Retrieval of surface solar irradiance from satellite imagery using machine learning: pitfalls and perspectives

Verbois, Hadrien; Saint-Drenan, Yves-Marie; Becquet, Vadim; Gschwind, Benoit; Blanc, Philippe

doi:https://doi.org/10.5194/amt-16-4165-2023

Articles | Volume 16, issue 18

https://doi.org/10.5194/amt-16-4165-2023

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

https://doi.org/10.5194/amt-16-4165-2023

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

Articles | Volume 16, issue 18

Research article

|

19 Sep 2023

Research article |

| 19 Sep 2023

Retrieval of surface solar irradiance from satellite imagery using machine learning: pitfalls and perspectives

Hadrien Verbois, Yves-Marie Saint-Drenan, Vadim Becquet, Benoit Gschwind, and Philippe Blanc

Supplement

https://doi.org/10.5194/amt-16-4165-2023-supplement

Data sets

Basic measurements of radiation at station Carpentras (2018-10) L. Brunier https://doi.org/10.1594/PANGAEA.896713

High Rate SEVIRI Level 1.5 Image Data - MSG - 0 degree EUMETSAT https://navigator.eumetsat.int/product/EO:EUM:DAT:MSG:HRSEVIRI

Model code and software

pvlib python: a python package for modeling solar energy systems (https://pvlib-python.readthedocs.io/en/stable/reference/generated/pvlib.iotools.get_cams.html) W. F. Holmgren, C. W. Hansen, and M. A. Mikofski https://doi.org/10.21105/joss.00884

Short summary

Solar surface irradiance (SSI) estimations inferred from satellite images are essential to gain a comprehensive understanding of the solar resource, which is crucial in many fields. This study examines the recent data-driven methods for inferring SSI from satellite images and explores their strengths and weaknesses. The results suggest that while these methods show great promise, they sometimes dramatically underperform and should probably be used in conjunction with physical approaches.