%0 Dataset
%T Long time series kilometer level annual average ground temperature dataset in the Northern Hemisphere (1850-2100)
%J National Cryosphere Desert Data Center
%I National Cryosphere Desert Data Center(www.ncdc.ac.cn)
%U http://www.ncdc.ac.cn/portal/metadata/dc58dd10-50c2-4bc6-a8b2-64f5c0c9ce32
%W NCDC
%R 10.12072/ncdc.nieer.db4213.2024
%A Peng Xiaoqing
%A jinhaodong
%A Zhao guohui
%K 多年冻土
%X The annual average ground temperature in permafrost regions is another important indicator for studying permafrost changes. In previous studies, there have been many explorations on the changes in annual average ground temperature over historical periods based on field measured data and remote sensing inversion algorithms, but their spatial resolution is relatively low. Based on CMIP6 data, obtain surface temperature in permafrost regions with a resolution of 1km through downscaling methods; Then, this data is used as a high-precision and high-resolution input variable for the future variation of multi-year average ground temperature, further obtaining a 1km resolution annual average ground temperature in the northern hemisphere. By using multiple machine learning methods to obtain multi-mode averages, the accuracy and resolution of the annual average ground temperature dataset are improved. The RMSE of the output result of the ensemble average mode is 1.01 ℃, MAE is 0.69 ℃, and R is 0.89.