,

Lianfa Li1, Roxana Khalili2, Frederick Lurmann3

  • 1State Key Laboratory of Resources and Environmental Information System, Institute of Geographical Sciences and Natural Resources, Chinese Academy of Sciences, No. A11, Rd. Datun, Beijing, 100101, Beijing, China; Department of Population and Public Health Sciences, University of Southern California, 1845 N Soto St, Los Angeles, 90032, CA, USA.

Environment international
|November 19, 2025
PubMed
概括

一个新的以物理为基础的深度学习框架通过整合物理定律,准确预测空气污染物,减少氧化物偏差高达42%,颗粒物偏差高达17%.