Knowledge-informed deep learning to mitigate bias in joint air pollutant prediction
文献类型：期刊论文
| 作者 | Li, Lianfa1,2; Khalili, Roxana1; Lurmann, Frederick6; Pavlovic, Nathan6; Wu, Jun7; Xu, Yan1; Liu, Yisi1; O'Sharkey, Karl1; Ritz, Beate8; Oman, Luke4 |
| 刊名 | ENVIRONMENT INTERNATIONAL
 |
| 出版日期 | 2025-12-01 |
| 卷号 | 206页码:109915 |
| 关键词 | Deep learning Physics-informed modeling Air pollution Knowledge fusion Bias mitigation Joint prediction |
| ISSN号 | 0160-4120 |
| DOI | 10.1016/j.envint.2025.109915 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Accurate prediction of atmospheric air pollutants is critical for public health protection and environmental management. Traditional machine learning (ML) methods achieve high spatial resolution but lack physicochemical constraints, leading to systematic biases that compromise exposure estimates for epidemiological studies. Chemical transport models incorporate atmospheric physics but require expensive parameterization and often fail to capture local-scale variability crucial for health impact assessment. This gap between data-driven accuracy and physical realism presents a major obstacle to advancing air quality science. We address this challenge through a novel physics-informed deep learning framework that integrates advection-diffusion equations and fluid dynamics constraints directly into neural network architectures for multi-pollutant prediction. Our approach models air pollutant pairs across geographically distinct domains (NO2/NOx for California; PM2.5/PM10 for mainland China), providing a comprehensive framework for physics-constrained atmospheric modeling at high resolution. Through an efficient framework, our methodology demonstrates that incorporating proxy advection and diffusion fields as physical constraints fundamentally alters learning dynamics, reducing generalization error and eliminating systematic bias inherent in data-driven approaches while improving computational efficiency compared to graph networks. Site-based validation reveals unprecedented bias reduction: 21%-42% for nitrogen oxides and 16%-17% for particulate matter compared to the baseline deep learning methods. Our methodology uniquely generates physically interpretable parameters while providing explicit uncertainty quantification through ensemble techniques. The substantial bias reduction coupled with physically interpretable parameters has immediate implications for improving air pollutant exposure assessment and understanding in epidemiological research, potentially transforming health effect evaluations that rely on accurate spatial predictions. |
| URL标识 | 查看原文 |
| WOS关键词 | NITROGEN-DIOXIDE ; NO2 CONCENTRATION ; RESOLUTION ; CHINA ; PM2.5 ; REGRESSION ; NETWORKS ; ERROR |
| WOS研究方向 | Environmental Sciences & Ecology |
| 语种 | 英语 |
| WOS记录号 | WOS:001625199400001 |
| 出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/219531]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Li, Lianfa |
| 作者单位 | 1.Univ Southern Calif, Dept Populat & Publ Hlth Sci, 1845 N Soto St, Los Angeles, CA 90032 USA; 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, A11 Datun Rd, Beijing 100101, Peoples R China; 3.Univ Southern Calif, Spatial Sci Inst, Los Angeles, CA 90089 USA 4.NASA, Goddard Space Flight Ctr, Greenbelt, MD 20771 USA; 5.Univ Toronto, Dept Stat Sci, Toronto, ON M5S 3G3, Canada; 6.Sonoma Technol Inc, 1450 N McDowell Blvd,Suite 200, Petaluma, CA 94954 USA; 7.Univ Calif Irvine, Program Publ Hlth, Susan & Henry Samueli Coll Hlth Sci, Irvine, CA 92697 USA; 8.Univ Calif Los Angeles, Fielding Sch Publ Hlth, Dept Epidemiol & Environm Hlth, Los Angeles, CA 90095 USA; |
| 推荐引用方式 GB/T 7714 | Li, Lianfa,Khalili, Roxana,Lurmann, Frederick,et al. Knowledge-informed deep learning to mitigate bias in joint air pollutant prediction[J]. ENVIRONMENT INTERNATIONAL,2025,206:109915. |
| APA | Li, Lianfa.,Khalili, Roxana.,Lurmann, Frederick.,Pavlovic, Nathan.,Wu, Jun.,...&Habre, Rima.(2025).Knowledge-informed deep learning to mitigate bias in joint air pollutant prediction.ENVIRONMENT INTERNATIONAL,206,109915. |
| MLA | Li, Lianfa,et al."Knowledge-informed deep learning to mitigate bias in joint air pollutant prediction".ENVIRONMENT INTERNATIONAL 206(2025):109915. |
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。