Potential for developing independent daytime/nighttime LUR models based on short-term mobile monitoring to improve model performance

Abstract

Land use regression model (LUR) is a widespread method for predicting air pollution exposure. Few studies have explored the performance of independently developed daytime/nighttime LUR models. In this study, fine particulate matter (PM 2.5 ), inhalable particulate matter (PM 10 ), and nitrogen dioxide (NO 2 ) concentrations were measured by mobile monitoring during non-heating and heating seasons in Taiyuan. Pollutant concentrations were higher in the nighttime than the daytime, and higher in the heating season than the non-heating season. Daytime/nighttime and full-day LUR models were developed and validated for each pollutant to examine variations in model performance. Adjusted coefficients of determination (adjusted R 2 ) for the LUR models ranged from 0.53e0.87 (PM 2.5 ), 0.53e0.85 (PM 10 ), and 0.33e0.67 (NO 2 ). The performance of the daytime/nighttime LUR models for PM 2.5 and PM 10 was better than that of the full-day models according to the results of model adjusted R 2 and validation R 2 . Consistent results were confirmed in the non-heating and heating seasons. Effectiveness of developing independent daytime/nighttime models for NO 2 to improve performance was limited. Surfaces based on the daytime/nighttime models revealed variations in concentrations and spatial distribution. In conclusion, the independent development of daytime/nighttime LUR models for PM 2.5 /PM 10 has the potential to replace full-day models for better model performance. The modeling strategy is consistent with the residential activity patterns and contributes to achieving reliable exposure predictions for PM 2.5 and PM 10 . Nighttime could be a critical exposure period, due to high pollutant concentrations.

High-resolution patterns and inequalities in ambient fine particle mass (PM2.5) and black carbon (BC) in the Greater Accra Metropolis, Ghana

“…Like PM 2.5 , length of major and secondary roads, indicating traffic emissions, were the most predictive variables for BC models. This is consistent with existing BC LUR literature across the globe ( Eeftens et al, 2012 ; Xu et al, 2021 ; Wang et al, 2014 ; Lee et al, 2015 ). Further, the number of bus stops in an area was positively associated with BC in the Harmattan model.…”

An Integrated Approach for Conducting long-term PM2.5 Exposure and Health Impact Assessments for Residents of a City-scale

“…The long-term data collected by AQMS offers advantages in characterizing temporal variations to the study area. With limited number of AQMS installed, the lack of spatial resolution is clearly a drawback (Xu et al, 2021;Ho et al, 2022). Alternatively, techniques that combine satellite-derived AOD data or LUR model predicting data with AQMS data (denoted as AQMS + satellite-derived AOD or AQMS + LUR) provide potential solutions to address the spatial scarcity issue associated with AQMS (WHO, 2023).…”

“…The above limitations are also applied to the AQMS + satellite-derived AOD approach. For the AQMS + LUR approach, it has demonstrated its ability to characterize the spatiotemporal heterogeneity of PM2.5 concentrations (Vlaanderen et al, 2019;Xu et al, 2021). More recently, the LUR approach has been enhanced through the integration with machine learning techniques (denoted as the Hybrid Kriging-LUR model; h_LUR) (Wu et al, 2018;Wong et al, 2021;Thongthammachart et al, 2022).…”

“…Considering the inherent spatial and temporal variations in residents' exposure to PM2.5, it is essential to develop suitable methodologies for conducting EA, particularly focusing on ground-level long-term PM2.5 concentrations. Many studies have indicated that the approach combining the data obtained from the MMS, AQMS, and LUR (i.e., MMS + AQMS + LUR) would be a promising EA approach for addressing spatial and temporal variations at the ground level (Hankey and Marshall, 2015a;Dröge et al, 2018;Piotrowicz and Polednik, 2019;Xu et al, 2021).…”

Development of Spatio-Temporal Land Use Regression Models for Fine Particulate Matter and Wood-Burning Tracers in Temuco, Chile

“…In environmental epidemiology, land use regression (LUR) models have been widely employed to visualize the geographical distribution of pollution concentrations and estimate long-term exposures to pollutants. − These models have been developed to predict the long-term spatial variation of air pollutants and, more recently, have been adapted for shorter time scales. Some studies have highlighted the importance of including a temporal variation term in the LUR models to predict with higher temporal resolution, such as weeks or days. − LUR models have been extensively used for predicting air pollution exposures in urban settings in Europe, − North America, − and Asia, − urban environments that are mostly dominated by traffic emissions and where models are able to predict air pollution concentrations at unmeasured sites given a satisfactorily evaluated model …”