scholarly journals Machine Learning-Based Integration of High-Resolution Wildfire Smoke Simulations and Observations for Regional Health Impact Assessment

Author(s):  
Yufei Zou ◽  
Susan M. O’Neill ◽  
Narasimhan K. Larkin ◽  
Ernesto C. Alvarado ◽  
Robert Solomon ◽  
...  

Large wildfires are an increasing threat to the western U.S. In the 2017 fire season, extensive wildfires occurred across the Pacific Northwest (PNW). To evaluate public health impacts of wildfire smoke, we integrated numerical simulations and observations for regional fire events during August-September of 2017. A one-way coupled Weather Research and Forecasting and Community Multiscale Air Quality modeling system was used to simulate fire smoke transport and dispersion. To reduce modeling bias in fine particulate matter (PM2.5) and to optimize smoke exposure estimates, we integrated modeling results with the high-resolution Multi-Angle Implementation of Atmospheric Correction satellite aerosol optical depth and the U.S. Environmental Protection Agency AirNow ground-level monitoring PM2.5 concentrations. Three machine learning-based data fusion algorithms were applied: An ordinary multi-linear regression method, a generalized boosting method, and a random forest (RF) method. 10-Fold cross-validation found improved surface PM2.5 estimation after data integration and bias correction, especially with the RF method. Lastly, to assess transient health effects of fire smoke, we applied the optimized high-resolution PM2.5 exposure estimate in a short-term exposure-response function. Total estimated regional mortality attributable to PM2.5 exposure during the smoke episode was 183 (95% confidence interval: 0, 432), with 85% of the PM2.5 pollution and 95% of the consequent multiple-cause mortality contributed by fire emissions. This application demonstrates both the profound health impacts of fire smoke over the PNW and the need for a high-performance fire smoke forecasting and reanalysis system to reduce public health risks of smoke hazards in fire-prone regions.

2021 ◽  
Vol 9 ◽  
Author(s):  
Gilliane Davison ◽  
Karoline K. Barkjohn ◽  
Gayle S. W. Hagler ◽  
Amara L. Holder ◽  
Sarah Coefield ◽  
...  

Effective strategies to reduce indoor air pollutant concentrations during wildfire smoke events are critically needed. Worldwide, communities in areas prone to wildfires may suffer from annual smoke exposure events lasting from days to weeks. In addition, there are many areas of the world where high pollution events are common and where methods employed to reduce exposure to pollution may have relevance to wildfire smoke pollution episodes and vice versa. This article summarizes a recent virtual meeting held by the United States Environmental Protection Agency (EPA) to share research, experiences, and other information that can inform best practices for creating clean air spaces during wildland fire smoke events. The meeting included presentations on the public health impacts of wildland fire smoke; public health agencies' experiences and resilience efforts; and methods to improve indoor air quality, including the effectiveness of air filtration methods [e.g., building heating ventilation and air conditioning (HVAC) systems and portable, free-standing air filtration systems]. These presentations and related research indicate that filtration has been demonstrated to effectively improve indoor air quality during high ambient air pollution events; however, several research questions remain regarding the longevity and maintenance of filtration equipment during and after smoke events, effects on the pollution mixture, and degree to which adverse health effects are reduced.


2021 ◽  
Author(s):  
Minsu Kim ◽  
Gerrit Kuhlmann ◽  
Lukas Emmenegger ◽  
Dominik Brunner

<p>Nitrogen oxides (NO<sub>x  </sub>= NO<sub></sub>+ NO<sub>2</sub>) are harmful to human health and are precursors of other key air pollutants like ozone (O<sub>3</sub>) and particulate matter (PM). Since the lifetime of NO<sub>x</sub> is short and its main sources are anthropogenic emissions like fuel combustion from traffic and industry, near-surface NO<sub>x </sub>concentrations are highly variable in space and time. To assess the impact of NO<sub>2 </sub>on public health, maps of high spatial and temporal resolution are critical. In this study, we present hourly near-surface NO<sub>2</sub> concentrations at 100 m resolution for Switzerland and northern Italy that are produced using machine learning, specifically an extreme gradient-boosted tree ensemble. The model was trained with <em>in situ </em>observations from European Air Quality e-Reporting data repositories (Airbase). Satellite NO<sub>2</sub> observations from the TROPospheric Monitoring Instrument (TROPOMI) were compiled together with land use data, meteorological data and topography as covariates. Evaluation against <em>in situ</em> observations not used for the training shows that the dynamic maps produced in this study reproduce the spatio-temporal variation in near-surface NO<sub>2</sub> concentrations with high accuracy (R<sup>2</sup> = 0.59, MAE = 7.69 µg/m<sup>3</sup>). In addition, we demonstrate how public health studies can utilize such high-resolution maps for unbiased assessment of population exposure that can account for home addresses and mobility of individuals. Comparing the relative importance of the different covariates based on two different metrics, total information gain and averaged local feature importance, show a leading contribution of the TROPOMI observations despite their rather coarse resolution (3.5 km × 5.5 km) and daily update. TROPOMI NO<sub>2 </sub>observations were particularly important for the quality of the NO<sub>2</sub> maps during periods of unusual NO<sub>2 </sub>reductions (e.g., during COVID19 lockdown) and when detailed emission-related covariates like traffic density, that may not be available in other regions of the globe, were not included in the model. Since all data used in our study are publicly available, our approach can be readily extended to other regions in Europe or applied worldwide.</p>


Atmosphere ◽  
2020 ◽  
Vol 11 (9) ◽  
pp. 941
Author(s):  
Fengjun Zhao ◽  
Yongqiang Liu ◽  
Lifu Shu ◽  
Qi Zhang

The air quality and human health impacts of wildfires depend on fire, meteorology, and demography. These properties vary substantially from one region to another in China. This study compared smoke from more than a dozen wildfires in Northeast, North, and Southwest China to understand the regional differences in smoke transport and the air quality and human health impacts. Smoke was simulated using the Hybrid Single Particle Lagrangian Integrated Trajectory Model (HYSPLIT) with fire emissions obtained from the Global Fire Emission Database (GFED). Although the simulated PM2.5 concentrations reached unhealthy or more severe levels at regional scale for some largest fires in Northeast China, smoke from only one fire was transported to densely populated areas (population density greater than 100 people/km2). In comparison, the PM2.5 concentrations reached unhealthy level in local densely populated areas for a few fires in North and Southwest China, though they were very low at regional scale. Thus, individual fires with very large sizes in Northeast China had a large amount of emissions but with a small chance to affect air quality in densely populated areas, while those in North and Southwest China had a small amount of emissions but with a certain chance to affect local densely populated areas. The results suggest that the fire and air quality management should focus on the regional air quality and human health impacts of very large fires under southward/southeastward winds toward densely populated areas in Northeast China and local air pollution near fire sites in North and Southwest China.


2018 ◽  
Vol 2018 (1) ◽  
Author(s):  
Kathleen Elizabeth McLean ◽  
Kathryn T Morrison ◽  
Jiayun Angela Yao ◽  
Gavin Shaddick ◽  
David L Buckeridge ◽  
...  

Author(s):  
Kunal Parikh ◽  
Tanvi Makadia ◽  
Harshil Patel

Dengue is unquestionably one of the biggest health concerns in India and for many other developing countries. Unfortunately, many people have lost their lives because of it. Every year, approximately 390 million dengue infections occur around the world among which 500,000 people are seriously infected and 25,000 people have died annually. Many factors could cause dengue such as temperature, humidity, precipitation, inadequate public health, and many others. In this paper, we are proposing a method to perform predictive analytics on dengue’s dataset using KNN: a machine-learning algorithm. This analysis would help in the prediction of future cases and we could save the lives of many.


Author(s):  
Patrick Amoatey ◽  
Azizallah Izady ◽  
Ali Al-Maktoumi ◽  
Mingjie Chen ◽  
Issa Al-Harthy ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document