Fusing physics and AI enhances accuracy and diagnostic capabilities in air quality forecasting
Huangjian Wu, Zifa Wang, Yuanhang Zhang, Wei Lin, Xinwei Li, Meng Gao, Hao Sun, Dawei Zhang, Wei Wang, Xiao Tang, Jiang Zhu, Yu Song, Chaoqun Ma, Pingqing Fu, Hang Su, Yafang Cheng, Gregory R Carmichael · 2026
Read Fusing physics and AI enhances accuracy and diagnostic capabilities in air quality forecasting by Huangjian Wu, Zifa Wang, Yuanhang Zhang, Wei Lin, Xinwei Li, Meng Gao, Hao Sun, Dawei Zhang, Wei Wang, Xiao Tang, Jiang Zhu, Yu Song, Chaoqun Ma, Pingqing Fu, Hang Su, Yafang Cheng, Gregory R Carmichael (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13678820.txt.
Description
Huangjian Wu and co-authors fuse physics based models with artificial intelligence to forecast air quality across China. Published in 2026, their system, ProNet, places trainable neural correctors inside the equations of a chemical transport model, rather than bolting AI on afterward. Pure physics models carry uncertain settings, while AI alone loses the ability to explain itself.
On data from 2022 and 2023 across 338 Chinese cities, ProNet beat both physics only and AI only rivals. It also beat forecaster adjusted operational forecasts for fine particle and ozone levels. The system keeps an error ledger that ties mistakes to place and time. That ledger exposed steady biases in current models and points to fixes.
Catalog record
| CREATOR | Huangjian Wu, Zifa Wang, Yuanhang Zhang, Wei Lin, Xinwei Li, Meng Gao, Hao Sun, Dawei Zhang, Wei Wang, Xiao Tang, Jiang Zhu, Yu Song, Chaoqun Ma, Pingqing Fu, Hang Su, Yafang Cheng, Gregory R Carmichael |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |