Optimizing modeling windows to better capture the long-term variation of PM2.5 concentrations in China during 2005–2019

Abstract

Including data of different time intervals during model development influences the predicting accuracy of PM2.5 but has not been widely discussed. Therefore, we included modeling data with multiple time windows to identify optimized modeling time windows for capturing the long-term variation of PM2.5 in China during 2005–2019. In general, we incorporated PM2.5 measurements, aerosol optical depth (AOD), meteorological parameters, land use data, and other predictors to train random forest models. The study period was separated into two phases (2013–2019 and 2005–2012) according to the availability of PM2.5 measurements. First, we trained models with two strategies of choosing time windows to compare model performance in predicting PM2.5 from 2013 to 2019, when measurements were available. Strategy 1a (ST1a) refers to training one model with all available data, and Strategy 1b (ST1b) refers to training multiple models each with one-year data. Second, we trained models with additional ten strategies (ST2a-ST2j) based on data from different time windows during 2013–2019 to compare the accuracy in predicting PM2.5 before 2013, when measurements were unavailable. The internal and external cross-validation (CV) indicated that the model performance of ST1b was better than ST1a. Predictions based on ST1a tended to underestimate PM2.5 levels in 2013 and 2014 when PM2.5 concentrations were high, and overestimate after 2017 when PM2.5 dropped dramatically. The external CV of predicting historical PM2.5 was the most robust in ST2i (averaged predictions from two models developed by 2013 and 2014 data, respectively). Models with data closer to historical years and PM2.5 levels performed better in predicting historical PM2.5 concentrations. Our results suggested that training models with data of current-years performed better during 2013–2019, and with data of 2013 and 2014 performed better in predicting historical PM2.5 before 2013 in China. The comparison provided evidence for choosing optimized time windows when predicting long-term PM2.5 concentrations in China.