Machine learning - driven solar forecasting in dust-prone regions for sustainable energy systems

This research focuses on improving solar energy forecasting in dust-affected regions such as the UAE, where frequent dust storms reduce photovoltaic (PV) efficiency by scattering and absorbing sunlight. Many existing models overlook the impact of dust events, leading to inaccurate forecasts during s...

Full description

Saved in:
Bibliographic Details
Main Authors: Kadhim Hayawi, Husna Maliakkal, Neethu Venugopal, Thanveer Musthafa Hussain, Gomathi Bhavani Rajagopalan
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Solar Energy Advances
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S266711312500021X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725580557156352
author Kadhim Hayawi
Husna Maliakkal
Neethu Venugopal
Thanveer Musthafa Hussain
Gomathi Bhavani Rajagopalan
author_facet Kadhim Hayawi
Husna Maliakkal
Neethu Venugopal
Thanveer Musthafa Hussain
Gomathi Bhavani Rajagopalan
author_sort Kadhim Hayawi
collection DOAJ
description This research focuses on improving solar energy forecasting in dust-affected regions such as the UAE, where frequent dust storms reduce photovoltaic (PV) efficiency by scattering and absorbing sunlight. Many existing models overlook the impact of dust events, leading to inaccurate forecasts during such conditions. To address this, the study develops machine learning models—including LSTM, GRU, and hybrid LSTM-GRU architectures—that incorporate solar, weather, and dust-related features. The models were evaluated across multiple forecasti24 hoursons (1, 6, 12, and 24 hours), demonstrating that including dust-related variables significantly enhances prediction accuracy, particularly for short-term forecasts. Temporal and seasonal analyses revealed that dust events, most frequent in the late afternoon and early spring, correlate with substantial drops in solar power output. The LSTM model consistently outperformed the others, achieving a Mean Absolute Error (MAE) of 0.018034 for a 1-hour horizon when dust features were included. Statistical tests confirmed that dust events significantly affect forecasting accuracy, reinforcing the importance of dust-related features for reliable predictions. This research contributes to optimizing PV power generation in challenging environments, supporting sustainable energy systems and decarbonization efforts. It also offers insights for further model refinement and the inclusion of additional environmental variables.
format Article
id doaj-art-dd2a99956a9f4e02837b7480707e8096
institution DOAJ
issn 2667-1131
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Solar Energy Advances
spelling doaj-art-dd2a99956a9f4e02837b7480707e80962025-08-20T03:10:25ZengElsevierSolar Energy Advances2667-11312025-01-01510010810.1016/j.seja.2025.100108Machine learning - driven solar forecasting in dust-prone regions for sustainable energy systemsKadhim Hayawi0Husna Maliakkal1Neethu Venugopal2Thanveer Musthafa Hussain3Gomathi Bhavani Rajagopalan4College of Interdisciplinary Studies, Computational Sciences, Zayed University, Abu Dhabi, United Arab Emirates; Correspondence author at. Zayed University, Abu Dhabi Campus, United Arab Emirates.College of Interdisciplinary Studies, Computational Sciences, Zayed University, Abu Dhabi, United Arab EmiratesCollege of Interdisciplinary Studies, Computational Sciences, Zayed University, Abu Dhabi, United Arab EmiratesDepartment of Electrical and Electronics Engineering, Birla Institute of Technology and Science, Pilani, Dubai, United Arab EmiratesDepartment of Electrical and Electronics Engineering, Birla Institute of Technology and Science, Pilani, Dubai, United Arab EmiratesThis research focuses on improving solar energy forecasting in dust-affected regions such as the UAE, where frequent dust storms reduce photovoltaic (PV) efficiency by scattering and absorbing sunlight. Many existing models overlook the impact of dust events, leading to inaccurate forecasts during such conditions. To address this, the study develops machine learning models—including LSTM, GRU, and hybrid LSTM-GRU architectures—that incorporate solar, weather, and dust-related features. The models were evaluated across multiple forecasti24 hoursons (1, 6, 12, and 24 hours), demonstrating that including dust-related variables significantly enhances prediction accuracy, particularly for short-term forecasts. Temporal and seasonal analyses revealed that dust events, most frequent in the late afternoon and early spring, correlate with substantial drops in solar power output. The LSTM model consistently outperformed the others, achieving a Mean Absolute Error (MAE) of 0.018034 for a 1-hour horizon when dust features were included. Statistical tests confirmed that dust events significantly affect forecasting accuracy, reinforcing the importance of dust-related features for reliable predictions. This research contributes to optimizing PV power generation in challenging environments, supporting sustainable energy systems and decarbonization efforts. It also offers insights for further model refinement and the inclusion of additional environmental variables.http://www.sciencedirect.com/science/article/pii/S266711312500021XSustainable energySolar energy forecastingDust impactPhotovoltaic (PV) efficiencyMachine learning
spellingShingle Kadhim Hayawi
Husna Maliakkal
Neethu Venugopal
Thanveer Musthafa Hussain
Gomathi Bhavani Rajagopalan
Machine learning - driven solar forecasting in dust-prone regions for sustainable energy systems
Solar Energy Advances
Sustainable energy
Solar energy forecasting
Dust impact
Photovoltaic (PV) efficiency
Machine learning
title Machine learning - driven solar forecasting in dust-prone regions for sustainable energy systems
title_full Machine learning - driven solar forecasting in dust-prone regions for sustainable energy systems
title_fullStr Machine learning - driven solar forecasting in dust-prone regions for sustainable energy systems
title_full_unstemmed Machine learning - driven solar forecasting in dust-prone regions for sustainable energy systems
title_short Machine learning - driven solar forecasting in dust-prone regions for sustainable energy systems
title_sort machine learning driven solar forecasting in dust prone regions for sustainable energy systems
topic Sustainable energy
Solar energy forecasting
Dust impact
Photovoltaic (PV) efficiency
Machine learning
url http://www.sciencedirect.com/science/article/pii/S266711312500021X
work_keys_str_mv AT kadhimhayawi machinelearningdrivensolarforecastingindustproneregionsforsustainableenergysystems
AT husnamaliakkal machinelearningdrivensolarforecastingindustproneregionsforsustainableenergysystems
AT neethuvenugopal machinelearningdrivensolarforecastingindustproneregionsforsustainableenergysystems
AT thanveermusthafahussain machinelearningdrivensolarforecastingindustproneregionsforsustainableenergysystems
AT gomathibhavanirajagopalan machinelearningdrivensolarforecastingindustproneregionsforsustainableenergysystems