Development and intercity transferability of land-use regression models for predicting ambient PM₁₀, PM_2.5, NO₂ and O₃ concentrations in northern Taiwan

Abstract

Abstract. To provide long-term air pollutant exposure estimates for epidemiological studies, it is essential to test the feasibility of developing land-use regression (LUR) models using only routine air quality measurement data and to evaluate the transferability of LUR models between nearby cities. In this study, we developed and evaluated the intercity transferability of annual-average LUR models for ambient respirable suspended particulates (PM10), fine suspended particulates (PM2.5), nitrogen dioxide (NO2) and ozone (O3) in the Taipei–Keelung metropolitan area of northern Taiwan in 2019. Ambient PM10, PM2.5, NO2 and O3 measurements at 30 fixed-site stations were used as the dependent variables, and a total of 156 potential predictor variables in six categories (i.e., population density, road network, land-use type, normalized difference vegetation index, meteorology and elevation) were extracted using buffer spatial analysis. The LUR models were developed using the supervised forward linear regression approach. The LUR models for ambient PM10, PM2.5, NO2 and O3 achieved relatively high prediction performance, with R2 values of > 0.72 and leave-one-out cross-validation (LOOCV) R2 values of > 0.53. The intercity transferability of LUR models varied among the air pollutants, with transfer-predictive R2 values of > 0.62 for NO2 and < 0.56 for the other three pollutants. The LUR-model-based 500 m × 500 m spatial-distribution maps of these air pollutants illustrated pollution hot spots and the heterogeneity of population exposure, which provide valuable information for policymakers in designing effective air pollution control strategies. The LUR-model-based air pollution exposure estimates captured the spatial variability in exposure for participants in a cohort study. This study highlights that LUR models can be reasonably established upon a routine monitoring network, but there exist uncertainties when transferring LUR models between nearby cities. To the best of our knowledge, this study is the first to evaluate the intercity transferability of LUR models in Asia.