气候变化领域集成服务门户(CCPortal): Bias correcting and extending the PM forecast by CMAQ up to 7 days using deep convolutional neural networks

CCPortal

DOI	10.1016/j.atmosenv.2021.118376
	Bias correcting and extending the PM forecast by CMAQ up to 7 days using deep convolutional neural networks
	Sayeed A.; Lops Y.; Choi Y.; Jung J.; Salman A.K.
发表日期	2021
ISSN	1352-2310
卷号	253
英文摘要	With rising levels of air-pollution, air-quality forecasting has become integral to the dissemination of human health advisories and the preparation of mitigation strategies. To achieve more accurate forecasts, researchers around the globe are developing mathematical modeling techniques to obtain more accurate forecasts. In this study, we explore the capabilities of a deep neural network (DNN) model in conjunction with conventional, more reliable chemical transport models i) to improve the performance of the chemical transport model (e.g., CMAQ) and; ii) to extend the forecast period to seven days. Using a generalized deep convolutional neural network (CNN) model, we forecast air pollutants such as PM2.5, PM10, and NO2 up to seven days in advance. The CNN model bias-corrects hourly concentrations of air pollutants from the CMAQ model on the first-day and forecasts the remaining six days. Our results show improved performance of the average yearly index of agreement (IOA) from the CMAQ to the CNN model by 13% for PM2.5, 22% for PM10, and 43% for NO2 for the first-day bias correction; and the seventh-day forecast of NO2 by the CNN model was more accurate than the first-day forecast of the CMAQ model. The forecasts for PM2.5 and PM10, however, are reliable only up to two days in advance. The trained model is also capable of forecasting pollutants at stations not included in the training. The increase in the average yearly IOA at such stations is 13% for PM2.5, 22% for PM10, and 40% for NO2. Although the CNN model enhances the performance of the CMAQ model, it can be further improved by adding remote sensing data. © 2021 Elsevier Ltd
关键词	Air-quality Artificial intelligence CNN NO2 Particulate matter PM
语种	英语
scopus关键词	Air quality; Convolution; Convolutional neural networks; Deep neural networks; Nitrogen oxides; Particles (particulate matter); Remote sensing; Air pollutants; Chemical transport models; Convolutional neural network; Neural network modelling; NO $-2$; Particulate Matter; Performance; PM; PM$-10$; PM$-2.5$; Forecasting; carbon monoxide; nitrogen dioxide; ozone; sulfur dioxide; air quality; artificial neural network; atmospheric pollution; atmospheric transport; forecasting method; mitigation; numerical model; particulate matter; pollutant transport; remote sensing; strategic approach; air pollution; air quality; Article; convolutional neural network; deep neural network; forecasting; particulate matter 10; particulate matter 2.5; pollution transport; priority journal; remote sensing
来源期刊	ATMOSPHERIC ENVIRONMENT
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/248496
作者单位	Department of Earth and Atmospheric Sciences, University of HoustonTX 77004, United States
推荐引用方式 GB/T 7714	Sayeed A.,Lops Y.,Choi Y.,et al. Bias correcting and extending the PM forecast by CMAQ up to 7 days using deep convolutional neural networks[J],2021,253.
APA	Sayeed A.,Lops Y.,Choi Y.,Jung J.,&Salman A.K..(2021).Bias correcting and extending the PM forecast by CMAQ up to 7 days using deep convolutional neural networks.ATMOSPHERIC ENVIRONMENT,253.
MLA	Sayeed A.,et al."Bias correcting and extending the PM forecast by CMAQ up to 7 days using deep convolutional neural networks".ATMOSPHERIC ENVIRONMENT 253(2021).