Copyright and Licensing
Articles accepted for publication will be licensed under the Creative Commons BY-NC-SA. Authors must sign a non-exclusive distribution agreement after article acceptance.
Machine Learning for Site Adaptation of Satellite-DerivedSolar Irradiance in Northwestern Argentina
DOI:
https://doi.org/10.24215/16666038.25.e10Keywords:
Solar Irradiance, Site Adaptation, Machine LearningAbstract
Accurate estimation of global horizontal irradiance (GHI) is essential for solar energy resource assessment, particularly in regions with limited ground-based measurements. This study evaluates the performance of three machine learning models—Simple Linear Regression (SLR), Extreme Gradient Boosting (XGB), and Multilayer Perceptron (MLP)—for the site adaptation of satellite-derived GHI data in five locations in Northwestern Argentina. Two satellite products, CAMS and LSA-SAF, were used as input data. The
models were assessed using standard error metrics (MBE, MAE, RMSE), and their residual patterns were analyzed. Results show that LSA-SAF data led to
lower errors compared to CAMS, especially in highaltitude sites. While complex models like MLP and XGB marginally improved accuracy in some cases, SLR offered comparable results with higher robustness. The analysis also identified systematic biases and discretization effects in tree-based models. These findings suggest that, under current data conditions,
simpler models may offer reliable performance. Enhancing input data quality and incorporating additional meteorological features may yield greater improvements than increasing model complexity
Downloads
Download data is not yet available.
References
R. Alonso-Suárez, “Estimación del recurso solar en uruguay mediante imágenes satelitales,” Ph.D. dissertation, Universidad de la República - Uruguay, Jul. 2017.
H. Grossi Gallegos y R. Righini, Atlas de Energía Solar de la República Argentina, 2007.
G. Salazar, R. D. Ledesma, C. López Ruiz, y O. de Castro Vilela, “Análisis de desempeño de diferentes técnicas de aprendizaje automático en una adaptación al sitio de irradiancia solar global para salta (argentina),” Avances en Energías Renovables y Medio Ambiente - AVERMA, vol. 28, pp. 308–320, Abr. 2025. Disponible en: https://portalderevistas.unsa.edu.ar/index.php/averma/article/view/4892.
R. Laspiur et al., “Trazado de mapas medios anuales de energía solar global, directa, difusa y tilt, usando la base de datos de swera. caso de estudio: provincias de salta y jujuy,” Avances en Energías Renovables y Medio Ambiente - AVERMA, vol. 17, pp. 47–52, Nov. 2021. Disponible en: https://portalderevistas.unsa.edu.ar/index.php/averma/article/view/2066.
N. Sarmiento et al., “A solar irradiation gis as decision support tool for the province of salta, argentina,” Renewable Energy, vol. 132, pp. 68–80, 2019. Disponible en: https://www.sciencedirect.com/science/article/pii/S0960148118308784.
J. Polo et al., “Preliminary survey on site-adaptation techniques for satellite-derived and reanalysis solar radiation datasets,” Solar Energy, vol. 132, pp. 25–37, 2016. Disponible en: https://www.sciencedirect.com/science/article/pii/S0038092X16001754.
J. Polo et al., “Benchmarking on improvement and site-adaptation techniques for modeled solar radiation datasets,” Solar Energy, vol. 201, pp. 469–479, 2020. Disponible en: https://www.sciencedirect.com/science/article/pii/S0038092X20302784.
H. Verbois et al., “Improvement of satellite-derived surface solar irradiance estimations using spatio-temporal extrapolation with statistical learning,” Solar Energy, vol. 258, pp. 175–193, 2023. Disponible en: https://www.sciencedirect.com/science/article/pii/S0038092X23002670.
V. Salamalikis, P. Tzoumanikas, A. A. Argiriou, y A. Kazantzidis, “Site adaptation of global horizontal irradiance from the copernicus atmospheric monitoring service for radiation using supervised machine learning techniques,” Renewable Energy, vol. 195, pp. 92–106, 2022. Disponible en: https://www.sciencedirect.com/science/article/pii/S0960148122008758.
S. Zainali, D. Yang, T. Landelius, y P. E. Campana, “Site adaptation with machine learning for a northern europe gridded global solar irradiance product,” Energy and AI, vol. 15, p. 100331, 2024. Disponible en: https://www.sciencedirect.com/science/article/pii/S2666546823001039.
G. A. Salazar et al., “Evaluación del proceso de adaptación al sitio aplicado a la irradiancia solar global medida en la ciudad de salta, argentina,” Avances en Energías Renovables y Medio Ambiente - AVERMA, vol. 25, pp. 353–362, May 2022. Disponible en: https://portalderevistas.unsa.edu.ar/index.php/averma/article/view/2431.
Z. Qu et al., “Fast radiative transfer parameterisation for assessing the surface solar irradiance: The heliosat?4 method,” Meteorologische Zeitschrift, vol. 26, no. 1, pp. 33–57, Feb. 2017. doi: 10.1127/metz/2016/0781.
B. Mayer y A. Kylling, “Technical note: The libradtran software package for radiative transfer calculations - description and examples of use,” Atmospheric Chemistry and Physics, vol. 5, no. 7, pp. 1855–1877, 2005. Disponible en: https://acp.copernicus.org/articles/5/1855/2005/.
K. T. Kriebel, G. Gesell, M. Kästner, y H. M. and, “The cloud analysis tool apollo: Improvements and validations,” International Journal of Remote Sensing, vol. 24, no. 12, pp. 2389–2408, 2003. doi: 10.1080/01431160210163065.
R. Ledesma, G. Salazar, y O. Vilela, “Avances en la estimación de irradiancia solar en las provincias de salta y jujuy mediante imágenes satelitales goes-16,” Avances en Energías Renovables y Medio Ambiente - AVERMA, vol. 27, pp. 413–427, Sep. 2024. Disponible en: https://portalderevistas.unsa.edu.ar/index.php/averma/article/view/4643.
M. Derrien y H. L. Gléau, “MSG/SEVIRI cloud mask and type from SAFNWC,” International Journal of Remote Sensing, vol. 26, no. 21, pp. 4707–4732, 2005. doi: 10.1080/01431160500166128.
N. SAF, “User manual for the cloud product processors of the nwc/geo: Science part,” Météo-France / Centre d’études en Météorologie Satellitaire, Tech. Rep., 2022.
X. Ceamanos, D. Carrer, y J.-L. Roujean, “Improved retrieval of direct and diffuse downwelling surface shortwave flux in cloudless atmosphere using dynamic estimates of aerosol content and type: application to the LSA-SAF project,” Atmospheric Chemistry and Physics, vol. 14, no. 15, pp. 8209–8232, 2014. Disponible en: https://acp.copernicus.org/articles/14/8209/2014/.
B. Geiger et al., “Near real-time provision of downwelling shortwave radiation estimates derived from satellite observations,” Meteorological Applications, vol. 15, no. 3, pp. 411–420, 2008. Disponible en: https://rmets.onlinelibrary.wiley.com/doi/abs/10.1002/met.84.
D. E. Rumelhart, G. E. Hinton, y R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, no. 6088, pp. 533–536, 1986. doi: 10.1038/323533a0.
T. Chen y C. Guestrin, “Xgboost: A scalable tree boosting system,” en Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16). New York, NY, USA: Association for Computing Machinery, 2016, pp. 785–794. doi: 10.1145/2939672.2939785.
F. Pedregosa et al., “Scikit-learn: Machine learning in python,” Journal of Machine Learning Research, vol. 12, Jan. 2012.
I. Goodfellow, Y. Bengio, y A. Courville, Deep Learning. MIT Press, 2016. Disponible en: http://www.deeplearningbook.org.
E. Soria Olivas et al., Inteligencia artificial: Casos prácticos con aprendizaje profundo, 1st ed. Bogotá, Colombia: Ediciones de la U, 2022.
M. C. Peel, B. L. Finlayson, y T. A. McMahon, “Updated world map of the köppen-geiger climate classification,” Hydrology and Earth System Sciences, vol. 11, no. 5, pp. 1633–1644, 2007. Disponible en: https://hess.copernicus.org/articles/11/1633/2007/.
F. M. Nollas, G. A. Salazar, y C. A. Gueymard, “Quality control procedure for 1-minute pyranometric measurements of global and shadowband-based diffuse solar irradiance,” Renewable Energy, vol. 202, pp. 40–55, 2023. Disponible en: https://www.sciencedirect.com/science/article/pii/S0960148122016962.
J. Zhang et al., “A suite of metrics for assessing the performance of solar power forecasting,” Solar Energy, vol. 111, pp. 157–175, 2015. Disponible en: https://www.sciencedirect.com/science/article/pii/S0038092X14005027.
Downloads
Published
2025-10-22
Issue
Section
Original Articles
License
Copyright (c) 2025 Rubén Ledesma, Germán Salazar
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
How to Cite
[1]
“Machine Learning for Site Adaptation of Satellite-DerivedSolar Irradiance in Northwestern Argentina”, JCS&T, vol. 25, no. 2, p. e10, Oct. 2025, doi: 10.24215/16666038.25.e10.
