Artificial Intelligence-Based Models for Estimating and Extrapolating Soiling Effects on Photovoltaic Systems in Spain

Environmental and temporal conditions, particularly dust accumulation, can significantly impact the performance of photovoltaic solar panels, potentially reducing their efficiency by up to 20%, and thereby affecting profitability. Accurately estimating these losses is crucial for optimising maintena...

Full description

Saved in:
Bibliographic Details
Main Authors: Carlos Sánchez-García, Jesús Polo, Joaquín Alonso-Montesinos
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/5960
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850160976030072832
author Carlos Sánchez-García
Jesús Polo
Joaquín Alonso-Montesinos
author_facet Carlos Sánchez-García
Jesús Polo
Joaquín Alonso-Montesinos
author_sort Carlos Sánchez-García
collection DOAJ
description Environmental and temporal conditions, particularly dust accumulation, can significantly impact the performance of photovoltaic solar panels, potentially reducing their efficiency by up to 20%, and thereby affecting profitability. Accurately estimating these losses is crucial for optimising maintenance and avoiding unforeseen losses. Various models have been proposed in the literature for this purpose. In this context, four machine learning models were developed using meteorological and air quality data from the Solar Energy Research Center (CIESOL). A Gradient-Boosting model (LightGBM) and a neural network achieved RMSE values of 0.68% and 0.88% of soiling loss, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> values of 0.86 and 0.76 between measured and estimated values, respectively, on their test sets. The generalisation capability of these models was tested by extrapolating them to other regions in Spain. To enhance robustness across locations, a global artificial neural network (ANN) model was trained using combined data from two sites, achieving an RMSE of 1.02% when estimating soiling losses. This result highlights a significant improvement over models trained on a single location and tested elsewhere, demonstrating the global model’s stronger ability to generalise across different geographic settings.
format Article
id doaj-art-9d6fb4c1f1e14277a53bb9eee692c9d2
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-9d6fb4c1f1e14277a53bb9eee692c9d22025-08-20T02:23:00ZengMDPI AGApplied Sciences2076-34172025-05-011511596010.3390/app15115960Artificial Intelligence-Based Models for Estimating and Extrapolating Soiling Effects on Photovoltaic Systems in SpainCarlos Sánchez-García0Jesús Polo1Joaquín Alonso-Montesinos2CIESOL, Joint Centre of the University of Almería-CIEMAT, 04120 Almería, SpainPhotovoltaic Solar Energy Unit, Renewable Energy Division, CIEMAT, 28040 Madrid, SpainCIESOL, Joint Centre of the University of Almería-CIEMAT, 04120 Almería, SpainEnvironmental and temporal conditions, particularly dust accumulation, can significantly impact the performance of photovoltaic solar panels, potentially reducing their efficiency by up to 20%, and thereby affecting profitability. Accurately estimating these losses is crucial for optimising maintenance and avoiding unforeseen losses. Various models have been proposed in the literature for this purpose. In this context, four machine learning models were developed using meteorological and air quality data from the Solar Energy Research Center (CIESOL). A Gradient-Boosting model (LightGBM) and a neural network achieved RMSE values of 0.68% and 0.88% of soiling loss, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> values of 0.86 and 0.76 between measured and estimated values, respectively, on their test sets. The generalisation capability of these models was tested by extrapolating them to other regions in Spain. To enhance robustness across locations, a global artificial neural network (ANN) model was trained using combined data from two sites, achieving an RMSE of 1.02% when estimating soiling losses. This result highlights a significant improvement over models trained on a single location and tested elsewhere, demonstrating the global model’s stronger ability to generalise across different geographic settings.https://www.mdpi.com/2076-3417/15/11/5960PV soilingmachine learningkNNgradient boostingLightGBMCatBoost
spellingShingle Carlos Sánchez-García
Jesús Polo
Joaquín Alonso-Montesinos
Artificial Intelligence-Based Models for Estimating and Extrapolating Soiling Effects on Photovoltaic Systems in Spain
Applied Sciences
PV soiling
machine learning
kNN
gradient boosting
LightGBM
CatBoost
title Artificial Intelligence-Based Models for Estimating and Extrapolating Soiling Effects on Photovoltaic Systems in Spain
title_full Artificial Intelligence-Based Models for Estimating and Extrapolating Soiling Effects on Photovoltaic Systems in Spain
title_fullStr Artificial Intelligence-Based Models for Estimating and Extrapolating Soiling Effects on Photovoltaic Systems in Spain
title_full_unstemmed Artificial Intelligence-Based Models for Estimating and Extrapolating Soiling Effects on Photovoltaic Systems in Spain
title_short Artificial Intelligence-Based Models for Estimating and Extrapolating Soiling Effects on Photovoltaic Systems in Spain
title_sort artificial intelligence based models for estimating and extrapolating soiling effects on photovoltaic systems in spain
topic PV soiling
machine learning
kNN
gradient boosting
LightGBM
CatBoost
url https://www.mdpi.com/2076-3417/15/11/5960
work_keys_str_mv AT carlossanchezgarcia artificialintelligencebasedmodelsforestimatingandextrapolatingsoilingeffectsonphotovoltaicsystemsinspain
AT jesuspolo artificialintelligencebasedmodelsforestimatingandextrapolatingsoilingeffectsonphotovoltaicsystemsinspain
AT joaquinalonsomontesinos artificialintelligencebasedmodelsforestimatingandextrapolatingsoilingeffectsonphotovoltaicsystemsinspain