TY - JOUR
T1 - Machine learning based bias correction for numerical chemical transport models
AU - Xu, Min
AU - Jin, Jianbing
AU - Wang, Guoqiang
AU - Segers, Arjo
AU - Deng, Tuo
AU - Lin, Hai Xiang
PY - 2021
Y1 - 2021
N2 - Air quality warning and forecasting systems are usually based on numerical chemical transport models (CTMs). Those dynamic models perform predictions by simulating the life cycles of the atmospheric components, including emission, transport and removal. However, the accuracy of these CTMs are still limited because of many imperfections, e.g., uncertainties in the input sources such as emission inventories, wind fields, boundary conditions, as well as insufficient knowledge about the atmospheric dynamics themselves. All these will mislead the CTM prediction constantly, or in a systematic way. In this paper, an approach based on machine learning is applied to predict model bias in the CTM. It is then combined with the CTM for formulating a hybrid forecast system. To our knowledge, it is the first time that machine learning methods are used in this way. The hybrid system is tested on the fine particular matter (PM2.5) prediction in Shanghai, China. The results showed that machine learning can be an effective tool to improve the accuracy of CTM prediction. In case of short term PM2.5 forecast (forecast length less than 12 h), statistical metrics of the root mean square error, mean absolute error, mean absolute percentage error as well as the air quality rank predicted accuracy all show the forecast skill is remarkably improved; while for long term prediction, improvement is not ensured.
AB - Air quality warning and forecasting systems are usually based on numerical chemical transport models (CTMs). Those dynamic models perform predictions by simulating the life cycles of the atmospheric components, including emission, transport and removal. However, the accuracy of these CTMs are still limited because of many imperfections, e.g., uncertainties in the input sources such as emission inventories, wind fields, boundary conditions, as well as insufficient knowledge about the atmospheric dynamics themselves. All these will mislead the CTM prediction constantly, or in a systematic way. In this paper, an approach based on machine learning is applied to predict model bias in the CTM. It is then combined with the CTM for formulating a hybrid forecast system. To our knowledge, it is the first time that machine learning methods are used in this way. The hybrid system is tested on the fine particular matter (PM2.5) prediction in Shanghai, China. The results showed that machine learning can be an effective tool to improve the accuracy of CTM prediction. In case of short term PM2.5 forecast (forecast length less than 12 h), statistical metrics of the root mean square error, mean absolute error, mean absolute percentage error as well as the air quality rank predicted accuracy all show the forecast skill is remarkably improved; while for long term prediction, improvement is not ensured.
KW - Air quality
KW - Neural network
KW - PM2.5
KW - Short term forecast
UR - http://www.scopus.com/inward/record.url?scp=85100066172&partnerID=8YFLogxK
U2 - 10.1016/j.atmosenv.2020.118022
DO - 10.1016/j.atmosenv.2020.118022
M3 - Article
AN - SCOPUS:85100066172
SN - 1352-2310
VL - 248
SP - 1
EP - 10
JO - Atmospheric Environment
JF - Atmospheric Environment
M1 - 118022
ER -