Machine-learning-based probabilistic forecasting of solar irradiance in Chile

<p>By the end of 2023, renewable sources covered 63.4 % of the total electric-power demand of Chile, and, in line with the global trend, photovoltaic (PV) power showed the most dynamic increase. Although Chile's Atacama Desert is considered to be the sunniest place on Earth, PV power prod...

Full description

Saved in:
Bibliographic Details
Main Authors: S. Baran, J. C. Marín, O. Cuevas, M. Díaz, M. Szabó, O. Nicolis, M. Lakatos
Format: Article
Language:English
Published: Copernicus Publications 2025-06-01
Series:Advances in Statistical Climatology, Meteorology and Oceanography
Online Access:https://ascmo.copernicus.org/articles/11/89/2025/ascmo-11-89-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850128576626556928
author S. Baran
J. C. Marín
J. C. Marín
O. Cuevas
O. Cuevas
M. Díaz
M. Szabó
O. Nicolis
M. Lakatos
author_facet S. Baran
J. C. Marín
J. C. Marín
O. Cuevas
O. Cuevas
M. Díaz
M. Szabó
O. Nicolis
M. Lakatos
author_sort S. Baran
collection DOAJ
description <p>By the end of 2023, renewable sources covered 63.4 % of the total electric-power demand of Chile, and, in line with the global trend, photovoltaic (PV) power showed the most dynamic increase. Although Chile's Atacama Desert is considered to be the sunniest place on Earth, PV power production, even in this area, can be highly volatile. Successful integration of PV energy into the country's power grid requires accurate short-term PV power forecasts, which can be obtained from predictions of solar irradiance and related weather quantities. Nowadays, in weather forecasting, the state-of-the-art approach is the use of ensemble forecasts based on multiple runs of numerical weather prediction models. However, ensemble forecasts still tend to be uncalibrated or biased, thus requiring some form of post-processing. The present work investigates probabilistic forecasts of solar irradiance for regions III and IV in Chile. For this reason, eight-member short-term ensemble forecasts of solar irradiance for the calendar year 2021 are generated using the Weather Research and Forecasting (WRF) model; these are then calibrated using the benchmark ensemble model output statistics (EMOS) method based on a censored Gaussian law and its machine-learning-based distributional regression network (DRN) counterpart. Furthermore, we also propose a neural-network-based post-processing method, resulting in improved eight-member ensemble predictions. All forecasts are evaluated against station observations for 30 locations in the study area, and the skill of post-processed predictions is compared to the raw WRF ensemble. Our case study confirms that all studied post-processing methods substantially improve both the calibration of probabilistic forecasts and the accuracy of point forecasts. Among the methods tested, the corrected ensemble exhibits the best overall performance. Additionally, the DRN model generally outperforms the corresponding EMOS approach.</p>
format Article
id doaj-art-75db072e5d524deaa08f6be839e3da32
institution OA Journals
issn 2364-3579
2364-3587
language English
publishDate 2025-06-01
publisher Copernicus Publications
record_format Article
series Advances in Statistical Climatology, Meteorology and Oceanography
spelling doaj-art-75db072e5d524deaa08f6be839e3da322025-08-20T02:33:15ZengCopernicus PublicationsAdvances in Statistical Climatology, Meteorology and Oceanography2364-35792364-35872025-06-01118910510.5194/ascmo-11-89-2025Machine-learning-based probabilistic forecasting of solar irradiance in ChileS. Baran0J. C. Marín1J. C. Marín2O. Cuevas3O. Cuevas4M. Díaz5M. Szabó6O. Nicolis7M. Lakatos8Faculty of Informatics, University of Debrecen, Debrecen, HungaryDepartment of Meteorology, University of Valparaíso, Valparaíso, ChileCenter for Atmospheric Studies and Climate Change (CEACC), University of Valparaíso, Valparaíso, ChileCenter for Atmospheric Studies and Climate Change (CEACC), University of Valparaíso, Valparaíso, ChileInstitute of Physics and Astronomy, University of Valparaíso, Valparaíso, ChileFaculty of Engineering, Andrés Bello University, Viña del Mar, ChileFaculty of Informatics, University of Debrecen, Debrecen, HungaryFaculty of Engineering, Andrés Bello University, Viña del Mar, ChileFaculty of Informatics, University of Debrecen, Debrecen, Hungary<p>By the end of 2023, renewable sources covered 63.4 % of the total electric-power demand of Chile, and, in line with the global trend, photovoltaic (PV) power showed the most dynamic increase. Although Chile's Atacama Desert is considered to be the sunniest place on Earth, PV power production, even in this area, can be highly volatile. Successful integration of PV energy into the country's power grid requires accurate short-term PV power forecasts, which can be obtained from predictions of solar irradiance and related weather quantities. Nowadays, in weather forecasting, the state-of-the-art approach is the use of ensemble forecasts based on multiple runs of numerical weather prediction models. However, ensemble forecasts still tend to be uncalibrated or biased, thus requiring some form of post-processing. The present work investigates probabilistic forecasts of solar irradiance for regions III and IV in Chile. For this reason, eight-member short-term ensemble forecasts of solar irradiance for the calendar year 2021 are generated using the Weather Research and Forecasting (WRF) model; these are then calibrated using the benchmark ensemble model output statistics (EMOS) method based on a censored Gaussian law and its machine-learning-based distributional regression network (DRN) counterpart. Furthermore, we also propose a neural-network-based post-processing method, resulting in improved eight-member ensemble predictions. All forecasts are evaluated against station observations for 30 locations in the study area, and the skill of post-processed predictions is compared to the raw WRF ensemble. Our case study confirms that all studied post-processing methods substantially improve both the calibration of probabilistic forecasts and the accuracy of point forecasts. Among the methods tested, the corrected ensemble exhibits the best overall performance. Additionally, the DRN model generally outperforms the corresponding EMOS approach.</p>https://ascmo.copernicus.org/articles/11/89/2025/ascmo-11-89-2025.pdf
spellingShingle S. Baran
J. C. Marín
J. C. Marín
O. Cuevas
O. Cuevas
M. Díaz
M. Szabó
O. Nicolis
M. Lakatos
Machine-learning-based probabilistic forecasting of solar irradiance in Chile
Advances in Statistical Climatology, Meteorology and Oceanography
title Machine-learning-based probabilistic forecasting of solar irradiance in Chile
title_full Machine-learning-based probabilistic forecasting of solar irradiance in Chile
title_fullStr Machine-learning-based probabilistic forecasting of solar irradiance in Chile
title_full_unstemmed Machine-learning-based probabilistic forecasting of solar irradiance in Chile
title_short Machine-learning-based probabilistic forecasting of solar irradiance in Chile
title_sort machine learning based probabilistic forecasting of solar irradiance in chile
url https://ascmo.copernicus.org/articles/11/89/2025/ascmo-11-89-2025.pdf
work_keys_str_mv AT sbaran machinelearningbasedprobabilisticforecastingofsolarirradianceinchile
AT jcmarin machinelearningbasedprobabilisticforecastingofsolarirradianceinchile
AT jcmarin machinelearningbasedprobabilisticforecastingofsolarirradianceinchile
AT ocuevas machinelearningbasedprobabilisticforecastingofsolarirradianceinchile
AT ocuevas machinelearningbasedprobabilisticforecastingofsolarirradianceinchile
AT mdiaz machinelearningbasedprobabilisticforecastingofsolarirradianceinchile
AT mszabo machinelearningbasedprobabilisticforecastingofsolarirradianceinchile
AT onicolis machinelearningbasedprobabilisticforecastingofsolarirradianceinchile
AT mlakatos machinelearningbasedprobabilisticforecastingofsolarirradianceinchile