Assessing PM2.5 Exposures with High Spatiotemporal Resolution across the Continental United States
By Qian Di, I. Kloog, P. Koutrakis, Alexei I. Lyapustin, Yujie Wang, Jasmine Schwartz. Environmental Science and Technology, 2016
461 citations recorded by the source corpus.
A number of models have been developed to estimate PM2.5 exposure, including satellite-based aerosol optical depth (AOD) models, land-use regression or chemical transport model simulation, all with both strengths and weaknesses. Variables like normalized difference vegetation index (NDVI), surface reflectance, absorbing aerosol index and meteoroidal fields, are also informative about PM2.5 concentrations. Our objective is to establish a hybrid model which incorporates multiple approaches and input variables to improve model performance. To account for complex atmospheric mechanisms, we used a neural network for its capacity to model nonlinearity and interactions. We used convolutional layers, which aggregate neighboring information, into a neural network to account for spatial and temporal autocorrelation. We trained the neural network for the continental United States from 2000 to 2012 and tested it with left out monitors. Ten-fold cross-validation revealed a good model performance with total R2 of 0.84 on the left out monitors. Regional R2 could be even higher for the Eastern and Central United States. Model performance was still good at low PM2.5 concentrations. Then, we used the trained neural network to make daily prediction of PM2.5 at 1 km×1 km grid cells. This model allows epidemiologists to access PM2.5 exposure in both the short-term and the long-term.
Subfields: Atmospheric Science, Global and Planetary Change, Health, Toxicology and Mutagenesis
View Paper: https://www.semanticscholar.org/paper/d466c3f1163ad6d34dd1e80dd1559b1645c55c7e
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Atmospheric Science
- Huanfeng Shen
- Qiangqiang Yuan
- Francesca Dominici
- Qian Di
- Jasmine Schwartz
- Felix Creutzig
- Alexandre Lacoste
- Liangpei Zhang
In Global and Planetary Change
In Health, Toxicology and Mutagenesis
- A. Zanobetti
- Francesca Dominici
- Jasmine Schwartz
- Qian Di
- Christine Choirat
- Felix Creutzig
- Antonio Gasparrini
- Ben Armstrong
Citations in the corpus
- Association of Short-term Exposure to Air Pollution With Mortality in Older Adults (2017, methodology): “The robustness of the analysis results was assessed with respect to (1) choosing thedfused for the confounding adjustment for temperature, (2) using lag01-day exposure as the exposuremetric, (3) thedefinitionofwarmseason, and (4) using only air pollutionmeasurements from the nearest EPAmonitoring si”
- Air pollution and COVID-19 mortality in the United States: Strengths and limitations of an ecological regression analysis (2020, background): “5 at the county level Use of well-validated atmospheric chemistry models and machine learning models (9, 24) Aggregation assumes that everyone in a county experiences the same exposures, leading to exposure misclassification, especially for the largest counties Individual-level data on COVID-19 deat”
- Tackling Climate Change with Machine Learning (2019, background): “[665] Qian Di, Itai Kloog, Petros Koutrakis, Alexei Lyapustin, Yujie Wang, and Joel Schwartz.”
- Deep learning in environmental remote sensing: Achievements and challenges (2020, methodology): “Wu et al. (2012) later trained the BPNN model with Bayesian regularization for AOD-based PM 2.5 estimation, and a BPNN with convolutional layers was developed to consider spatiotemporal auto-correlation for the PM 2.5 estimation in the continental US (Di et al., 2016a).”