首页 | 本学科首页   官方微博 | 高级检索  
     


Study on Water Quality Prediction of Urban Reservoir by Coupled CEEMDAN Decomposition and LSTM Neural Network Model
Authors:Zhang  Lei  Jiang  Zhiqiang  He  Shanshan  Duan  Jiefeng  Wang  Pengfei  Zhou  Ting
Affiliation:1.School of Civil and Water Resources Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China
;2.School of Engineering, Anhui Agricultural University, Hefei, 230036, China
;
Abstract:

Urban reservoir is one of the important urban drinking water sources, and it is of important significance to ensuring the safety of urban water supply. The water quality of the reservoir is an important factor affecting the safety of water supply. Timely and accurate water quality prediction is very important for the formulation of a scientific and reasonable reservoir water supply plan. Considering the problem of high requirement of basic data in constructing water quality hydrodynamic physical model, this paper established a new data-driven model of water quality prediction in urban reservoir based on the Long and Short-Term Memory (LSTM) model, and the water quality data’s decomposition is implemented through the Complete Ensemble Empirical Modal Decomposition with Adaptive Noise (CEEMDAN) method. This model can not only realize the water quality prediction during different foreseen periods, but also solve the problem of low prediction accuracy caused by the randomness and large volatility of the measured data. Taking Xili Reservoir in Shenzhen of China as an example, the prediction of water concentration including total nitrogen, ammonia nitrogen, total phosphorus and PH value of Xili reservoir was realized based on historical monitoring data. Through simulation calculation, the prediction results of total nitrogen, ammonia nitrogen, total phosphorus and PH value in the water quality prediction model are highly consistent with the measured results, it is found that the simulation effect is good, and this model can well simulate the reservoir’s water quality concentration change process. For the total nitrogen and ammonia nitrogen, the relative prediction error of the model can be controlled below 10%, which shows the rationality of the built model. The research of this paper can provide an important theoretical and technical support for the water quality prediction and operation plan formulation of Xili Reservoir.

Keywords:
本文献已被 SpringerLink 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号