A Geo-AI-based ensemble mixed spatial prediction model with fine spatial-temporal resolution for estimating daytime/nighttime/daily average ozone concentrations variations in Taiwan.

High levels of ground level ozone (O3) are associated with detrimental health concerns. Most of the studies only focused on daily average and daytime trends due to the presence of sunlight that initiates its formation. However, atmospheric chemical reactions occur all day, thus, nighttime concentrations should be given equal importance. In this study, geospatial-artificial intelligence (Geo-AI) which combined kriging, land use regression (LUR), machine learning, an ensemble learning, was applied to develop ensemble mixed spatial models (EMSMs) for daily, daytime, and nighttime periods. These models were used to estimate the long-term O3 spatio-temporal variations using a two-decade worth of in-situ measurements, meteorological parameters, geospatial predictors, and social and season-dependent factors. From the traditional LUR approach, the performance of EMSMs improved by 60% (daytime), 49% (nighttime), and 57% (daily). The resulting daily, daytime, and nighttime EMSMs had a high explanatory power with and adjusted R2 of 0.91, 0.91, and 0.88, respectively. Estimation maps were produced to examine the changes before and during the implementation of nationwide COVID-19 restrictions. These results provide accurate estimates and its diurnal variation that will support pollution control measure and epidemiological studies.

Incidence and Risk of Fatal Vehicle Crashes Among Professional Drivers: A Population-Based Study in Taiwan.

Fatal vehicle crashes (FVCs) are among the leading causes of death worldwide. Professional drivers often drive under dangerous conditions; however, knowledge of the risk factors for FVCs among professional drivers remain scant. We investigated whether professional drivers have a higher risk of FVCs than non-professional drivers and sought to clarify potential risk factors for FVCs among professional drivers. We analyzed nationwide incidence rates of FVCs as preliminary data. Furthermore, by using these data, we created a 1:4 professionals/non-professionals preliminary study to compare with the risk factors between professional and non-professional drivers. In Taiwan, the average crude incidence rate of FVCs for 2003-2016 among professional drivers was 1.09 per 1,000 person-years; professional drivers had a higher percentage of FVCs than non-professional drivers among all motor vehicle crashes. In the 14-year preliminary study with frequency-matched non-professional drivers, the risk of FVCs among professional drivers was significantly associated with a previous history of involvement in motor vehicle crashes (adjustment odds ratio [OR] = 2.157; 95% confidence interval [CI], 1.896-2.453), previous history of benzodiazepine use (adjustment OR = 1.385; 95% CI, 1.215-1.579), and speeding (adjustment OR = 1.009; 95% CI, 1.006-1.013). The findings have value to policymakers seeking to curtail FVCs.