A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Long Short-Term Memory Network and Ordinary Kriging Method for Prediction of PM2.5 Concentration
https://orcid.org/http://orcid.org/0000-0002-8343-7536
https://orcid.org/http://orcid.org/0000-0002-3163-9718
https://orcid.org/http://orcid.org/0000-0003-3741-797X
When building a smart city, one must pay attention to the complex and diverse environmental problems in the city. Air quality prediction is an indispensable part of smart cities as it is conducive to guiding the development of air pollution prevention and control and alleviating urban air pollution. Based on the PM2.5 concentration data of 10 state-controlled air quality monitoring sites in Changsha City, Hunan Province, China from January 1, 2017 to December 30, 2021 and the meteorological data of Changsha city, a long short- term memory recurrent neural network model applicable to PM2.5 concentration prediction of Changsha city is formulated according to actual conditions with reference to related machine learning methods, and is used to predict the daily average concentration of PM2.5 at 10 air quality monitoring sites. Using the predicted PM2.5 concentration at the air quality monitoring sites in Changsha city, the spatial distribution simulation map of PM2.5 mass concentration within Changsha Third Ring Road is made by ordinary kriging method. Suggestions for PM2.5 pollution protection measures are put forward based on the predicted results. In addition, the interpolation analysis map of PM2.5 concentration distribution based on the measured value of each monitoring station is made. This is used to compare with the interpolation analysis map based on the predicted values so as to illustrate the rationality of the PM2.5 concentration prediction method.
Long Short-Term Memory Network and Ordinary Kriging Method for Prediction of PM2.5 Concentration
https://orcid.org/http://orcid.org/0000-0002-8343-7536
https://orcid.org/http://orcid.org/0000-0002-3163-9718
https://orcid.org/http://orcid.org/0000-0003-3741-797X
When building a smart city, one must pay attention to the complex and diverse environmental problems in the city. Air quality prediction is an indispensable part of smart cities as it is conducive to guiding the development of air pollution prevention and control and alleviating urban air pollution. Based on the PM2.5 concentration data of 10 state-controlled air quality monitoring sites in Changsha City, Hunan Province, China from January 1, 2017 to December 30, 2021 and the meteorological data of Changsha city, a long short- term memory recurrent neural network model applicable to PM2.5 concentration prediction of Changsha city is formulated according to actual conditions with reference to related machine learning methods, and is used to predict the daily average concentration of PM2.5 at 10 air quality monitoring sites. Using the predicted PM2.5 concentration at the air quality monitoring sites in Changsha city, the spatial distribution simulation map of PM2.5 mass concentration within Changsha Third Ring Road is made by ordinary kriging method. Suggestions for PM2.5 pollution protection measures are put forward based on the predicted results. In addition, the interpolation analysis map of PM2.5 concentration distribution based on the measured value of each monitoring station is made. This is used to compare with the interpolation analysis map based on the predicted values so as to illustrate the rationality of the PM2.5 concentration prediction method.
Long Short-Term Memory Network and Ordinary Kriging Method for Prediction of PM2.5 Concentration
https://orcid.org/http://orcid.org/0000-0002-8343-7536
https://orcid.org/http://orcid.org/0000-0002-3163-9718
https://orcid.org/http://orcid.org/0000-0003-3741-797X
When building a smart city, one must pay attention to the complex and diverse environmental problems in the city. Air quality prediction is an indispensable part of smart cities as it is conducive to guiding the development of air pollution prevention and control and alleviating urban air pollution. Based on the PM2.5 concentration data of 10 state-controlled air quality monitoring sites in Changsha City, Hunan Province, China from January 1, 2017 to December 30, 2021 and the meteorological data of Changsha city, a long short- term memory recurrent neural network model applicable to PM2.5 concentration prediction of Changsha city is formulated according to actual conditions with reference to related machine learning methods, and is used to predict the daily average concentration of PM2.5 at 10 air quality monitoring sites. Using the predicted PM2.5 concentration at the air quality monitoring sites in Changsha city, the spatial distribution simulation map of PM2.5 mass concentration within Changsha Third Ring Road is made by ordinary kriging method. Suggestions for PM2.5 pollution protection measures are put forward based on the predicted results. In addition, the interpolation analysis map of PM2.5 concentration distribution based on the measured value of each monitoring station is made. This is used to compare with the interpolation analysis map based on the predicted values so as to illustrate the rationality of the PM2.5 concentration prediction method.
Long Short-Term Memory Network and Ordinary Kriging Method for Prediction of PM2.5 Concentration
Lecture Notes in Civil Engineering
Guo, Wei (editor) / Qian, Kai (editor) / Liu, Junyou (author) / Zheng, Bohong (author) / Fan, Jinyu (author)
International Conference on Green Building, Civil Engineering and Smart City ; 2022 ; Guilin, China
Proceedings of the 2022 International Conference on Green Building, Civil Engineering and Smart City ; Chapter: 119 ; 1158-1169
2022-09-08
12 pages
Article/Chapter (Book)
Electronic Resource
English
| DOAJ | 2023
Design of groundwater level monitoring network with ordinary kriging
| British Library Online Contents | 2008
Regional Logistics Demand Prediction: A Long Short-Term Memory Network Method
| DOAJ | 2022
Strain estimation using ordinary Kriging interpolation
| Online Contents | 2016