PM<sub>2.5</sub> Concentration Prediction Based on Spatiotemporal Feature Selection Using XGBoost-MSCNN-GA-LSTM

With the rapid development of China’s industrialization, air pollution is becoming more and more serious. Predicting air quality is essential for identifying further preventive measures to avoid negative impacts. The existing prediction of atmospheric pollutant concentration ignores the problem of f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hongbin Dai, Guangqiu Huang, Huibin Zeng, Fan Yang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	XGBoost MSCNN genetic algorithm LSTM feature selection spatiotemporal feature extraction Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/b15a4deb69f54444b9e485ea191ca55d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b15a4deb69f54444b9e485ea191ca55d
record_format	dspace
spelling	oai:doaj.org-article:b15a4deb69f54444b9e485ea191ca55d2021-11-11T19:43:05ZPM<sub>2.5</sub> Concentration Prediction Based on Spatiotemporal Feature Selection Using XGBoost-MSCNN-GA-LSTM10.3390/su1321120712071-1050https://doaj.org/article/b15a4deb69f54444b9e485ea191ca55d2021-11-01T00:00:00Zhttps://www.mdpi.com/2071-1050/13/21/12071https://doaj.org/toc/2071-1050With the rapid development of China’s industrialization, air pollution is becoming more and more serious. Predicting air quality is essential for identifying further preventive measures to avoid negative impacts. The existing prediction of atmospheric pollutant concentration ignores the problem of feature redundancy and spatio-temporal characteristics; the accuracy of the model is not high, the mobility of it is not strong. Therefore, firstly, extreme gradient lifting (XGBoost) is applied to extract features from PM<sub>2.5</sub>, then one-dimensional multi-scale convolution kernel (MSCNN) is used to extract local temporal and spatial feature relations from air quality data, and linear splicing and fusion is carried out to obtain the spatio-temporal feature relationship of multi-features. Finally, XGBoost and MSCNN combine the advantages of LSTM in dealing with time series. Genetic algorithm (GA) is applied to optimize the parameter set of long-term and short-term memory network (LSTM) network. The spatio-temporal relationship of multi-features is input into LSTM network, and then the long-term feature dependence of multi-feature selection is output to predict PM<sub>2.5</sub> concentration. A XGBoost-MSCGL of PM<sub>2.5</sub> concentration prediction model based on spatio-temporal feature selection is established. The data set comes from the hourly concentration data of six kinds of atmospheric pollutants and meteorological data in Fen-Wei Plain in 2020. To verify the effectiveness of the model, the XGBoost-MSCGL model is compared with the benchmark models such as multilayer perceptron (MLP), CNN, LSTM, XGBoost, CNN-LSTM with before and after using XGBoost feature selection. According to the forecast results of 12 cities, compared with the single model, the root mean square error (RMSE) decreased by about 39.07%, the average MAE decreased by about 42.18%, the average MAE decreased by about 49.33%, but R<sup>2</sup> increased by 23.7%. Compared with the model after feature selection, the root mean square error (RMSE) decreased by an average of about 15%. On average, the MAPE decreased by 16%, the MAE decreased by 21%, and R<sup>2</sup> increased by 2.6%. The experimental results show that the XGBoost-MSCGL prediction model offer a more comprehensive understanding, runs deeper levels, guarantees a higher prediction accuracy, and ensures a better generalization ability in the prediction of PM<sub>2.5</sub> concentration.Hongbin DaiGuangqiu HuangHuibin ZengFan YangMDPI AGarticleXGBoostMSCNNgenetic algorithmLSTMfeature selectionspatiotemporal feature extractionEnvironmental effects of industries and plantsTD194-195Renewable energy sourcesTJ807-830Environmental sciencesGE1-350ENSustainability, Vol 13, Iss 12071, p 12071 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	XGBoost MSCNN genetic algorithm LSTM feature selection spatiotemporal feature extraction Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
spellingShingle	XGBoost MSCNN genetic algorithm LSTM feature selection spatiotemporal feature extraction Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350 Hongbin Dai Guangqiu Huang Huibin Zeng Fan Yang PM<sub>2.5</sub> Concentration Prediction Based on Spatiotemporal Feature Selection Using XGBoost-MSCNN-GA-LSTM
description	With the rapid development of China’s industrialization, air pollution is becoming more and more serious. Predicting air quality is essential for identifying further preventive measures to avoid negative impacts. The existing prediction of atmospheric pollutant concentration ignores the problem of feature redundancy and spatio-temporal characteristics; the accuracy of the model is not high, the mobility of it is not strong. Therefore, firstly, extreme gradient lifting (XGBoost) is applied to extract features from PM<sub>2.5</sub>, then one-dimensional multi-scale convolution kernel (MSCNN) is used to extract local temporal and spatial feature relations from air quality data, and linear splicing and fusion is carried out to obtain the spatio-temporal feature relationship of multi-features. Finally, XGBoost and MSCNN combine the advantages of LSTM in dealing with time series. Genetic algorithm (GA) is applied to optimize the parameter set of long-term and short-term memory network (LSTM) network. The spatio-temporal relationship of multi-features is input into LSTM network, and then the long-term feature dependence of multi-feature selection is output to predict PM<sub>2.5</sub> concentration. A XGBoost-MSCGL of PM<sub>2.5</sub> concentration prediction model based on spatio-temporal feature selection is established. The data set comes from the hourly concentration data of six kinds of atmospheric pollutants and meteorological data in Fen-Wei Plain in 2020. To verify the effectiveness of the model, the XGBoost-MSCGL model is compared with the benchmark models such as multilayer perceptron (MLP), CNN, LSTM, XGBoost, CNN-LSTM with before and after using XGBoost feature selection. According to the forecast results of 12 cities, compared with the single model, the root mean square error (RMSE) decreased by about 39.07%, the average MAE decreased by about 42.18%, the average MAE decreased by about 49.33%, but R<sup>2</sup> increased by 23.7%. Compared with the model after feature selection, the root mean square error (RMSE) decreased by an average of about 15%. On average, the MAPE decreased by 16%, the MAE decreased by 21%, and R<sup>2</sup> increased by 2.6%. The experimental results show that the XGBoost-MSCGL prediction model offer a more comprehensive understanding, runs deeper levels, guarantees a higher prediction accuracy, and ensures a better generalization ability in the prediction of PM<sub>2.5</sub> concentration.
format	article
author	Hongbin Dai Guangqiu Huang Huibin Zeng Fan Yang
author_facet	Hongbin Dai Guangqiu Huang Huibin Zeng Fan Yang
author_sort	Hongbin Dai
title	PM<sub>2.5</sub> Concentration Prediction Based on Spatiotemporal Feature Selection Using XGBoost-MSCNN-GA-LSTM
title_short	PM<sub>2.5</sub> Concentration Prediction Based on Spatiotemporal Feature Selection Using XGBoost-MSCNN-GA-LSTM
title_full	PM<sub>2.5</sub> Concentration Prediction Based on Spatiotemporal Feature Selection Using XGBoost-MSCNN-GA-LSTM
title_fullStr	PM<sub>2.5</sub> Concentration Prediction Based on Spatiotemporal Feature Selection Using XGBoost-MSCNN-GA-LSTM
title_full_unstemmed	PM<sub>2.5</sub> Concentration Prediction Based on Spatiotemporal Feature Selection Using XGBoost-MSCNN-GA-LSTM
title_sort	pm<sub>2.5</sub> concentration prediction based on spatiotemporal feature selection using xgboost-mscnn-ga-lstm
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b15a4deb69f54444b9e485ea191ca55d
work_keys_str_mv	AT hongbindai pmsub25subconcentrationpredictionbasedonspatiotemporalfeatureselectionusingxgboostmscnngalstm AT guangqiuhuang pmsub25subconcentrationpredictionbasedonspatiotemporalfeatureselectionusingxgboostmscnngalstm AT huibinzeng pmsub25subconcentrationpredictionbasedonspatiotemporalfeatureselectionusingxgboostmscnngalstm AT fanyang pmsub25subconcentrationpredictionbasedonspatiotemporalfeatureselectionusingxgboostmscnngalstm
_version_	1718431429298225152

PM<sub>2.5</sub> Concentration Prediction Based on Spatiotemporal Feature Selection Using XGBoost-MSCNN-GA-LSTM

Ejemplares similares