Application of artificial intelligence based on synchrosqueezed wavelet transform and improved deep extreme learning machine in water quality prediction

作     者：Song, Chenguang Yao, Leihua 

作者机构：China Univ Geosci Beijing Sch Engn & Technol Beijing 100083 Peoples R China 

出 版 物：《ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH》 (环境科学与污染研究)

年 卷 期：2022年第29卷第25期

页      面：38066-38082页

核心收录：

学科分类：0830[工学-环境科学与工程（可授工学、理学、农学学位）] 08[工学] 

基　　金：We sincerely thank the anonymous reviewers for their time and effort devoted to improving the manuscript 

主　　题：SSA SWT Integrated model Data-driven model Optimization algorithm 

摘      要：Water quality prediction is the basis for the prevention and control of water pollution. In this paper, to address the problem of low prediction accuracy of existing empirical models due to the non-smoothness and nonlinearity of water quality series, a novel water quality forecasting model integrating synchrosqueezed wavelet transform and deep extreme learning machine optimized with the sparrow search algorithm (SWT-SSA-DELM) was proposed. First, the water quality series was denoised by SWT to reduce the non-stationarity and randomness of water quality series. Then, construct DELM by combining ELM and an autoencoder, and an innovative metaheuristic algorithm, SSA, was used to optimize the hyperparameters of the DELM. Finally, the constructed feature vector was used as the input of the DELM, and the proposed water quality prediction model SWT-SSA-DELM was trained and tested with the data sets of Xinchengqiao and Xiaolangdi in the Yellow River Basin, China. Models such as ELM and DELM alone, as well as their improved form based on ensemble learning, long short-term memory network (LSTM), autoregressive integrated moving average (ARIMA) were adopted as comparison models. The results make it evident that the model presented, linking the ability to ensure convergence to the global optima of the SSA with the nonlinear mapping of the DELM, outperforms similar models in terms of predictive performance, with average MAE, MAPE, and RMSE of 0.15, 2.02%, and 0.21 in the test stage, which is 72.82%, 72.88%, and 74.32% lower than the baseline ELM model, respectively.