High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery
文献类型：期刊论文
| 作者 | Liu, Xiansheng1; Zhang, Xun2; Wang, Rui; Liu, Ying; Hadiatullah, Hadiatullah3; Xu, Yanning4; Wang, Tao5; Bendl, Jan6; Adam, Thomas6; Schnelle-Kreis, Jurgen |
| 刊名 | ENVIRONMENTAL SCIENCE & TECHNOLOGY
 |
| 出版日期 | 2024-02-14 |
| 关键词 | PM metrics deep learning LSTM exposureassessment models air quality |
| DOI | 10.1021/acs.est.3c06511 |
| 产权排序 | 3 |
| 文献子类 | Article ; Early Access |
| 英文摘要 | In this study, we propose a novel long short-term memory (LSTM) neural network model that leverages color features (HSV: hue, saturation, value) extracted from street images to estimate air quality with particulate matter (PM) in four typical European environments: urban, suburban, villages, and the harbor. To evaluate its performance, we utilize concentration data for eight parameters of ambient PM (PM1.0, PM2.5, and PM10, particle number concentration, lung-deposited surface area, equivalent mass concentrations of ultraviolet PM, black carbon, and brown carbon) collected from a mobile monitoring platform during the nonheating season in downtown Augsburg, Germany, along with synchronized street view images. Experimental comparisons were conducted between the LSTM model and other deep learning models (recurrent neural network and gated recurrent unit). The results clearly demonstrate a better performance of the LSTM model compared with other statistically based models. The LSTM-HSV model achieved impressive interpretability rates above 80%, for the eight PM metrics mentioned above, indicating the expected performance of the proposed model. Moreover, the successful application of the LSTM-HSV model in other seasons of Augsburg city and various environments (suburbs, villages, and harbor cities) demonstrates its satisfactory generalization capabilities in both temporal and spatial dimensions. The successful application of the LSTM-HSV model underscores its potential as a versatile tool for the estimation of air pollution after presampling of the studied area, with broad implications for urban planning and public health initiatives. |
| WOS关键词 | BLACK CARBON ; LAND-USE ; DISPERSION MODEL ; AIR ; POLLUTION ; POLLUTANTS ; AUGSBURG ; NEXUS |
| WOS研究方向 | Engineering ; Environmental Sciences & Ecology |
| 语种 | 英语 |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/202746]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 作者单位 | 1.Beijing Technol & Business Univ, Sch Comp Sci & Engn, Beijing Key Lab Big Data Technol Food Safety, Beijing 100048, Peoples R China 2.Inst Environm Assessment & Water Res, CSIC, IDAEA, Barcelona 08034, Spain 3.State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 4.Tianjin Univ, Sch Pharmaceut Sci & Technol, Tianjin 300072, Peoples R China 5.Qingdao Univ Technol, Sch Environm & Municipal Engn, Qingdao 266525, Peoples R China 6.Fudan Univ, Dept Environm Sci & Engn, Shanghai Key Lab Atmospher Particle Pollut & Preve, Shanghai 200433, Peoples R China 7.Univ Bundeswehr Munich, Inst Chem & Environm Engn, Fac Mech Engn, D-85577 Neubiberg, Germany 8.Joint Mass Spectrometry Ctr, German Res Ctr Environm Hlth, Helmholtz Zent Munchen, Cooperat Grp Comprehens Mol Analyt, D-85764 Neuherberg, Germany |
| 推荐引用方式 GB/T 7714 | Liu, Xiansheng,Zhang, Xun,Wang, Rui,et al. High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery[J]. ENVIRONMENTAL SCIENCE & TECHNOLOGY,2024. |
| APA | Liu, Xiansheng.,Zhang, Xun.,Wang, Rui.,Liu, Ying.,Hadiatullah, Hadiatullah.,...&Querol, Xavier.(2024).High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery.ENVIRONMENTAL SCIENCE & TECHNOLOGY. |
| MLA | Liu, Xiansheng,et al."High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery".ENVIRONMENTAL SCIENCE & TECHNOLOGY (2024). |
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。