An Innovative Deep Learning Based TemperatureEmissivity Separation Algorithm for Highresolution Thermal Missions
文献类型：期刊论文
| 作者 | Zhang, Huanyu1,4; Tang, Bo-Hui2; Jiang, Yun4; Hu, Tian3 |
| 刊名 | IGARSS 2025-2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM
 |
| 出版日期 | 2025 |
| 卷号 | N/A页码:954-958 |
| 关键词 | land surface temperature (LST) temperature-emissivity separation (TES) uncertainty analysis deep learning |
| ISSN号 | 2153-6996 |
| DOI | 10.1109/IGARSS55030.2025.11244090 |
| 产权排序 | 1 |
| 文献子类 | Proceedings Paper |
| 英文摘要 | The temperature-emissivity separation (TES) algorithm is a widely used method for clear-sky land surface temperature (LST) estimation, standing as a promising candidate for the future high-resolution thermal missions. However, the error characteristics of TES has yet to be fully revealed, resulting in a lack of reliable theoretical supports for further refining TES. In this study, the independent impacts of each error source were first quantified using a comprehensive simulation dataset, and the respective impact of the maximum minimum difference (MMD) module was isolated from the TES algorithm. Results reaffirmed the importance of improving the atmospheric correction and MMD module in TES, while the benefits of refining other modules appeared minimal. Based on the above analyses, by combining deep learning (DL) and the split-window (SW) algorithm, the atmospheric correction step in TES was refined, and evaluations sufficiently demonstrated the improved retrieval accuracy and efficiency of the new model. |
| URL标识 | 查看原文 |
| WOS关键词 | LAND-SURFACE TEMPERATURE ; EMISSIVITY PRODUCTS ; ASTER ; MODIS |
| WOS研究方向 | Physical Geography ; Geology ; Instruments & Instrumentation ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001697407700201 |
| 出版者 | IEEE |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221365]  |
| 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 | Zhang, Huanyu |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing, Peoples R China; 2.Kunming Univ Sci & Technol, Fac Land Resource Engn, Kunming, Yunnan, Peoples R China; 3.Luxembourg Inst Sci & Technol, Belvaux, Luxembourg 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Zhang, Huanyu,Tang, Bo-Hui,Jiang, Yun,et al. An Innovative Deep Learning Based TemperatureEmissivity Separation Algorithm for Highresolution Thermal Missions[J]. IGARSS 2025-2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM,2025,N/A:954-958. |
| APA | Zhang, Huanyu,Tang, Bo-Hui,Jiang, Yun,&Hu, Tian.(2025).An Innovative Deep Learning Based TemperatureEmissivity Separation Algorithm for Highresolution Thermal Missions.IGARSS 2025-2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM,N/A,954-958. |
| MLA | Zhang, Huanyu,et al."An Innovative Deep Learning Based TemperatureEmissivity Separation Algorithm for Highresolution Thermal Missions".IGARSS 2025-2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM N/A(2025):954-958. |
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。