In:
Frontiers in Public Health, Frontiers Media SA, Vol. 11 ( 2023-8-10)
Abstract:
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.
Type of Medium:
Online Resource
ISSN:
2296-2565
DOI:
10.3389/fpubh.2023.1213453
DOI:
10.3389/fpubh.2023.1213453.s001
Language:
Unknown
Publisher:
Frontiers Media SA
Publication Date:
2023
detail.hit.zdb_id:
2711781-9
Permalink