Large-scale spatiotemporal deep learning predicting urban residential indoor PM2.5 concentration
文献类型:期刊论文
作者 | Dai, Hui1; Liu, Yumeng1; Wang, Jianghao3; Ren, Jun2; Gao, Yao2; Dong, Zhaomin4; Zhao, Bin1,5 |
刊名 | ENVIRONMENT INTERNATIONAL |
出版日期 | 2023-12-01 |
卷号 | 182页码:12 |
ISSN号 | 0160-4120 |
关键词 | Indoor PM 2.5 Bayesian neural network Low-cost sensor Human exposure Health effect |
DOI | 10.1016/j.envint.2023.108343 |
通讯作者 | Dong, Zhaomin(dongzm@buaa.edu.cn) ; Zhao, Bin(binzhao@tsinghua.edu.cn) |
英文摘要 | Indoor PM2.5 pollution is one of the leading causes of death and disease worldwide. As monitoring indoor PM2.5 concentrations on a large scale is challenging, it is urgent to assess population-level exposure and related health risks to develop an easy-to-use and generalized model to predict indoor PM2.5 concentrations and spatiotemporal variations at the global level. Existing machine learning models of indoor PM2.5 are prone to deliver single-point predictions, and their input strategies are not widely applicable. Here, we developed a Bayesian neural network (BNN) model for predicting the distribution of daily average urban residential PM2.5 concentration based on multiple data sources available from nationwide comprehensive sensor-monitoring records in China. The BNN model showed good performance with a 10-fold cross-validation R2 of 0.70, mean-absolute-error of 9.45 mu g/m3, root-mean-square error of 13.3 mu g/m3, and 95 % prediction interval coverage of 85 %. To demonstrate the application process, this model was applied to predict indoor PM2.5 concentrations on a large spatiotemporal scale. Our modeled population-weighted annual indoor PM2.5 concentration for China in 2019 was 22.8 mu g/m3, far exceeding the WHO standard. The validity of the model at the population level can be further bolstered, making it valuable for assessing and managing indoor air pollution-related health risks. |
WOS关键词 | BAYESIAN NEURAL-NETWORK ; FINE PARTICULATE MATTER ; AIR-QUALITY ; EXPOSURE ; BUILDINGS ; PARTICLES ; OCCUPANTS ; CHINA |
资助项目 | National Science Foundation of China[51978366] |
WOS研究方向 | Environmental Sciences & Ecology |
语种 | 英语 |
出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
WOS记录号 | WOS:001131607200001 |
资助机构 | National Science Foundation of China |
源URL | [http://ir.igsnrr.ac.cn/handle/311030/201212] |
专题 | 中国科学院地理科学与资源研究所 |
通讯作者 | Dong, Zhaomin; Zhao, Bin |
作者单位 | 1.Tsinghua Univ, Sch Architecture, Dept Bldg Sci, Beijing 100084, Peoples R China 2.Shenzhen Inst Bldg Res Co Ltd, Shenzhen, Peoples R China 3.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 4.Beihang Univ, Sch Space & Environm, Beijing 100191, Peoples R China 5.Tsinghua Univ, Beijing Key Lab Indoor Air Qual Evaluat & Control, Beijing 100084, Peoples R China |
推荐引用方式 GB/T 7714 | Dai, Hui,Liu, Yumeng,Wang, Jianghao,et al. Large-scale spatiotemporal deep learning predicting urban residential indoor PM2.5 concentration[J]. ENVIRONMENT INTERNATIONAL,2023,182:12. |
APA | Dai, Hui.,Liu, Yumeng.,Wang, Jianghao.,Ren, Jun.,Gao, Yao.,...&Zhao, Bin.(2023).Large-scale spatiotemporal deep learning predicting urban residential indoor PM2.5 concentration.ENVIRONMENT INTERNATIONAL,182,12. |
MLA | Dai, Hui,et al."Large-scale spatiotemporal deep learning predicting urban residential indoor PM2.5 concentration".ENVIRONMENT INTERNATIONAL 182(2023):12. |
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。