析，最后采用BP神经网络以聚类的因子为输入对中长期日平均径流进行预测。以湖南省凤滩水库为例，预测结果表明：1) BP神经网络预测模型预报效果优于支持向量基、时间序列预测模型的预报结果；2) 考虑气象因素的径流预报优于未采用气象相似相的径流预报；3) 采用气象相似性与BP神经网络相结合的径流预报效果较好，预报精度均在丙级以上。
Abstract: The results of medium and long-term runoff forecast are very important for medium and long-term power generation planning. In order to improve the accuracy of medium and long-term runoff forecast, a forecast method combining meteorological factors with BP neural network is proposed. Firstly, the key factors affecting the medium and long-term inflow are obtained by partial mutual information method, and the related factors affecting runoff are analyzed by fuzzy clustering method. Finally, the BP neural network is used to predict the medium and long-term daily average runoff with the clustering factors as input. Taking Fengtan reservoir in Hunan Province as an example, the prediction results show that: 1) The prediction effect of BP neural network prediction model is better than that of support vector basis and time series prediction model; 2) The runoff prediction considering meteorological factors is better than that without meteorological similarity; 3) The runoff prediction effect of combining meteorological similarity and BP neural network is better, and the prediction accuracy is in the third above grade.
文章引用：王伟, 金新峰, 尹华政, 刘洋, 余豪, 胡朋瑞. 考虑气象因素和BP神经网络的中长期径流预报[J]. 水资源研究, 2021, 10(4): 391-398. https://doi.org/10.12677/JWRR.2021.104042

参考文献

[1] 李伶杰, 王银堂, 胡庆芳, 等. 基于随机森林与支持向量机的水库长期径流预报[J]. 水利水运工程学报, 2020(4): 33-40. LI Lingjie, WANG Yintang, HU Qingfang, et al. Long term runoff forecast of reservoir based on random forest and support vector machine. Journal of Water Conservancy and Water Transport Engineering, 2020(4): 33-40. (in Chinese)
[2] 晋健, 刘育, 王琴慧, 等. 基于小波去噪和FA-SVM的中长期径流预报[J]. 人民长江, 2020, 51(9): 67-72. JIN Jian, LIU Yu, WANG Qinhui, et al. Medium and long term runoff forecasting based on wavelet denoising and FA-SVM. Renmin Changjiang River, 2020, 51(9): 67-72. (in Chinese)
[3] CARLSON, R. F., MACCORMICK, A. J. A. and WATTS, D. G. Application of linear random models to four annual streamflow series. Water Resources Research, 1970, 6(4): 1070-1078.
https://doi.org /10.1029/WR006i004p01070
[4] 谢帅, 黄跃飞, 李铁键, 刘朝云, 王建华. LASSO回归和支持向量回归耦合的中长期径流预报[J]. 应用基础与工程科学学报, 2018, 26(4): 709-722. XIE Shuai, HUANG Yuefei, LI Tiejian, LIU Chaoyun and WANG Jianhua. Medium and long term runoff forecasting based on the coupling of LASSO regression and support vector regression. Journal of Applied Basic and Engineering Sciences, 2018, 26(4): 709-722. (in Chinese)
[5] KALTEH, A. M. Monthly river flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform. Computers & Geosciences, 2013, 54(4): 1-8.
https://doi.org /10.1016/j.cageo.2012.11.015
[6] CHU, H., WEI, J., LI, T., et al. Application of support vector regression for mid- and long-term runoff forecasting in “Yellow River Headwater” region. Procedia Engineering, 2016(54): 1251-1257.
https://doi.org /10.1016/j.proeng.2016.07.452
[7] 杨强. 耦合CFS集合预报和深度学习的中长期径流预测方法研究[D]: [硕士学位论文]. 大连: 大连理工大学, 2019. YANG Qiang. Research on medium and long term runoff forecasting method coupled with CFS ensemble forecasting and deep learning. Dalian: Dalian University of Technology, 2019. (in Chinese)
[8] HE, J., VALEO, C., CHU, A., et al. Prediction of event-based stormwater runoff quantity and quality by ANNs developed using PMI-based input selection. Journal of Hydrology, 2011, 400(1-2): 10-23.
https://doi.org /10.1016/j.jhydrol.2011.01.024
[9] MAY, R. J., DANDY, G. C., MAIER, H. R., et al. Application of partial mutual information variable selection to ANN forecasting of water quality in water distribution systems. Environmental Modelling & Software, 2008, 23(10-11): 1289-1299.
https://doi.org /10.1016/j.envsoft.2008.03.008
[10] 刘本希, 廖胜利, 冯仲恺, 等. 耦合偏互信息的贫资料地区小水电发电能力预测[J]. 电力系统自动化, 2015, 39(19): 149-154. LIU Benxi, LIAO Shengli, FENG Zhongkai, et al. Prediction of small hydropower generation capacity in poor data area based on coupling partial mutual information. Power System Automation, 2015, 39(19): 149-154. (in Chinese)
[11] SCOTT, D. W. Multivariate density estimation: Theory, practice, and visualization. Indian Apolis: Wiley, 2008.
[12] MAY, R. J., MAIER, H. R., DANDY, G. C., et al. Non-linear variable selection for artificial neural networks using partial mutual information. Environmental Modelling & Software, 2008, 23(10-11): 1312-1326.
https://doi.org /10.1016/j.envsoft.2008.03.007
[13] 周雨婷, 张善亮, 邬雪松, 等. 基于改进BP神经网络的非平稳水文时间序列长期预报研究[C]//河海大学. 2020年(第八届)中国水利信息化技术论坛论文集: 2020年卷. 北京: 北京沃特咨询有限公司, 2020: 8. ZHOU Yuting, ZHANG Shanliang, WU Xuesong, et al. Study on long-term forecasting of non-stationary hydrological time series based on improved BP neural network//Hehai University. Proceedings of the 8th China Water Conservancy Information Technology Forum: 2020. Beijing: Beijing Water Resources Consulting Co., Ltd., 2020: 8. (in Chinese)
[14] 朱静思, 侯天宇, 张治倩. 海河流域逐月降水预测研究[C]//中国气象学会. 第35届中国气象学会年会S10水文气象灾害形成机理、预报预测预警与风险评估新技术: 2018年卷. 中国气象学会, 2018: 14. ZHU Jingsi, HOU Tianyu and ZHANG Zhiqian. Research on monthly precipitation prediction in Haihe River Basin//China Meteorological Society. The 35th Annual Meeting of China Meteorological Society. S10 New Technologies of Hydrometeorological Disaster Formation Mechanism, Prediction, Early Warning and Risk Assessment: 2018. China Meteorological Society, 2018: 14. (in Chinese)