Enhancing indoor PM_2.5 predictions based on land use and indoor environmental factors by applying machine learning...

The presence of fine particulate matter (PM_2.5) indoors constitutes a significant component of overall PM_2.5 exposure, as individuals spend 90% of their time indoors; however, personal monitoring for large cohorts is often impractical. In light of this, this study seeks to employ a novel geospatial artificial intelligence (Geo-AI) coupled with machine learning (ML) approaches to develop indoor PM_2.5 models. Multiple predictor variables were collected from 102 residential households, including meteorological data; elevation; land use; indoor environmental factors including human activities, building characteristics, infiltration factors, and real-time measurements; and various other factors. Geo-AI, which integrates land use regression, inverse distance weighting, and ML algorithms, was utilized to construct outdoor PM_2.5 and PM₁₀ estimates for residential households. The most influential variables were identified via correlation analysis and stepwise regression. Three ML methods, namely support vector machine, multiple linear regression, and multilayer perceptron (MLP) were used to estimate indoor PM_2.5 concentration. Then, MLP was employed to blend three ML algorithms. The resulting model demonstrated commendable performance, achieving a 10-fold cross-validation R² of 0.92 and a root mean square error of 2.3 μg/m³ for indoor PM_2.5 estimations. Notably, the combination of Geo-AI and ensembled ML models in this study outperformed all other individual models. In addition, the present study pointed out the most influential factors for indoor PM_2.5 model were outdoor PM_2.5, PM_2.5/PM₁₀ ratio, sampling month, infiltration factor, located near factory, cleaning frequency, number of door entrance linked with outdoor, and wall material. Further exploration of diverse ensemble model formats to integrate estimates from different models could enhance overall performance. Consequently, the potential applications of this model extend to estimating real individual exposure to PM_2.5 for further epidemiological research. Moreover, the model offers valuable insights for efficient indoor air quality management and control strategies.