2026-10-13T01:58:00Z https://www.scidb.cn/oai

10.11922/sciencedb.j00001.00368 2023-08-11T09:24:41Z

2023-08-11 Establishment of a global CO2 concentration dataset for 2009-2020 based on GOSAT satellite data doi:10.11922/sciencedb.j00001.00368 en We used the transfer learning theory to integrate the time information as a prior profile into the spatial information based on the global data of GOSAT satellite. The spatial prediction information was adjusted to obtain more accurate spatio-temporal prediction of carbon dioxide concentration. The Spatial and temporal resolution of the product database are 0.25° and monthly respectively. Finally, the database has been compared with TCCON data in middle and low latitude, which shows the correlation coefficient R is 0.98, RMSE is 1.38 ppm.  CO2 concentration; GOSAT; Transfer learning; Global Jingjing Xu Wei Gong Jin Zhang Haowei Zhang Xin Ma Ge Han PUBLIC https://creativecommons.org/licenses/by/4.0/ dataset http://www.doi.org/10.11922/11-6035.noda.2022.0003.zh Science Data Bank