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
Correction of Overestimation in Observed Land Surface Temperatures Based on Machine Learning Models

文献类型：期刊论文

作者Liu, Fa1; Wang, Xunming1,2; Sun, Fubao1,2,3,4; Wang, Hong1; Wu, Lifeng5; Zhang, Xuanze1; Liu, Wenbin1; Che, Huizheng6
刊名JOURNAL OF CLIMATE
出版日期2022-08-15
卷号35期号:16页码:5359-5377
关键词Land surface temperature Machine learning model Climate regions Prediction Correction
ISSN号0894-8755
DOI10.1175/JCLI-D-21-0447.1
通讯作者Wang, Xunming(xunming@igsnrr.ac.cn) ; Sun, Fubao(sunfb@igsnrr.ac.cn)
英文摘要Land surface temperature (LST) is an essential variable for high-temperature prediction, drought monitoring, climate, and ecological environment research. Several recent studies reported that LST observations in China warmed much faster than surface air temperature (SAT), especially after 2002. Here we found that the abrupt change in daily LST was mainly due to the overestimation of LST values from the automatic recording thermometer under snow cover conditions. These inhomogeneity issues in LST data could result in wrong conclusions without appropriate correction. To address these issues, we proposed three machine learning models-multivariate adaptive regression spline (MARS), random forest (RF), and a novel simple tree-based method named extreme gradient boosting (XGBoost)-for accurate prediction of daily LST using conventional meteorological data. Daily air temperature (maximum, minimum, mean), sunshine duration, precipitation, wind speed, relative humidity, daily solar radiation, and diurnal temperature range of 2185 stations over 1971-2002 from four regions of China were used to train and test the models. The results showed that the machine learning models, particularly XGBoost, outperformed other models in estimating daily LST. Based on LST data corrected by the XGBoost model, the dramatic increase in LST disappeared. The long-term trend for the new LST was estimated to be 0.32 degrees +/- 0.03 degrees C decade(-1) over 1971-2019, which is close to the trend in SAT (0.30 degrees +/- 0.03 degrees C decade(-1)). This study corrected the inhomogeneities of daily LST in China, indicating the strong potential of machine learning models for improving estimation of LST and other surface climatic factors.
WOS关键词GLOBAL SOLAR-RADIATION ; SOIL TEMPERATURES ; RANDOM FOREST ; SUPPORT ; PRECIPITATION ; OPTIMIZATION ; CLIMATES ; ENERGY ; CHINA ; WATER
资助项目National Natural Science Foundation of China[42025104] ; National Natural Science Foundation of China[42101011] ; Program for the Kezhen-Bingwei Youth Talents[2021RC002] ; Key Frontier Program of Chinese Academy of Sciences[QYZDJSSW-DQC043] ; National Key Research and Development Programof China[2019YFA0606903]
WOS研究方向Meteorology & Atmospheric Sciences
语种英语
WOS记录号WOS:000835668800007
出版者AMER METEOROLOGICAL SOC
资助机构National Natural Science Foundation of China ; Program for the Kezhen-Bingwei Youth Talents ; Key Frontier Program of Chinese Academy of Sciences ; National Key Research and Development Programof China
源URL[http://ir.igsnrr.ac.cn/handle/311030/181933]  
专题中国科学院地理科学与资源研究所
通讯作者Wang, Xunming; Sun, Fubao
作者单位1.Chinese Acad Sci, Inst Geog Sci & Sci & Nat Resources Res, Key Lab Water Cycle & Related Land Surface Proc, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing, Peoples R China
3.Chinese Acad Sci, Xinjiang Inst Ecol & Geog, State Key Lab Desert & Oasis Ecol, Urumqi, Peoples R China
4.Akesu Natl Stn Observat & Res Oasis Agroecosystem, Akesu, Peoples R China
5.Nanchang Inst Technol, Sch Hydraul & Ecol Engn, Nanchang, Peoples R China
6.Chinese Acad Meteorol Sci, Inst Atmospher Composit & Environm Meteorol, Key Lab Atmospher Chem LAC, China Meteorol Adm, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Fa,Wang, Xunming,Sun, Fubao,et al. Correction of Overestimation in Observed Land Surface Temperatures Based on Machine Learning Models[J]. JOURNAL OF CLIMATE,2022,35(16):5359-5377.
APA Liu, Fa.,Wang, Xunming.,Sun, Fubao.,Wang, Hong.,Wu, Lifeng.,...&Che, Huizheng.(2022).Correction of Overestimation in Observed Land Surface Temperatures Based on Machine Learning Models.JOURNAL OF CLIMATE,35(16),5359-5377.
MLA Liu, Fa,et al."Correction of Overestimation in Observed Land Surface Temperatures Based on Machine Learning Models".JOURNAL OF CLIMATE 35.16(2022):5359-5377.

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。