Machine-learned modeling of PM2.5 exposures in rural Lao PDR

Application of machine learning in atmospheric pollution research: A state-of-art review

Machine learning (ML) is an artificial intelligence technology that has been used in atmospheric pollution research due to their powerful fitting ability. In this review, 105 articles related to ML and the atmospheric pollution research are critically reviewed. Applications of ML in the prediction of atmospheric pollution (mainly particulate matters) are systematically described, including the principle of prediction, influencing factors and improvement measures. Researchers can improve the accuracy of the prediction model through three main aspects, namely considering the geographical features of the study area into the model, introducing the physical characteristics of pollutants, matching and optimizing ML models. And by using interpretable ML tools, researchers are able to understand the mechanism of the model and gain in-depth information. Then, the state-of-art applications of ML in the source apportionment of atmospheric particulate matter and the effect of atmospheric pollutants on human health are also described. In addition, the advantages and disadvantages of the current applications of ML in atmospheric pollution research are summarized, and the application perspective of ML in this field is elucidated. Given the scarcity of source apportionment applications and human health research, standardized research methods and specialized ML methods are required in atmospheric pollution research to connect these two disciplines.

A pruned feed-forward neural network (pruned-FNN) approach to measure air pollution exposure

Environmental epidemiology studies require accurate estimations of exposure intensities to air pollution. The process from air pollutant emission to individual exposure is however complex and nonlinear, which poses significant modeling challenges. This study aims to develop an exposure assessment model that can strike a balance between accuracy, complexity, and usability. In this regard, neural networks offer one possible approach. This study employed a custom-designed pruned feed-forward neural network (pruned-FNN) approach to calculate the air pollution exposure index based on emission time and rates, terrain factors, meteorological conditions, and proximity measurements. The model's performance was evaluated by cross-validating the estimated exposure indexes with ground-based monitoring records. The pruned FNN can predict pollution exposure indexes (PEIs) that are highly and stably correlated with the monitored air pollutant concentrations (Spearman's rank correlation coefficients for tenfold cross-validation (mean ± standard deviation: 0.906 ± 0.028) and for random cross-validation (0.913 ± 0.024)). The predicted values are also close to the ground truth in most cases (95.5% of the predicted PEIs have relative errors smaller than 10%) when the training datasets are sufficiently large and well-covered. The pruned-FNN method can make accurate exposure estimations using a flexible number of variables and less extensive data in a less money/time-consuming manner. Compared to other exposure assessment models, the pruned FNN is an appropriate and effective approach for exposure assessment that covers a large geographic area over a long period of time.

Comparing human exposure to fine particulate matter in low and high-income countries: A systematic review of studies measuring personal PM2.5 exposure

BACKGROUND

Due to the adverse health effects of air pollution, researchers have advocated for personal exposure measurements whereby individuals carry portable monitors in order to better characterise and understand the sources of people's pollution exposure.

OBJECTIVES

The aim of this systematic review is to assess the differences in the magnitude and sources of personal PM2.5 exposures experienced between countries at contrasting levels of income.

METHODS

This review summarised studies that measured participants personal exposure by carrying a PM2.5 monitor throughout their typical day. Personal PM2.5 exposures were summarised to indicate the distribution of exposures measured within each country income category (based on low (LIC), lower-middle (LMIC), upper-middle (UMIC), and high (HIC) income countries) and between different groups (i.e. gender, age, urban or rural residents).

RESULTS

From the 2259 search results, there were 140 studies that met our criteria. Overall, personal PM2.5 exposures in HICs were lower compared to other countries, with UMICs exposures being slightly lower than exposures measured in LMICs or LICs. 34% of measured groups in HICs reported below the ambient World Health Organisation 24-h PM2.5 guideline of 15 μg/m3, compared to only 1% of UMICs and 0% of LMICs and LICs. There was no difference between rural and urban participant exposures in HICs, but there were noticeably higher exposures recorded in rural areas compared to urban areas in non-HICs, due to significant household sources of PM2.5 in rural locations. In HICs, studies reported that secondhand smoke, ambient pollution infiltrating indoors, and traffic emissions were the dominant contributors to personal exposures. While, in non-HICs, household cooking and heating with biomass and coal were reported as the most important sources.

CONCLUSION

This review revealed a growing literature of personal PM2.5 exposure studies, which highlighted a large variability in exposures recorded and severe inequalities in geographical and social population subgroups.

Modeling approaches and performance for estimating personal exposure to household air pollution: A case study in Kenya

This study assessed the performance of modeling approaches to estimate personal exposure in Kenyan homes where cooking fuel combustion contributes substantially to household air pollution (HAP). We measured emissions (PM_2.5 , black carbon, CO); household air pollution (PM_2.5 , CO); personal exposure (PM_2.5 , CO); stove use; and behavioral, socioeconomic, and household environmental characteristics (eg, ventilation and kitchen volume). We then applied various modeling approaches: a single-zone model; indirect exposure models, which combine person-location and area-level measurements; and predictive statistical models, including standard linear regression and ensemble machine learning approaches based on a set of predictors such as fuel type, room volume, and others. The single-zone model was reasonably well-correlated with measured kitchen concentrations of PM_2.5 (R²  = 0.45) and CO (R²  = 0.45), but lacked precision. The best performing regression model used a combination of survey-based data and physical measurements (R²  = 0.76) and a root mean-squared error of 85 µg/m³ , and the survey-only-based regression model was able to predict PM2.5 exposures with an R² of 0.51. Of the machine learning algorithms evaluated, extreme gradient boosting performed best, with an R² of 0.57 and RMSE of 98 µg/m³ .

Transition to clean household energy through an application of integrated model: Ensuring sustainability for better health, climate and environment

Sustained use and adoption of clean cooking fuels have become an important concern for developing countries due to the enormous burden of diseases attributable to household air pollution (HAP). The transition and adoption of clean household energy involve various socio-economic, behavioral, and technological barriers at different community levels. Hence, the present paper aims to scrutinize the factors, key determinants, and other interventions among rural households that limit clean cookstoves' sustained uses. The study proposes an integrated model to enhance clean cooking fuel uptake and uses based on the available evidence. The health, climate and environmental factors were identified as the key to trigger the adoption of clean cooking fuel alternatives. The model comprises the integration of components for targeted clean fuel policy interventions and promotes green recovery. The elements include Knowledge, Housing characteristics, Awareness, Interventions, Willingness to pay, Adoption, Lower emissions and Gender Equality (THE KHAIWAL model) to ascertain the intervention focus regions. Integration of model components in policy implementation will promote clean household energy to reduce emissions, leading to improve quality of life, good health, women empowerment, better air quality and climate.

Combined use of principal component analysis and artificial neural network approach to improve estimates of PM2.5 personal exposure: A case study on older adults

Accurate exposure estimate of the air pollutant PM_2.5 is required to evaluate its health impacts in epidemiological studies, due to its adverse effects on human's respiratory and cardiovascular systems. However, traditional personal sampling is time and cost consuming. Thus, modeling techniques are needed to accurately predict the personal exposure level to PM_2.5. In this study, a total of 117 older adults over 60 were recruited in Tianjin, a heavily polluted city in northern China, for indoor, outdoor and personal PM_2.5 sampling. Eighteen variables which may increase the exposure level of older adults were recorded for artificial neural network (ANN) simulation. Four modeling techniques, including time-integrated activity modeling, Monte Carlo simulation, ANN modeling, and combined use of principal component analysis (PCA) and ANN model, were used to evaluate their ability for predicting real exposure values of PM_2.5. The results of traditional time-weighted activity modeling showed the lowest correlation with measured values with R² of 0.57 and 0.42 in winter and summer, respectively. For Monte Carlo simulation, high correlation was obtained (R² of 0.93 and 0.92 in winter and summer, respectively) between percentiles of the predicted and the real exposure values. Compared with the simple ANN models, the combined use of PCA and ANN produced the most accurate results with R² of 0.99 and RMSE lower than 15. Since the information of the input variables for the PCA-ANN model can be obtained from the questionnaire and fixed air quality monitoring sites, this technique shows a great potential in predicting personal exposure level to the air pollutant because no additional concentration measurement is needed.

Air Pollutant Exposure and Stove Use Assessment Methods for the Household Air Pollution Intervention Network (HAPIN) Trial

BACKGROUND

High quality personal exposure data is fundamental to understanding the health implications of household energy interventions, interpreting analyses across assigned study arms, and characterizing exposure-response relationships for household air pollution. This paper describes the exposure data collection for the Household Air Pollution Intervention Network (HAPIN), a multicountry randomized controlled trial of liquefied petroleum gas stoves and fuel among 3,200 households in India, Rwanda, Guatemala, and Peru.

OBJECTIVES

The primary objectives of the exposure assessment are to estimate the exposure contrast achieved following a clean fuel intervention and to provide data for analyses of exposure-response relationships across a range of personal exposures.

METHODS

Exposure measurements are being conducted over the 3-y time frame of the field study. We are measuring fine particulate matter [PM <   2.5 μ m in aerodynamic diameter (PM 2.5 )] with the Enhanced Children's MicroPEM™ (RTI International), carbon monoxide (CO) with the USB-EL-CO (Lascar Electronics), and black carbon with the OT21 transmissometer (Magee Scientific) in pregnant women, adult women, and children < 1   year of age, primarily via multiple 24-h personal assessments (three, six, and three measurements, respectively) over the course of the 18-month follow-up period using lightweight monitors. For children we are using an indirect measurement approach, combining data from area monitors and locator devices worn by the child. For a subsample (up to 10%) of the study population, we are doubling the frequency of measurements in order to estimate the accuracy of subject-specific typical exposure estimates. In addition, we are conducting ambient air monitoring to help characterize potential contributions of PM 2.5 exposure from background concentration. Stove use monitors (Geocene) are being used to assess compliance with the intervention, given that stove stacking (use of traditional stoves in addition to the intervention gas stove) may occur.

CONCLUSIONS

The tools and approaches being used for HAPIN to estimate personal exposures build on previous efforts and take advantage of new technologies. In addition to providing key personal exposure data for this study, we hope the application and learnings from our exposure assessment will help inform future efforts to characterize exposure to household air pollution and for other contexts. https://doi.org/10.1289/EHP6422.