Influence of weather and air pollution on concentration change of PM2.5 using a generalized additive model and gradient boosting machine

2021 ◽  
pp. 118437
Author(s):  
Bowen Cheng ◽  
Yuxia Ma ◽  
Fengliu Feng ◽  
Yifan Zhang ◽  
Jiahui Shen ◽  
...  
Keyword(s):  
Air Pollution ◽  
Generalized Additive Model ◽  
Additive Model ◽  
Gradient Boosting ◽  
Concentration Change ◽  
Gradient Boosting Machine

scholarly journals Himawari-8-derived diurnal variations of ground-level PM<sub>2.5</sub> pollution across China using a fast space-time Light Gradient Boosting Machine

2021 ◽  
Author(s):  
Jing Wei ◽  
Zhanqing Li ◽  
Rachel T. Pinker ◽  
Lin Sun ◽  
Wenhao Xue ◽  
...  
Keyword(s):  
Air Pollution ◽  
Space Time ◽  
Diurnal Variations ◽  
Pollution Monitoring ◽  
Anthropogenic Factors ◽  
Gradient Boosting ◽  
Statistical Regression ◽  
Data Set ◽  
Light Gradient ◽  
Gradient Boosting Machine

Abstract. PM2.5 has been used as an important atmospheric environmental parameter primarily due to its impact on human health. PM2.5 is affected by both natural and anthropogenic factors that usually have strong diurnal variations. Monitoring it does not only help understand the causes of air pollution but also our adaptation to it. Most existing PM2.5 products have been derived from polar-orbiting satellites. This study exploits the usage of the next-generation geostationary meteorological satellite Himawari-8/AHI in revealing its diurnal variations. Given the huge volume of the satellite data, a highly efficient tree-based Light Gradient Boosting Machine (LightGBM) learning approach, which is based on the idea of gradient boosting, is applied by involving the spatiotemporal characteristics of air pollution, named the space-time LightGBM (STLG) model. Hourly PM2.5 data set in China (i.e., ChinaHighPM2.5) at a 5 km spatial resolution is derived based on the Himawari-8/AHI aerosol products together with other variables. The hourly PM2.5 estimates (N = 1,415,188) are well correlated with ground measurements (R2 = 0.85) with a RMSE and MAE of 13.62 and 8.49 μg/m3 respectively in China. Our model can capture well the PM2.5 diurnal variations, where the pollution increases gradually in the morning, and reaches a peak at about 10:00 a.m. local time, then decreases steadily until sunset. The proposed approach outperforms most traditional statistical regression and tree-based machine learning models with a much lower computation burden in terms of speed and memory, making it most suitable for routine pollution monitoring.

scholarly journals Exploring bias in a generalized additive model for spatial air pollution data.

2003 ◽  
Vol 111 (10) ◽  
pp. 1283-1288 ◽  
Author(s):  
Timothy Ramsay ◽  
Richard Burnett ◽  
Daniel Krewski
Keyword(s):  
Air Pollution ◽  
Generalized Additive Model ◽  
Additive Model

scholarly journals Himawari-8-derived diurnal variations in ground-level PM<sub>2.5</sub> pollution across China using the fast space-time Light Gradient Boosting Machine (LightGBM)

2021 ◽  
Vol 21 (10) ◽  
pp. 7863-7880
Author(s):  
Jing Wei ◽  
Zhanqing Li ◽  
Rachel T. Pinker ◽  
Jun Wang ◽  
Lin Sun ◽  
...  
Keyword(s):  
Air Pollution ◽  
Space Time ◽  
Diurnal Variations ◽  
Pollution Monitoring ◽  
Coefficient Of Determination ◽  
Anthropogenic Factors ◽  
Gradient Boosting ◽  
Statistical Regression ◽  
Light Gradient ◽  
Gradient Boosting Machine

Abstract. Fine particulate matter with a diameter of less than 2.5 µm (PM2.5) has been used as an important atmospheric environmental parameter mainly because of its impact on human health. PM2.5 is affected by both natural and anthropogenic factors that usually have strong diurnal variations. Such information helps toward understanding the causes of air pollution, as well as our adaptation to it. Most existing PM2.5 products have been derived from polar-orbiting satellites. This study exploits the use of the next-generation geostationary meteorological satellite Himawari-8/AHI (Advanced Himawari Imager) to document the diurnal variation in PM2.5. Given the huge volume of satellite data, based on the idea of gradient boosting, a highly efficient tree-based Light Gradient Boosting Machine (LightGBM) method by involving the spatiotemporal characteristics of air pollution, namely the space-time LightGBM (STLG) model, is developed. An hourly PM2.5 dataset for China (i.e., ChinaHighPM2.5) at a 5 km spatial resolution is derived based on Himawari-8/AHI aerosol products with additional environmental variables. Hourly PM2.5 estimates (number of data samples = 1 415 188) are well correlated with ground measurements in China (cross-validation coefficient of determination, CV-R2 = 0.85), with a root-mean-square error (RMSE) and mean absolute error (MAE) of 13.62 and 8.49 µg m−3, respectively. Our model captures well the PM2.5 diurnal variations showing that pollution increases gradually in the morning, reaching a peak at about 10:00 LT (GMT+8), then decreases steadily until sunset. The proposed approach outperforms most traditional statistical regression and tree-based machine-learning models with a much lower computational burden in terms of speed and memory, making it most suitable for routine pollution monitoring.

Generalized Additive Model of Air Pollution to Daily Mortality

2005 ◽  
Vol 277-279 ◽  
pp. 487-491
Author(s):  
Jae Hee Kim ◽  
Hee Eun Yang
Keyword(s):  
Cardiovascular Disease ◽  
Air Pollution ◽  
Wind Speed ◽  
Generalized Additive Model ◽  
Generalized Additive Models ◽  
Additive Model ◽  
Additive Models ◽  
Daily Mortality ◽  
Pollution Levels ◽  
Poisson Models

The association of air pollution with daily mortality due to cardiovascular disease, respiratory disease, and old age (65 or older) in Seoul, Korea was investigated in 1999 using daily values of TSP, PM10, O3, SO2, NO2, and CO. Generalized additive Poisson models were applied to allow for the highly flexible fitting of daily trends in air pollution as well as nonlinear association with meteorological variables such as temperature, humidity, and wind speed. To estimate the effect of air pollution and weather on mortality, LOESS smoothing was used in generalized additive models. The findings suggest that air pollution levels affect significantly the daily mortality.

scholarly journals Alcohol Consumption, Poor Lifestyle Choices and Air Pollution Worsen Cognitive Function in Seniors: a Cohort Study in China

2021 ◽  
Author(s):  
Lizhen Han ◽  
Jinzhu Jia
Keyword(s):  
Air Pollution ◽  
Cognitive Function ◽  
Alcohol Consumption ◽  
Generalized Additive Model ◽  
Additive Model ◽  
Atmospheric Environment ◽  
Activity Participation ◽  
Daily Alcohol Consumption ◽  
Balanced Diet ◽  
Lifestyle Choices

Abstract Background: Based on the complexity of cognitive-related influences and the specificity of Chinese liquor culture, this study aimed to explore the associations and potential interactions between demographic characteristics, alcohol consumption, life and atmospheric environment and cognitive function in seniors through a comprehensive analysis, in order to provide evidence support and feasible recommendations.Methods: The study sample was selected from the Chinese Longitudinal Healthy Longevity Survey, which included 40,583 seniors aged 65-115 years. Data analysis and processing were performed by R 4.0.4. The relationship between the factors and cognition was modeled and analyzed by generalized additive model, and the interaction was explored by combining the ANOVA.Results: The generalized additive model confirmed that alcohol consumption was detrimental to the cognitive status of older adults, especially for liquor (≥ 38º) and beer. The higher the average daily alcohol consumption, the greater the impairment. SO2 and PM2.5 showed the same negative effects. In contrast, life environment factors such as good education, balanced diet and positive activity participation had a positive effect on cognition in seniors. In addition, interactions between alcohol consumption and average daily alcohol consumption, frequency of vegetable and meat intake, and between open-air activities and air pollution were also confirmed.Conclusions: Poor lifestyle choices such as alcohol consumption, unbalanced diet, lower activity participation, and air pollution deteriorate cognitive function in seniors. It is recommended that the elderly population should avoid alcohol consumption, maintain a balanced diet and be physically active. Attention should also be paid to the effects of air quality.

Sign in / Sign up

Export Citation Format

Share Document