TY - JOUR
T1 - Large-scale water quality prediction with integrated deep neural network
AU - Bi, Jing
AU - Lin, Yongze
AU - Dong, Quanxi
AU - Yuan, Haitao
AU - Zhou, Meng Chu
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China (NSFC) under Grants 61802015 and 62073005, and in part by the Major Science and Technology Program for Water Pollution Control and Treatment of China under Grant 2018ZX07111005.
Publisher Copyright:
© 2021 Elsevier Inc.
PY - 2021/9
Y1 - 2021/9
N2 - Water environment time series prediction is important to efficient water resource management. Traditional water quality prediction is mainly based on linear models. However, owing to complex conditions of the water environment, there is a lot of noise in the water quality time series, which will seriously affect the accuracy of water quality prediction. In addition, linear models are difficult to deal with the nonlinear relations of data of time series. To address this challenge, this work proposes a hybrid model based on a long short-term memory-based encoder-decoder neural network and a Savitzky-Golay filter. Among them, the filter of Savitzky-Golay can eliminate the potential noise in the time series of water quality, and the long short-term memory can investigate nonlinear characteristics in a complicated water environment. In this way, an integrated model is proposed and effectively obtains statistical characteristics. Realistic data-based experiments prove that its prediction performance is better than its several state-of-the-art peers.
AB - Water environment time series prediction is important to efficient water resource management. Traditional water quality prediction is mainly based on linear models. However, owing to complex conditions of the water environment, there is a lot of noise in the water quality time series, which will seriously affect the accuracy of water quality prediction. In addition, linear models are difficult to deal with the nonlinear relations of data of time series. To address this challenge, this work proposes a hybrid model based on a long short-term memory-based encoder-decoder neural network and a Savitzky-Golay filter. Among them, the filter of Savitzky-Golay can eliminate the potential noise in the time series of water quality, and the long short-term memory can investigate nonlinear characteristics in a complicated water environment. In this way, an integrated model is proposed and effectively obtains statistical characteristics. Realistic data-based experiments prove that its prediction performance is better than its several state-of-the-art peers.
KW - Deep neural network
KW - Encoder-decoder network
KW - Prediction algorithms
KW - Savitzky-Golay filter
KW - Water quality management
UR - http://www.scopus.com/inward/record.url?scp=85110515104&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85110515104&partnerID=8YFLogxK
U2 - 10.1016/j.ins.2021.04.057
DO - 10.1016/j.ins.2021.04.057
M3 - Article
AN - SCOPUS:85110515104
SN - 0020-0255
VL - 571
SP - 191
EP - 205
JO - Information sciences
JF - Information sciences
ER -