An integrated and homogenized global surface solar radiation dataset and its reconstruction based on a convolutional neural network approach
Boyang Jiao,Yucheng Su,Qingxiang Li,Veronica Manara,and Martin Wild
Boyang Jiao
School of Atmospheric Sciences, Sun Yat-sen University, and Key
Laboratory of Tropical Atmosphere–Ocean System, Ministry of Education,
Zhuhai 519082, China
Southern Laboratory of Ocean Science and Engineering (Guangdong
Zhuhai), Zhuhai 519082, China
Yucheng Su
Department of Public Meteorological Service Center, Meteorological Bureau of Zhuhai, Zhuhai 519082, China
School of Atmospheric Sciences, Sun Yat-sen University, and Key
Laboratory of Tropical Atmosphere–Ocean System, Ministry of Education,
Zhuhai 519082, China
Southern Laboratory of Ocean Science and Engineering (Guangdong
Zhuhai), Zhuhai 519082, China
Veronica Manara
Department of Environmental Science and Policy, Università degli
Studi di Milano, via Celoria 10, 20133, Milan, Italy
This paper develops an observational integrated and homogenized global-terrestrial (except for Antarctica) SSRIH station. This is interpolated into a 5° × 5° SSRIH grid and reconstructed into a long-term (1955–2018) global land (except for Antarctica) 5° × 2.5° SSR anomaly dataset (SSRIH20CR) by an improved partial convolutional neural network deep-learning method. SSRIH20CR yields trends of −1.276 W m−2 per decade over the dimming period and 0.697 W m−2 per decade over the brightening period.
This paper develops an observational integrated and homogenized global-terrestrial (except for...
