Background Accurately assessing individual ambient air pollution exposure is a crucial part of epidemiological studies looking at the adverse health effect of poor air quality. This is particularly challenging in developing countries with high levels of air pollution but having sparse monitoring networks with a lack of consistent data. Methods We evaluated the performance of 6 different machine learning algorithms in predicting fine particulate matter (PM 2.5 ) concentrations in Ulaanbaatar, Mongolia from 2010 to 2018. We found that the algorithms produce robust results based on performance metrics. Results Random forest (RF) and gradient boosting models performed the best with leave-one-location-out cross-validated R 2 of 0.82 for when using data from the entire study period. After applying tuned models on the hold-out test set, R 2 increased to 0.96 for the RF and 0.90 for the gradient boosting model. We also predicted PM 2.5 concentrations for each administrative area (khoroo) of the city using RF and maps of predictions show spatiotemporal variations that are in line with the location of the ger district, city center, and population density. Conclusion Our results provide evidence of the advantage and feasibility of machine learning approaches in predicting ambient PM 2.5 levels in a setting with limited resources and extreme air pollution levels.
Background: Asthma is a heterogeneous disease, usually characterized by chronic airway inflammation. The air quality is influenced by locations of the air pollution sources, their performance capacity, the technology used, the composition of waste generated and geographical and climate conditions. In this study, a time-series analysis was conducted to estimate the association of short-term exposure to ambient air pollutants and hospitalization due to asthma in Ulaanbaatar. Objectives: We estimate the short-term associations between daily changes in ambient air pollutants and daily asthma in Ulaanbaatar, Mongolia. Methods: This is a time-series cross over study. All asthma hospital admission and air pollution data of 2008-2017 was used for this assessment. Data analyzed by using the program STATA-12. For testing the differences of the results were used appropriate non-parametric tests. Result: The daily mean of sulfur dioxide concentration was 35.22 mg/m 3 in the cold season, which was 7.57 times higher than the mean of the hot season. The mean annual PM 10 concentration was 182.73 μg/m 3. Most of the cases of asthma were among women, aged between 5-64 years old, registered during winter and spring. 3.8 people admitted to the hospital mostly on weekdays. In all Lag of SO 2 , in Lag of NO 2 , in all Lag of PM 10, in PM 2.5 and in all Lag except for Lag 2 of CO, Lag 0-2 of O 3 the incidence is likely to increase by 0.3%-6.1% per 10 units of pollutants. Conclusion: The air pollution especially PM 10, PM 2.5, and CO are the most harmful air pollutants to asthma in Ulaanbaatar. The correlation mainly between asthma admission cases with meteorological parameters is because of the cold winter condition.
Background: Mongolia is situated in northern Central Asia. Landlocked between China and Russia, it is a vast expanse of high attitude grassland steppe, desert, and mountain covering an area of 1,565,000 square kilometers. Air pollution is an increasingly series problem in Mongolia. Materials and Methods: This is a time-series cross over study. All health and air pollution data of 2008-2017 was used for this survey. Results: The mean level of SO 2 during the cold season was 35.22 µg/m 3 and during the warm season it was 4.65 µg/m 3. 24 hours PM10 concentration, during the cold season daily average concentration was 226.77 µg/m 3. The 8 hours average daily carbon monoxide concentration (1352.85 µg/m 3 [95% CI: 1313.07-1396.15]) was high during the cold season, ozone concentration (39.10 µg/m 3 [95% CI: 37.95-40.35]) was high during the warm season. Air quality depends on metrological parameters. All correlation was statistically significant during the whole year and cold season. In total, 288,832 people get admitted to the hospital due to cardiovascular system disease in Ulaanbaatar during the year of 2008-2017. In general, hospitalization is increasing year by year. Significant associations were found for SO 2 with hypertensive diseases (I10-I15), ischemic heart diseases (I20-I25), cerebrovascular diseases (I60-I69), diseases of pulmonary circulation and other forms of heart (I00-I09, I26-I52) in all lags. For NO 2 was less associated with Ischemic heart diseases (I20-I25) and diseases of pulmonary circulation and other forms of heart (I00-I09, I26-I52).
The study aims to reveal the impact of three sequential strict-lockdowns of COVID-19 measures on the air pollutants including NO2, SO2, PM10, and PM2.5 in Ulaanbaatar, Mongolia during November 2020 -February 2021 based on air quality network and satellite data. Based on measurements of automatic air quality sites in Ulaanbaatar, we found a substantial decrease in NO2 (up to 45%), PM10 (72%), and PM2.5 (59%) compared to the same periods in the previous five years. On the other hand, up to a threefold increase in SO2 concentration was seen. Compared to 2015-2020, the number of days exceeding the national air quality standard level of NO2 decreased by 55% during November 2020 -February 2021. A similar trend was observed for PM10 and PM2.5 (30% and 14%, respectively). Conversely, days exceeding the national air quality standard level of SO2 increased by 58%. The third strict-lockdown exhibited significant reductions in pollutant concentrations. The percentage exceeding the national standard level for NO2, PM10, and PM2.5 constituted 23%, 50%, and 67% during the lockdown periods while it was 89%, 84%, and 91%, respectively, for the same periods in the previous five years. Even though Sentinel 5P-TROPOMI data do not fully reflect the above findings, they add valuable insights into the spatial pollution pattern during strict-lockdown and non-lockdown periods. The study demonstrates that measures taken during the strict-lockdown periods clearly influenced the values of daily patterns of NO2, PM10, and PM2.5 concentrations. On the contrary, it is important to note that SO2 concentration increased during the last two winter months after 2019.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.