摘要
准确的径流预测是水资源开发利用的重要依据,但预测难度大。为提高日径流预测精度,以榕江流域南河东桥园站日径流为例,建立了经验模态分解(EMD)和支持向量机(SVM)耦合的日径流预测模型。首先,利用经验模态分解将日径流系列分解为若干子过程,再采用支持向量机深度学习模型分别对每一个子过程进行预测,最后将每个预测结果相加得到原日径流数据的预测结果。研究表明:EMD-SVM组合模型相对于SVM、BP、LSTM单模型具有更好的预测性能。
Accurate runoff prediction is an important basis for water resources development and utilization,but the prediction is difficult.In order to improve the accuracy of daily runoff prediction,a coupled daily runoff prediction model coupled with empirical mode decomposition(EMD)and support vector machine(SVM)is established.Taking the daily runoff of Nanhe Dongqiaoyuan Station in Rongjiang River basin as an example,the daily runoff series is firstly decomposed into several sub-processes by using EMD,then each sub-process is separately predicted by SVM deep learning model,and finally,each prediction result is summed to obtain the prediction result of original daily runoff data.The results show that the EMD-SVM combined model has better prediction performance than the single models of SVM,BP and LSTM.
作者
万新宇
王鑫宇
侯添甜
林晓梦
WAN Xinyu;WANG Xinyu;HOU Tiantian;LIN Xiaomeng(College of Hydrology and Water Resources,Hohai University,Nanjing 210024,Jiangsu,China)
出处
《水力发电》
CAS
2023年第10期39-44,共6页
Water Power
基金
国家自然科学基金资助项目(52079037)。
关键词
日径流预测
经验模态分解
支持向量机
组合模型
预测精度
榕江流域
daily runoff prediction
empirical mode decomposition(EMD)
support vector machine(SVM)
combined model
prediction accuracy
Rongjiang River basin
