An integrated and homogenized global surface solar radiation dataset and its reconstruction based on a convolutional neural network approach

Jiao, Boyang; Su, Yucheng; Li, Qingxiang; Manara, Veronica; Wild, Martin

doi:https://doi.org/10.5194/essd-15-4519-2023

Articles | Volume 15, issue 10

https://doi.org/10.5194/essd-15-4519-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/essd-15-4519-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 15, issue 10

Data description paper

|

06 Oct 2023

Data description paper |

| 06 Oct 2023

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

Supplement

https://doi.org/10.5194/essd-15-4519-2023-supplement

Data sets

Global Integrated and Homogenized Solar surface Radiation Datasets Boyang Jiao and Qingxiang Li https://doi.org/10.6084/m9.figshare.21625079.v1

Download

Article (8401 KB)
Full-text XML

Short summary

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 (SSRIH_20CR) by an improved partial convolutional neural network deep-learning method. SSRIH_20CR 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.