View in EDS

PM2.5 concentration prediction based on WD-SA-LSTM-BP model: a case study of Nanjing city.

Saved in:
Bibliographic Details
Title: PM2.5 concentration prediction based on WD-SA-LSTM-BP model: a case study of Nanjing city.
Authors: Hu, Shuo, Liu, Pengfei, Qiao, Yunxia, Wang, Qing, Zhang, Ying, Yang, Yuan
Source: Environmental Science & Pollution Research; Oct2022, Vol. 29 Issue 46, p70323-70339, 17p
Subject Terms: AIR quality monitoring stations, SIMULATED annealing, AIR quality, AIR pollutants
Geographic Terms: NANJING (Jiangsu Sheng, China)
Abstract: PM2.5 concentration is an important indicator to measure the concentration of air pollutants, and it is of important social significance and application value to realize accurate prediction of PM2.5 concentration. To further improve the accuracy of PM2.5 concentration prediction, this paper proposes a hybrid machine learning model (WD-SA-LSTM-BP model) based on simulated annealing (SA) optimization and wavelet decomposition. Firstly, the wavelet decomposition algorithm was used to realize the multiscale decomposition and single-branch reconstruction of PM2.5 concentrations to weaken the prediction error caused by time series data. Secondly, the SA optimization method was used to optimize the super-parameters of each machine learning model under each reconstructed component, so as to solve the problem that it is difficult to determine the parameters of machine learning model. Thirdly, the optimized machine learning model was used to predict the PM2.5 concentration, and the error value was calculated from the actual measured value. Then, the optimized machine learning model was used to predict the error value. Finally, the predicted error value was added to the predicted PM2.5 concentration to obtain the final predicted PM2.5 concentration. The study is experimentally validated based on daily PM2.5 data collected from Nanjing air quality monitoring stations. The experimental results showed that the RMSE and MAE values of the constructed WD-SA-LSTM-BP model were 5.26 and 3.72, respectively, which were superior to those of the WD-LSTM and LSTM models, indicating that the hybrid machine learning model based on SA optimization and wavelet decomposition could better predict the PM2.5 concentration. [ABSTRACT FROM AUTHOR]
Copyright of Environmental Science & Pollution Research is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:PM<subscript>2.5</subscript> concentration is an important indicator to measure the concentration of air pollutants, and it is of important social significance and application value to realize accurate prediction of PM<subscript>2.5</subscript> concentration. To further improve the accuracy of PM<subscript>2.5</subscript> concentration prediction, this paper proposes a hybrid machine learning model (WD-SA-LSTM-BP model) based on simulated annealing (SA) optimization and wavelet decomposition. Firstly, the wavelet decomposition algorithm was used to realize the multiscale decomposition and single-branch reconstruction of PM<subscript>2.5</subscript> concentrations to weaken the prediction error caused by time series data. Secondly, the SA optimization method was used to optimize the super-parameters of each machine learning model under each reconstructed component, so as to solve the problem that it is difficult to determine the parameters of machine learning model. Thirdly, the optimized machine learning model was used to predict the PM<subscript>2.5</subscript> concentration, and the error value was calculated from the actual measured value. Then, the optimized machine learning model was used to predict the error value. Finally, the predicted error value was added to the predicted PM<subscript>2.5</subscript> concentration to obtain the final predicted PM<subscript>2.5</subscript> concentration. The study is experimentally validated based on daily PM<subscript>2.5</subscript> data collected from Nanjing air quality monitoring stations. The experimental results showed that the RMSE and MAE values of the constructed WD-SA-LSTM-BP model were 5.26 and 3.72, respectively, which were superior to those of the WD-LSTM and LSTM models, indicating that the hybrid machine learning model based on SA optimization and wavelet decomposition could better predict the PM<subscript>2.5</subscript> concentration. [ABSTRACT FROM AUTHOR]
ISSN:09441344
DOI:10.1007/s11356-022-20744-7