Enhancing 72-Hour air quality forecasting with an observation-driven deep learning chemistry transport model
Real-time air quality forecasting with atmospheric chemistry transport models (CTMs) has long been hindered by the inaccessibility of in-time updates for crucial inputs (e.g., emissions) and chemical mechanism, posing a significant obstacle to designing effective control strategies for protecting hu...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-08-01
|
| Series: | Environment International |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0160412025004404 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849731379538952192 |
|---|---|
| author | Siwei Li Jia Xing |
| author_facet | Siwei Li Jia Xing |
| author_sort | Siwei Li |
| collection | DOAJ |
| description | Real-time air quality forecasting with atmospheric chemistry transport models (CTMs) has long been hindered by the inaccessibility of in-time updates for crucial inputs (e.g., emissions) and chemical mechanism, posing a significant obstacle to designing effective control strategies for protecting human health. Here we present a study that leveraging multiple observations combined with corresponding meteorological conditions to overcome these long-standing limitations in high-resolution air quality forecasting. Specifically, we developed a novel observation-driven deep learning-based atmospheric chemistry forecasting (DeepFC), which effectively integrates abundant near-real-time satellite and ground-based observations. Using a nine-year observation dataset (2013–2021) with CTM simulation training over a 27 km × 27 km resolution domain in China, DeepFC driven entirely by observations significantly improves the accuracy of traditional numerical models in forecasting the concentrations of two major pollutants, PM2.5 and O3, for the following 72 h across the country. Specifically, it enhances R2 from 0.2 to 0.6 and reduces RMSE by 50 % for PM2.5 and 20 % for O3, primarily due to the effective of fusing historical observation data and a more effective prediction strategy. Moreover, the newly developed observation-driven DeepFC provides deep insights into key factors for effective policy design, including source-receptor relationships, emission-response dynamics, and the separation of meteorology- and emission-driven variations. While consistent with traditional CTMs, DeepFC achieves these insights with significantly greater efficiency. These results highlight its strong potential in supporting global efforts to combat air pollution for better protection of human health and ecosystem. |
| format | Article |
| id | doaj-art-46c50b016a874104a8db59ee719e9b0b |
| institution | DOAJ |
| issn | 0160-4120 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Environment International |
| spelling | doaj-art-46c50b016a874104a8db59ee719e9b0b2025-08-20T03:08:33ZengElsevierEnvironment International0160-41202025-08-0120210968910.1016/j.envint.2025.109689Enhancing 72-Hour air quality forecasting with an observation-driven deep learning chemistry transport modelSiwei Li0Jia Xing1School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China; Perception and Effectiveness Assessment for Carbon-neutrality Efforts, Engineering Research Center of Ministry of Education, Institute for Carbon Neutrality, Wuhan University, Wuhan 430072, China; State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaDepartment of Civil and Environmental Engineering, the University of Tennessee, Knoxville, TN 37996, USA; Corresponding author.Real-time air quality forecasting with atmospheric chemistry transport models (CTMs) has long been hindered by the inaccessibility of in-time updates for crucial inputs (e.g., emissions) and chemical mechanism, posing a significant obstacle to designing effective control strategies for protecting human health. Here we present a study that leveraging multiple observations combined with corresponding meteorological conditions to overcome these long-standing limitations in high-resolution air quality forecasting. Specifically, we developed a novel observation-driven deep learning-based atmospheric chemistry forecasting (DeepFC), which effectively integrates abundant near-real-time satellite and ground-based observations. Using a nine-year observation dataset (2013–2021) with CTM simulation training over a 27 km × 27 km resolution domain in China, DeepFC driven entirely by observations significantly improves the accuracy of traditional numerical models in forecasting the concentrations of two major pollutants, PM2.5 and O3, for the following 72 h across the country. Specifically, it enhances R2 from 0.2 to 0.6 and reduces RMSE by 50 % for PM2.5 and 20 % for O3, primarily due to the effective of fusing historical observation data and a more effective prediction strategy. Moreover, the newly developed observation-driven DeepFC provides deep insights into key factors for effective policy design, including source-receptor relationships, emission-response dynamics, and the separation of meteorology- and emission-driven variations. While consistent with traditional CTMs, DeepFC achieves these insights with significantly greater efficiency. These results highlight its strong potential in supporting global efforts to combat air pollution for better protection of human health and ecosystem.http://www.sciencedirect.com/science/article/pii/S0160412025004404SatelliteDeep learningChemistry transport modelAir qualityForecast |
| spellingShingle | Siwei Li Jia Xing Enhancing 72-Hour air quality forecasting with an observation-driven deep learning chemistry transport model Environment International Satellite Deep learning Chemistry transport model Air quality Forecast |
| title | Enhancing 72-Hour air quality forecasting with an observation-driven deep learning chemistry transport model |
| title_full | Enhancing 72-Hour air quality forecasting with an observation-driven deep learning chemistry transport model |
| title_fullStr | Enhancing 72-Hour air quality forecasting with an observation-driven deep learning chemistry transport model |
| title_full_unstemmed | Enhancing 72-Hour air quality forecasting with an observation-driven deep learning chemistry transport model |
| title_short | Enhancing 72-Hour air quality forecasting with an observation-driven deep learning chemistry transport model |
| title_sort | enhancing 72 hour air quality forecasting with an observation driven deep learning chemistry transport model |
| topic | Satellite Deep learning Chemistry transport model Air quality Forecast |
| url | http://www.sciencedirect.com/science/article/pii/S0160412025004404 |
| work_keys_str_mv | AT siweili enhancing72hourairqualityforecastingwithanobservationdrivendeeplearningchemistrytransportmodel AT jiaxing enhancing72hourairqualityforecastingwithanobservationdrivendeeplearningchemistrytransportmodel |