PDF下载

[1]崔忠捷,卿晓霞,杨森雄.基于DM-LSTM的城市降雨径流预测研究[J].中国给水排水,2022,38(19):132-138.
　CUIZhong-jie,QINGXiao-xia,YANGSen-xiong.Prediction of Urban Rainfall Runoff Based on DM-LSTM[J].China Water & Wastewater,2022,38(19):132-138.

点击复制

基于DM-LSTM的城市降雨径流预测研究

中国给水排水[ISSN:1000-4062/CN:12-1073/TU] 卷: 第38卷期数: 2022年第19期页码: 132-138 栏目: 出版日期: 2022-10-01

Title:: Prediction of Urban Rainfall Runoff Based on DM-LSTM

作者:: 崔忠捷¹，卿晓霞²，杨森雄³; （1.重庆大学环境与生态学院，重庆 400045；2.重庆大学土木工程学院，重庆 400045；3.中国电建贵阳勘测设计研究院有限公司，贵州贵阳 550000）

Author(s):: CUI　Zhong-jie¹， QING　Xiao-xia²， YANG　Sen-xiong³; （1. College of Environment and Ecology， Chongqing University， Chongqing 400045， China； 2. School of Civil Engineering， Chongqing University， Chongqing 400045， China； 3. PowerChina Guiyang Engineeering Corporation Limited， Guiyang 550000， China）

关键词:: 城市降雨径流预测; 数据驱动模型; 长短期记忆（LSTM）模型; 数据挖掘; 深度学习; 智慧水务

Keywords:: urban rainfall runoff prediction; data-driven model; LSTM model; data mining（DM）; deep learning; smart water

摘要:: 智慧水务背景下，如何基于人工智能理论与技术深化城市降雨径流模型研究，是一项值得探索的课题。由于城市降雨径流时间分辨率高且样本特征分布不具有规律性，直接采用长短期记忆（LSTM）模型进行预测面临着挑战。基于此，提出用数据挖掘（DM）算法及规则对城市降雨径流时序数据集进行聚类和重构，并基于深度学习算法对LSTM模型的结构和参数进行优化，构建了DM-LSTM耦合模型，并用于研究区域的降雨径流模拟。结果表明，对于各类降雨事件，与LSTM模型相比，DM-LSTM耦合模型的均方根误差（RMSE）降低了2.1%~41.9%，纳什效率系数（NSE）提高了0.4%~56.4%，决定系数（R²）提高了0.3%~65.6%。DM-LSTM耦合模型不仅对各类降雨事件均表现出更好的预测性，而且模型运行时间仅为2.044 s，能够很好地满足城市降雨径流预测对实时性、准确性和稳定性的需求。

Abstract:: Under the background of smart water, how to deepen the research on urban rainfall runoff model based on artificial intelligence theory and technology is a topic worthy of exploration. Due to the high temporal resolution of urban rainfall runoff and irregular distribution of sample features, it is challenging to directly use long short term memory (LSTM) model for prediction. Based on this backround, data mining (DM) algorithm and rules were proposed to cluster and reconstruct the urban rainfall runoff time series data sets, the structure and parameters of LSTM model were optimized based on deep learning algorithm, and a DM-LSTM coupling model was constructed and applied to simulate rainfall runoff in the study area. For all kinds of rainfall events, compared with the LSTM model, the root mean square error (RMSE) of the DM-LSTM coupling model was decreased by 2.1%-41.9%, the Nash-Sutcliffe effciency (NSE) coefficient was increased by 0.4%-56.4%, and the coefficient of determination (R²) was increased by 0.3%-65.6%. The DM-LSTM coupling model showed a better prediction performance for all kinds of rainfall events, and decreased the running time of the model to only 2.044 s, which could well meet the needs of real-time, accuracy and stability for urban rainfall runoff prediction.

更新日期/Last Update: 2022-10-01