Improving air quality assessment using physics-inspired deep graph learning
文献类型:期刊论文
作者 | Li, Lianfa5,6; Wang, Jinfeng6; Franklin, Meredith4,5; Yin, Qian6; Wu, Jiajie6; Camps-Valls, Gustau3; Zhu, Zhiping6; Wang, Chengyi2; Ge, Yong6; Reichstein, Markus1 |
刊名 | NPJ CLIMATE AND ATMOSPHERIC SCIENCE |
出版日期 | 2023-09-27 |
卷号 | 6期号:1页码:13 |
ISSN号 | 2397-3722 |
DOI | 10.1038/s41612-023-00475-3 |
通讯作者 | Li, Lianfa(lspatial@gmail.com) ; Wang, Jinfeng(wangjf@lreis.ac.cn) |
英文摘要 | Existing methods for fine-scale air quality assessment have significant gaps in their reliability. Purely data-driven methods lack any physically-based mechanisms to simulate the interactive process of air pollution, potentially leading to physically inconsistent or implausible results. Here, we report a hybrid multilevel graph neural network that encodes fluid physics to capture spatial and temporal dynamic characteristics of air pollutants. On a multi-air pollutant test in China, our method consistently improved extrapolation accuracy by an average of 11-22% compared to several baseline machine learning methods, and generated physically consistent spatiotemporal trends of air pollutants at fine spatial and temporal scales. |
WOS关键词 | OZONE POLLUTION ; CHINA ; REGRESSION ; CHEMISTRY ; NETWORKS ; FRAMEWORK ; PM2.5 |
资助项目 | This research was funded by the National Natural Science Foundation of China grant (42071369), Key Project of Innovation LREIS (KP1004, 05Z5006JYA), the National Key Research and Development Program of China grant (2021YFB3900501), and the Strategic Priori[42071369] ; National Natural Science Foundation of China[KP1004] ; National Natural Science Foundation of China[05Z5006JYA] ; Key Project of Innovation LREIS[2021YFB3900501] ; National Key Research and Development Program of China[XDA19040501] ; Strategic Priority Research Program of the Chinese Academy of Sciences ; NVIDIA Corporation |
WOS研究方向 | Meteorology & Atmospheric Sciences |
语种 | 英语 |
出版者 | NATURE PORTFOLIO |
WOS记录号 | WOS:001072596500001 |
资助机构 | This research was funded by the National Natural Science Foundation of China grant (42071369), Key Project of Innovation LREIS (KP1004, 05Z5006JYA), the National Key Research and Development Program of China grant (2021YFB3900501), and the Strategic Priori ; National Natural Science Foundation of China ; Key Project of Innovation LREIS ; National Key Research and Development Program of China ; Strategic Priority Research Program of the Chinese Academy of Sciences ; NVIDIA Corporation |
源URL | [http://ir.igsnrr.ac.cn/handle/311030/198084] |
专题 | 中国科学院地理科学与资源研究所 |
通讯作者 | Li, Lianfa; Wang, Jinfeng |
作者单位 | 1.Max Planck Inst Biogeochem, Jena, Germany 2.Chinese Acad Sci, Aerosp Informat Res Inst, Natl Engn Res Ctr Geomat, Beijing, Peoples R China 3.Univ Valencia, Image Proc Lab IPL, Valencia, Spain 4.Univ Toronto, Dept Stat Sci, Toronto, ON, Canada 5.Univ Southern Calif, Dept Prevent Med, Los Angeles, CA 90007 USA 6.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Li, Lianfa,Wang, Jinfeng,Franklin, Meredith,et al. Improving air quality assessment using physics-inspired deep graph learning[J]. NPJ CLIMATE AND ATMOSPHERIC SCIENCE,2023,6(1):13. |
APA | Li, Lianfa.,Wang, Jinfeng.,Franklin, Meredith.,Yin, Qian.,Wu, Jiajie.,...&Reichstein, Markus.(2023).Improving air quality assessment using physics-inspired deep graph learning.NPJ CLIMATE AND ATMOSPHERIC SCIENCE,6(1),13. |
MLA | Li, Lianfa,et al."Improving air quality assessment using physics-inspired deep graph learning".NPJ CLIMATE AND ATMOSPHERIC SCIENCE 6.1(2023):13. |
入库方式: OAI收割
来源:地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。