Cargando…

Construction and evaluation of hourly average indoor PM(2.5) concentration prediction models based on multiple types of places

BACKGROUND: People usually spend most of their time indoors, so indoor fine particulate matter (PM(2.5)) concentrations are crucial for refining individual PM(2.5) exposure evaluation. The development of indoor PM(2.5) concentration prediction models is essential for the health risk assessment of PM...

Descripción completa

Detalles Bibliográficos
Autores principales: Shi, Yewen, Du, Zhiyuan, Zhang, Jianghua, Han, Fengchan, Chen, Feier, Wang, Duo, Liu, Mengshuang, Zhang, Hao, Dong, Chunyang, Sui, Shaofeng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10447970/
https://www.ncbi.nlm.nih.gov/pubmed/37637795
http://dx.doi.org/10.3389/fpubh.2023.1213453
_version_ 1785094618298187776
author Shi, Yewen
Du, Zhiyuan
Zhang, Jianghua
Han, Fengchan
Chen, Feier
Wang, Duo
Liu, Mengshuang
Zhang, Hao
Dong, Chunyang
Sui, Shaofeng
author_facet Shi, Yewen
Du, Zhiyuan
Zhang, Jianghua
Han, Fengchan
Chen, Feier
Wang, Duo
Liu, Mengshuang
Zhang, Hao
Dong, Chunyang
Sui, Shaofeng
author_sort Shi, Yewen
collection PubMed
description BACKGROUND: People usually spend most of their time indoors, so indoor fine particulate matter (PM(2.5)) concentrations are crucial for refining individual PM(2.5) exposure evaluation. The development of indoor PM(2.5) concentration prediction models is essential for the health risk assessment of PM(2.5) in epidemiological studies involving large populations. METHODS: In this study, based on the monitoring data of multiple types of places, the classical multiple linear regression (MLR) method and random forest regression (RFR) algorithm of machine learning were used to develop hourly average indoor PM(2.5) concentration prediction models. Indoor PM(2.5) concentration data, which included 11,712 records from five types of places, were obtained by on-site monitoring. Moreover, the potential predictor variable data were derived from outdoor monitoring stations and meteorological databases. A ten-fold cross-validation was conducted to examine the performance of all proposed models. RESULTS: The final predictor variables incorporated in the MLR model were outdoor PM(2.5) concentration, type of place, season, wind direction, surface wind speed, hour, precipitation, air pressure, and relative humidity. The ten-fold cross-validation results indicated that both models constructed had good predictive performance, with the determination coefficients (R(2)) of RFR and MLR were 72.20 and 60.35%, respectively. Generally, the RFR model had better predictive performance than the MLR model (RFR model developed using the same predictor variables as the MLR model, R(2) = 71.86%). In terms of predictors, the importance results of predictor variables for both types of models suggested that outdoor PM(2.5) concentration, type of place, season, hour, wind direction, and surface wind speed were the most important predictor variables. CONCLUSION: In this research, hourly average indoor PM(2.5) concentration prediction models based on multiple types of places were developed for the first time. Both the MLR and RFR models based on easily accessible indicators displayed promising predictive performance, in which the machine learning domain RFR model outperformed the classical MLR model, and this result suggests the potential application of RFR algorithms for indoor air pollutant concentration prediction.
format Online
Article
Text
id pubmed-10447970
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-104479702023-08-25 Construction and evaluation of hourly average indoor PM(2.5) concentration prediction models based on multiple types of places Shi, Yewen Du, Zhiyuan Zhang, Jianghua Han, Fengchan Chen, Feier Wang, Duo Liu, Mengshuang Zhang, Hao Dong, Chunyang Sui, Shaofeng Front Public Health Public Health BACKGROUND: People usually spend most of their time indoors, so indoor fine particulate matter (PM(2.5)) concentrations are crucial for refining individual PM(2.5) exposure evaluation. The development of indoor PM(2.5) concentration prediction models is essential for the health risk assessment of PM(2.5) in epidemiological studies involving large populations. METHODS: In this study, based on the monitoring data of multiple types of places, the classical multiple linear regression (MLR) method and random forest regression (RFR) algorithm of machine learning were used to develop hourly average indoor PM(2.5) concentration prediction models. Indoor PM(2.5) concentration data, which included 11,712 records from five types of places, were obtained by on-site monitoring. Moreover, the potential predictor variable data were derived from outdoor monitoring stations and meteorological databases. A ten-fold cross-validation was conducted to examine the performance of all proposed models. RESULTS: The final predictor variables incorporated in the MLR model were outdoor PM(2.5) concentration, type of place, season, wind direction, surface wind speed, hour, precipitation, air pressure, and relative humidity. The ten-fold cross-validation results indicated that both models constructed had good predictive performance, with the determination coefficients (R(2)) of RFR and MLR were 72.20 and 60.35%, respectively. Generally, the RFR model had better predictive performance than the MLR model (RFR model developed using the same predictor variables as the MLR model, R(2) = 71.86%). In terms of predictors, the importance results of predictor variables for both types of models suggested that outdoor PM(2.5) concentration, type of place, season, hour, wind direction, and surface wind speed were the most important predictor variables. CONCLUSION: In this research, hourly average indoor PM(2.5) concentration prediction models based on multiple types of places were developed for the first time. Both the MLR and RFR models based on easily accessible indicators displayed promising predictive performance, in which the machine learning domain RFR model outperformed the classical MLR model, and this result suggests the potential application of RFR algorithms for indoor air pollutant concentration prediction. Frontiers Media S.A. 2023-08-10 /pmc/articles/PMC10447970/ /pubmed/37637795 http://dx.doi.org/10.3389/fpubh.2023.1213453 Text en Copyright © 2023 Shi, Du, Zhang, Han, Chen, Wang, Liu, Zhang, Dong and Sui. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Public Health
Shi, Yewen
Du, Zhiyuan
Zhang, Jianghua
Han, Fengchan
Chen, Feier
Wang, Duo
Liu, Mengshuang
Zhang, Hao
Dong, Chunyang
Sui, Shaofeng
Construction and evaluation of hourly average indoor PM(2.5) concentration prediction models based on multiple types of places
title Construction and evaluation of hourly average indoor PM(2.5) concentration prediction models based on multiple types of places
title_full Construction and evaluation of hourly average indoor PM(2.5) concentration prediction models based on multiple types of places
title_fullStr Construction and evaluation of hourly average indoor PM(2.5) concentration prediction models based on multiple types of places
title_full_unstemmed Construction and evaluation of hourly average indoor PM(2.5) concentration prediction models based on multiple types of places
title_short Construction and evaluation of hourly average indoor PM(2.5) concentration prediction models based on multiple types of places
title_sort construction and evaluation of hourly average indoor pm(2.5) concentration prediction models based on multiple types of places
topic Public Health
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10447970/
https://www.ncbi.nlm.nih.gov/pubmed/37637795
http://dx.doi.org/10.3389/fpubh.2023.1213453
work_keys_str_mv AT shiyewen constructionandevaluationofhourlyaverageindoorpm25concentrationpredictionmodelsbasedonmultipletypesofplaces
AT duzhiyuan constructionandevaluationofhourlyaverageindoorpm25concentrationpredictionmodelsbasedonmultipletypesofplaces
AT zhangjianghua constructionandevaluationofhourlyaverageindoorpm25concentrationpredictionmodelsbasedonmultipletypesofplaces
AT hanfengchan constructionandevaluationofhourlyaverageindoorpm25concentrationpredictionmodelsbasedonmultipletypesofplaces
AT chenfeier constructionandevaluationofhourlyaverageindoorpm25concentrationpredictionmodelsbasedonmultipletypesofplaces
AT wangduo constructionandevaluationofhourlyaverageindoorpm25concentrationpredictionmodelsbasedonmultipletypesofplaces
AT liumengshuang constructionandevaluationofhourlyaverageindoorpm25concentrationpredictionmodelsbasedonmultipletypesofplaces
AT zhanghao constructionandevaluationofhourlyaverageindoorpm25concentrationpredictionmodelsbasedonmultipletypesofplaces
AT dongchunyang constructionandevaluationofhourlyaverageindoorpm25concentrationpredictionmodelsbasedonmultipletypesofplaces
AT suishaofeng constructionandevaluationofhourlyaverageindoorpm25concentrationpredictionmodelsbasedonmultipletypesofplaces