Generating Fine-Scale Aerosol Data through Downscaling with an Artificial Neural Network Enhanced with Transfer Learning
文献类型：期刊论文
| 作者 | Wang, Menglin3; Franklin, Meredith1,3,4; Li, Lianfa2,3 |
| 刊名 | ATMOSPHERE
 |
| 出版日期 | 2022-02-01 |
| 卷号 | 13期号:2页码:18 |
| 关键词 | downscaling artificial neural network transfer learning deep learning G5NR MERRA-2 |
| DOI | 10.3390/atmos13020255 |
| 通讯作者 | Franklin, Meredith(menglinw@usc.edu) |
| 英文摘要 | Spatially and temporally resolved aerosol data are essential for conducting air quality studies and assessing the health effects associated with exposure to air pollution. As these data are often expensive to acquire and time consuming to estimate, computationally efficient methods are desirable. When coarse-scale data or imagery are available, fine-scale data can be generated through downscaling methods. We developed an Artificial Neural Network Sequential Downscaling Method (ASDM) with Transfer Learning Enhancement (ASDMTE) to translate time-series data from coarse- to fine-scale while maintaining between-scale empirical associations as well as inherent within-scale correlations. Using assimilated aerosol optical depth (AOD) from the GEOS-5 Nature Run (G5NR) (2 years, daily, 7 km resolution) and Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) (20 years, daily, 50 km resolution), coupled with elevation (1 km resolution), we demonstrate the downscaling capability of ASDM and ASDMTE and compare their performances against a deep learning downscaling method, Super Resolution Deep Residual Network (SRDRN), and a traditional statistical downscaling framework called dissever ASDM/ASDMTE utilizes empirical between-scale associations, and accounts for within-scale temporal associations in the fine-scale data. In addition, within-scale temporal associations in the coarse-scale data are integrated into the ASDMTE model through the use of transfer learning to enhance downscaling performance. These features enable ASDM/ASDMTE to be trained on short periods of data yet achieve a good downscaling performance on a longer time-series. Among all the test sets, ASDM and ASDMTE had mean maximum image-wise R-2 of 0.735 and 0.758, respectively, while SRDRN, dissever GAM and dissever LM had mean maximum image-wise R-2 of 0.313, 0.106 and 0.095, respectively. |
| WOS关键词 | OPTICAL DEPTH ; PM2.5 CONCENTRATIONS ; PARTICULATE MATTER ; AIR-POLLUTION ; MODEL ; MERRA-2 ; IMPACT |
| 资助项目 | National Aeronautics and Space Administration[80NSSC19K0225] |
| WOS研究方向 | Environmental Sciences & Ecology ; Meteorology & Atmospheric Sciences |
| 语种 | 英语 |
| WOS记录号 | WOS:000770428300001 |
| 出版者 | MDPI |
| 资助机构 | National Aeronautics and Space Administration |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/172567]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Franklin, Meredith |
| 作者单位 | 1.Univ Toronto, Dept Stat Sci, Toronto, ON M5G 1Z5, Canada 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources, State Key Lab Resources & Environm Informat Syst, 11A, Datun Rd,Chaoyang Dist, Beijing 100101, Peoples R China 3.Univ Southern Calif, Div Biostat, Los Angeles, CA 90032 USA 4.Univ Toronto, Sch Environm, Toronto, ON M5G 1Z5, Canada |
| 推荐引用方式 GB/T 7714 | Wang, Menglin,Franklin, Meredith,Li, Lianfa. Generating Fine-Scale Aerosol Data through Downscaling with an Artificial Neural Network Enhanced with Transfer Learning[J]. ATMOSPHERE,2022,13(2):18. |
| APA | Wang, Menglin,Franklin, Meredith,&Li, Lianfa.(2022).Generating Fine-Scale Aerosol Data through Downscaling with an Artificial Neural Network Enhanced with Transfer Learning.ATMOSPHERE,13(2),18. |
| MLA | Wang, Menglin,et al."Generating Fine-Scale Aerosol Data through Downscaling with an Artificial Neural Network Enhanced with Transfer Learning".ATMOSPHERE 13.2(2022):18. |
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。