中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
Spatial Downscaling of Land Surface Temperature Based on a Multi-Factor Geographically Weighted Machine Learning Model

文献类型：期刊论文

作者Xu, Saiping1,2; Zhao, Qianjun1; Yin, Kai1; He, Guojin1; Zhang, Zhaoming1; Wang, Guizhou1; Wen, Meiping1; Zhang, Ning3,4
刊名REMOTE SENSING
出版日期2021-03-01
卷号13期号:6页码:33
关键词land surface temperature spatial downscaling geographically weighted regression ensemble learning extreme gradient boosting multivariate adaptive regression splines Bayesian ridge regression Sentinel-2A
DOI10.3390/rs13061186
通讯作者Yin, Kai(yinkai@aircas.ac.cn)
英文摘要Land surface temperature (LST) is a critical parameter of surface energy fluxes and has become the focus of numerous studies. LST downscaling is an effective technique for supplementing the limitations of the coarse-resolution LST data. However, the relationship between LST and other land surface parameters tends to be nonlinear and spatially nonstationary, due to spatial heterogeneity. Nonlinearity and spatial nonstationarity have not been considered simultaneously in previous studies. To address this issue, we propose a multi-factor geographically weighted machine learning (MFGWML) algorithm. MFGWML utilizes three excellent machine learning (ML) algorithms, namely extreme gradient boosting (XGBoost), multivariate adaptive regression splines (MARS), and Bayesian ridge regression (BRR), as base learners to capture the nonlinear relationships. MFGWML uses geographically weighted regression (GWR), which allows for spatial nonstationarity, to fuse the three base learners' predictions. This paper downscales the 30 m LST data retrieved from Landsat 8 images to 10 m LST data mainly based on Sentinel-2A images. The results show that MFGWML outperforms two classic algorithms, namely thermal image sharpening (TsHARP) and the high-resolution urban thermal sharpener (HUTS). We conclude that MFGWML combines the advantages of multiple regression, ML, and GWR, to capture the local heterogeneity and obtain reliable and robust downscaled LST data.
WOS关键词WATER INDEX NDWI ; VARIABLE SELECTION ; ENERGY FLUXES ; REGRESSION ; DISAGGREGATION ; COEFFICIENTS ; MODULATION ; ALGORITHMS ; DERIVATION ; RESOLUTION
资助项目National Key R&D Programof China[2017YFB0503902] ; National Natural Science Foundation of China[61731022] ; National Natural Science Foundation of China[61860206004]
WOS研究方向Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:000651957200001
出版者MDPI
资助机构National Key R&D Programof China ; National Natural Science Foundation of China
源URL[http://ir.igsnrr.ac.cn/handle/311030/162724]  
专题中国科学院地理科学与资源研究所
通讯作者Yin, Kai
作者单位1.Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Minist Housing & Urban Rural Dev Peoples Republ C, Remote Sensing Applicat Ctr, Beijing 100835, Peoples R China
4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China
推荐引用方式
GB/T 7714		 Xu, Saiping,Zhao, Qianjun,Yin, Kai,et al. Spatial Downscaling of Land Surface Temperature Based on a Multi-Factor Geographically Weighted Machine Learning Model[J]. REMOTE SENSING,2021,13(6):33.
APA Xu, Saiping.,Zhao, Qianjun.,Yin, Kai.,He, Guojin.,Zhang, Zhaoming.,...&Zhang, Ning.(2021).Spatial Downscaling of Land Surface Temperature Based on a Multi-Factor Geographically Weighted Machine Learning Model.REMOTE SENSING,13(6),33.
MLA Xu, Saiping,et al."Spatial Downscaling of Land Surface Temperature Based on a Multi-Factor Geographically Weighted Machine Learning Model".REMOTE SENSING 13.6(2021):33.

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。