Estimating hourly average indoor PM2.5 using the random forest approach in two megacities, China

People usually spend most of their time indoors, so indoor fine particulate matter (PM2.5) concentrations are crucial for refining individual PM2.5 exposure evaluation. The development of indoor PM2.5 concentration prediction models is essential for the health risk assessment of PM2.5 in epidemiological studies involving large populations. 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 PM2.5 concentration prediction models. Indoor PM2.5 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. The final predictor variables incorporated in the MLR model were outdoor PM2.5 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 (R2) 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, R2 = 71.86%). In terms of predictors, the importance results of predictor variables for both types of models suggested that outdoor PM2.5 concentration, type of place, season, hour, wind direction, and surface wind speed were the most important predictor variables. In this research, hourly average indoor PM2.5 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.

Determinants of personal exposure to fine particulate matter in the retired adults – Results of a panel study in two megacities, China

Background: The Reducing Air Pollution in Detroit Intervention Study (RAPIDS) was designed to evaluate cardiovascular health benefits and personal fine particulate matter (particulate matter < 2.5 μm in diameter, PM2.5) exposure reductions via portable air filtration units (PAFs) among older adults in Detroit, Michigan. This double-blind randomized crossover intervention study has shown that, compared to sham, air filtration for 3 days decreased 3-day average brachial systolic blood pressure by 3.2 mmHg. The results also showed that commercially available HEPA-type and true HEPA PAFs mitigated median indoor PM2.5 concentrations by 58% and 65%, respectively. However, to our knowledge, no health intervention study in which a significant positive health effect was observed has also evaluated how outdoor and indoor PM2.5 sources impacted the subjects. With that in mind, detailed characterization of outdoor and indoor PM2.5 samples collected during this study and a source apportionment analysis of those samples using a positive matrix factorization model were completed. The aims of this most recent work were to characterize the indoor and outdoor sources of the PM2.5 this community was exposed to and to assess how effectively commercially available HEPA-type and true HEPA PAFs were able to reduce indoor and outdoor PM2.5 source contributions. Methods: Approximately 24 h daily indoor and outdoor PM2.5 samples were collected on Teflon and Quartz filters from the apartments of 40 study subjects during each 3-day intervention period. These filters were analyzed for mass, carbon, and trace elements. Environmental Protection Agency Positive Matrix Factorization (PMF) 5.0 was utilized to determine major emission sources that contributed to the outdoor and indoor PM2.5 levels during this study. Results: The major sources of outdoor PM2.5 were secondary aerosols (28%), traffic/urban dust (24%), iron/steel industries (15%), sewage/municipal incineration (10%), and oil combustion/refinery (6%). The major sources of indoor PM2.5 were organic compounds (45%), traffic + sewage/municipal incineration (14%), secondary aerosols (13%), smoking (7%), and urban dust (2%). Infiltration of outdoor PM2.5 for sham, HEPA-type, and true HEPA air filtration was 79 ± 24%, 61 ± 32%, and 51 ± 34%, respectively. Conclusions: The results from our study showed that intervention with PAFs was able to significantly decrease indoor PM2.5 derived from outdoor and indoor PM2.5 sources. The PAFs were also able to significantly reduce the infiltration of outdoor PM2.5. The results of this study provide insights into what types of major PM2.5 sources this community is exposed to and what degree of air quality and systolic blood pressure improvements are possible through the use of commercially available PAFs in a real-world setting.

Indoor PM2.5 and its morphology in a naturally ventilated office in Xi'an, China

Evaluation of random forest regression and multiple linear regression for predicting indoor fine particulate matter concentrations in a highly polluted city

As individuals become more confined to their homes, especially during the COVID-19 lockdown and the post-pandemic era, human activities will continue to generate more indoor particles. However, the toxicity effects of indoor particles remain unknown during residents’ occupancy time. Eighteen 24 hours of indoor and outdoor PM2.5 samples were collected using 37 mm polyvinyl chloride (PVC) filter within a residential terrace house in Serdang, Selangor, during the 2021 Malaysia lockdown between February and March 2021. PM2.5 samples were then extracted using methanol. MTT assay determined the cytotoxic activity of extracted indoor and outdoor PM2.5 treated at different concentrations (25–200 µg mL−1) on human lung cells (MRC-5) at a 24-hour incubation period. The 24-h mass concentration of outdoor PM2.5 (41.4 ± 1.99 µg m−3) was significantly three times higher than indoor PM2.5 (11.8 ± 0.60 µg m−3) (p < 0.05). However, exposure to indoor PM2.5 at higher concentrations (100 and 200 µg mL−1) on lung cells (MRC-5) significantly reduces cell viability compared to outdoor PM2.5, suggesting that exposure to indoor PM2.5 causes toxicity to the lung cells compared to outdoor PM2.5. In parallel, indoor real-time PM2.5 measurements were recorded in the kitchen during cooking and non-cooking days. We found cooking days generated higher indoor PM2.5 concentrations (maximum PM2.5 = 75.0 µg m−3), suggesting that cooking activity might contribute to the toxicity of indoor PM2.5. Due to the limited yield of indoor and outdoor PM2.5, further optimization on the extraction of PM2.5 should be carried out to evaluate further the mechanism of cytotoxicity of indoor PM2.5 on the lung cells.

Exposure to indoor particulate matter less than 2.5 µm in diameter (PM2.5) is a critical health risk factor. Therefore, measuring indoor PM2.5 concentrations is important for assessing their health risks and further investigating the sources and influential factors. However, installing monitoring instruments to collect indoor PM2.5 data is difficult and expensive. Therefore, several indoor PM2.5 concentration prediction models have been developed. However, these prediction models only assess the daily average PM2.5 concentrations in cold or temperate regions. The factors that influence PM2.5 concentration differ according to climatic conditions. In this study, we developed a prediction model for hourly indoor PM2.5 concentrations in Taiwan (tropical and subtropical region) by using a multiple linear regression model and investigated the impact factor. The sample comprised 93 study cases (1979 measurements) and 25 potential predictor variables. Cross-validation was performed to assess performance. The prediction model explained 74% of the variation, and outdoor PM2.5 concentrations, the difference between indoor and outdoor CO2 levels, building type, building floor level, bed sheet cleaning, bed sheet replacement, and mosquito coil burning were included in the prediction model. Cross-validation explained 75% of variation on average. The results also confirm that the prediction model can be used to estimate indoor PM2.5 concentrations across seasons and areas. In summary, we developed a prediction model of hourly indoor PM2.5 concentrations and suggested that outdoor PM2.5 concentrations, ventilation, building characteristics, and human activities should be considered. Moreover, it is important to consider outdoor air quality while occupants open or close windows or doors for regulating ventilation rate and human activities changing also can reduce indoor PM2.5 concentrations.

Indoor PM2.5 in an urban zone with heavy wood smoke pollution: The case of Temuco, Chile

Indoor PM2.5 and its chemical composition during a heavy haze–fog episode at Jinan, China

The health risks associated with wildfires are expected to increase due to climate change. Children are susceptible to wildfire smoke, but little is known about indoor smoke exposure at childcare facilities. The objective of this analysis was to estimate the effects of outdoor PM2.5 and wildfire smoke episodes on indoor PM2.5 at childcare facilities across British Columbia, Canada. We installed low-cost air-quality sensors inside and outside 45 childcare facilities and focused our analysis on operational hours (Monday–Friday, 08:00–18:00) during the 2022 wildfire season (01 August–31 October). Using random-slope random-intercept linear mixed effects regression, we estimated the overall and facility-specific effects of outdoor PM2.5 on indoor PM2.5, while accounting for covariates. We examined how wildfire smoke affected this relationship by separately analyzing days with and without wildfire smoke. Average indoor PM2.5 increased by 235% on wildfire days across facilities. There was a positive relationship between outdoor and indoor PM2.5 that was not strongly influenced by linear adjustment for meteorological and area-based socio-economic factors. A 1.0 μg m−3 increase in outdoor PM2.5 was associated with a 0.55 μg m−3 [95% CI: 0.47, 0.63] increase indoors on non-wildfire smoke days and 0.51 μg m−3 [95% CI: 0.44, 0.58] on wildfire-smoke days. Facility-specific regression coefficients of the effect of outdoor PM2.5 on indoor PM2.5 was variable between facilities on wildfire (0.18–0.79 μg m−3) and non-wildfire days (0.11–1.03 μg m−3). Indoor PM2.5 responded almost immediately to increased outdoor PM2.5 concentrations. Across facilities, 89% and 93% of the total PM2.5 infiltration over 60 min occurred within the first 10 min following an increase in outdoor PM2.5 on non-wildfire and wildfire days, respectively. We found that indoor PM2.5 in childcare facilities increased with outdoor PM2.5. This effect varied between facilities and between wildfire-smoke and non-wildfire smoke days. These findings highlight the importance of air quality monitoring at childcare facilities for informed decision-making.

Measuring and modeling of residential black carbon concentrations in two megacities, China

This study was carried out to determine the distribution of particles in classrooms in primary schools located in the centre of the city of Sari, Iran and identify the relationship between indoor classroom particle levels and outdoor PM2.5 concentrations. Outdoor PM2.5 and indoor PM1, PM2.5, and PM10 were monitored using a real-time Micro Dust Pro monitor and a GRIMM monitor, respectively. Both monitors were calibrated by gravimetric method using filters. The Kolmogorov-Smirnov test showed that all indoor and outdoor data fitted normal distribution. Mean indoor PM1, PM2.5, PM10 and outdoor PM2.5 concentrations for all of the classrooms were 17.6 μg m(-3), 46.6 μg m(-3), 400.9 μg m(-3), and 36.9 μg m(-3), respectively. The highest levels of indoor and outdoor PM2.5 concentrations were measured at the Shahed Boys School (69.1 μg m(-3) and 115.8 μg m(-3), respectively). The Kazemi school had the lowest levels of indoor and outdoor PM2.5 (29.1 μg m(-3) and 15.5 μg m(-3), respectively). In schools located near both main and small roads, the association between indoor fine particle (PM2.5 and PM1) and outdoor PM2.5 levels was stronger than that between indoor PM10 and outdoor PM2.5 levels. Mean indoor PM2.5 and PM10 and outdoor PM2.5 were higher than the standards for PM2.5 and PM10, and there was a good correlation between indoor and outdoor fine particle concentrations.

In order to identify the sources of indoor PM2.5 and to check which factors influence the concentration of indoor PM2.5 and chemical elements, indoor concentrations of PM2.5 and its related elements in residential houses in Beijing were explored. Indoor and outdoor PM2.5 samples that were monitored continuously for one week were collected. Indoor and outdoor concentrations of PM2.5 and 15 elements (Al, As, Ca, Cd, Cu, Fe, K, Mg, Mn, Na, Pb, Se, Tl, V, Zn) were calculated and compared. The median indoor concentration of PM2.5 was 57.64 μg/m3. For elements in indoor PM2.5, Cd and As may be sensitive to indoor smoking, Zn, Ca and Al may be related to indoor sources other than smoking, Pb, V and Se may mainly come from outdoor. Five factors were extracted for indoor PM2.5 by factor analysis, explained 76.8% of total variance, outdoor sources contributed more than indoor sources. Multiple linear regression analysis for indoor PM2.5, Cd and Pb was performed. Indoor PM2.5 was influenced by factors including outdoor PM2.5, smoking during sampling, outdoor temperature and time of air conditioner use. Indoor Cd was affected by factors including smoking during sampling, outdoor Cd and building age. Indoor Pb concentration was associated with factors including outdoor Pb and time of window open per day, building age and RH. In conclusion, indoor PM2.5 mainly comes from outdoor sources, and the contributions of indoor sources also cannot be ignored. Factors associated indoor and outdoor air exchange can influence the concentrations of indoor PM2.5 and its constituents.

Influence of atmospheric fine particulate matter (PM2.5) pollution on indoor environment during winter in Beijing

Humans basically have a basic need to have a place to live, which can be a house or shelter. Along with the rapid population growth in Indonesia, which continues to increase every year, many people do not have or have a decent place to live. Therefore, careful planning is needed so that every family can have a decent home. One very important aspect in planning investment in the form of property is predicting future house prices. One approach that can be used is to use a Random Forest and Multiple Linear Regression algorithm, which is an algorithm from Machine Learning. There are several factors that can influence the price of a house, including land area, building area, number of bedrooms, bathrooms and garage. In this research, multiple linear regression and random forest regression methods were chosen. The aim of this research is to find the best prediction results between the two methods. To achieve accurate predictions, research was carried out repeatedly by dividing the dataset into 80% for training and 20% for testing. The research results show that the random forest regression algorithm provides the best results, with an accuracy of 81.6%.