MACHINE LEARNING-BASED INVERSION OF MAXIMUM SURFACE RELATIVE HUMIDITY
文献类型：期刊论文
| 作者 | Wang, Xiaowei3,4; Jiang, Yazhen3,5; Tang, Ronglin3,5; Li, Zhao-Liang1,3,5; Lan, Xinyu2 |
| 刊名 | 2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS)
 |
| 出版日期 | 2025 |
| 卷号 | N/A页码:7832-7836 |
| 关键词 | Maximum surface relative humidity Evapotranspiration Surface vapor pressure |
| ISSN号 | 2153-6996 |
| DOI | 10.1109/IGARSS55030.2025.11242335 |
| 产权排序 | 1 |
| 文献子类 | Proceedings Paper |
| 英文摘要 | The maximum surface relative humidity (h(s,max)) is a key factor that affects surface vapor pressure (es), which governs evapotranspiration (ET) rates. However, current empirical methods for quantifying h(s, max) introduce limitations in the accuracy of saturation vapor pressure calculations, and consequently, ET estimates. In this study, we performed a back-calculation of h(s, max) using a multivariate interaction model based on site-observed ET data. A Bayesian-optimized XGBoost algorithm was applied to construct h(s,max) models for different land types, which were then combined with remote sensing and reanalysis data for spatial estimation. Model validation shows that the constructed h(s, max) models are highly accurate, with average Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and correlation coefficient (R) values of 0.049, 0.078, and 0.916, respectively, across various land types. Furthermore, h(s, max) exhibits distinct spatial patterns, with higher values predominantly found in tropical rainforest regions, and significant temporal variations in monsoon, arid, and semi-arid regions. |
| URL标识 | 查看原文 |
| WOS研究方向 | Physical Geography ; Geology ; Instruments & Instrumentation ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001704613000301 |
| 出版者 | IEEE |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221370]  |
| 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 | Jiang, Yazhen |
| 作者单位 | 1.Chinese Acad Agr Sci, Minist Agr & Rural Affaires Inst Agr Resources &, Key Lab Agr Remote Sensing, Beijing 100081, Peoples R China; 2.Beijing Forestry Univ, Sch Grassland Sci, Beijing 100083, Peoples R China 3.Chinese Acad Sci, Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China; 4.Nanjing Univ Informat Sci Technol, Sch Ecol & Appl Meteorol, Nanjing 210044, Peoples R China; 5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Wang, Xiaowei,Jiang, Yazhen,Tang, Ronglin,et al. MACHINE LEARNING-BASED INVERSION OF MAXIMUM SURFACE RELATIVE HUMIDITY[J]. 2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS),2025,N/A:7832-7836. |
| APA | Wang, Xiaowei,Jiang, Yazhen,Tang, Ronglin,Li, Zhao-Liang,&Lan, Xinyu.(2025).MACHINE LEARNING-BASED INVERSION OF MAXIMUM SURFACE RELATIVE HUMIDITY.2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS),N/A,7832-7836. |
| MLA | Wang, Xiaowei,et al."MACHINE LEARNING-BASED INVERSION OF MAXIMUM SURFACE RELATIVE HUMIDITY".2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) N/A(2025):7832-7836. |
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。