AI-Driven Detection of Atmospheric Obstructions Using YOLOv10 and Satellite Imagery for PV System Optimization in the GCC
M. B. Danbatta, N. Al-Azri, N. Al-Rawahi   Department of Mechanical and Industrial Engineering. Sultan Qaboos University. Al-Khoud 123, Muscat (Oman)   2025-07-25

Abstract

The performance of solar photovoltaic (PV) systems is highly dependent on environmental conditions, with atmospheric obstructions significantly impacting energy yield. Traditional monitoring methods rely on ground-based sensors and periodic cleaning schedules, which may not effectively address real-time soiling dynamics. This research presents an AI-powered approach using YOLOv10 to label and train satellite imagery for the detection of dust accumulation, cloud cover, and other obstructions affecting solar radiation reaching PV systems. By integrating deep learning with multi-temporal satellite imagery, an automated framework for real-time environmental monitoring of solar farms is feasible. The YOLOv10 model is trained on labelled datasets to accurately classify dust prone regions, atmospheric disturbances, and potential shading effects. The framework enables early detection of solar obstructions, allowing operators to optimize panel-cleaning schedules, mitigate power losses, and enhance overall energy efficiency. By leveraging satellite-based remote sensing and deep learning, this study offers a cost-effective, scalable solution for maintaining optimal solar PV performance. The findings contribute to sustainable energy development in the GCC region, aligning with national renewable energy goals and ensuring long-term operational efficiency of solar infrastructure.

Key words: Photovoltaic, Detection, Renewable Energy, Solar, Forecasting

References

[1] N. Al-Azri, Y. Zurigat and N. Al-Rawahi, “Development of bioclimatic chart for passive building design in Muscat-Omant,” Renewable Energy and Power Quality Journal, vol. 10, p. 1809, 2012, doi: https://10.24084/repqj10.841.

[2] M. B. Danbatta, N. Al-Rawahi, and N. Al-Azri, “Satellite-Ground Temperature Correlation for Solar Energy: Insights from Oman,” JMCER, vol. 2025, pp. 1–9, 2025.

[3] M. B. Danbatta, N. Al-Azri, and N. Al-Rawahi, “Analysis of Solar Radiation and Remote Sensing Indices for Coastal Management in Oman.,” Journal EJENS-European Journal of Engineering & Natural Sciences, vol. 9, no. 1, 2024.

[4] M. Kolahi, S. M. Esmailifar, A. M. Moradi Sizkouhi, and M. Aghaei, “Digital-PV: A digital twin-based platform for autonomous aerial monitoring of large-scale photovoltaic power plants,” Energy Convers Manag, vol. 321, p. 118963, 2024, doi: https://doi.org/10.1016/j.enconman.2024.118963.

[5] G. B. Balachandran, M. Devisridhivyadharshini, M. E. Ramachandran, and R. Santhiya, “Comparative investigation of imaging techniques, pre-processing and visual fault diagnosis using artificial intelligence models for solar photovoltaic system – A comprehensive review,” Measurement, vol. 232, p. 114683, 2024, doi: https://doi.org/10.1016/j.measurement.2024.114683.

[6] H. Mao et al., “Advances and prospects on estimating solar photovoltaic installation capacity and potential based on satellite and aerial images,” Renewable and Sustainable Energy Reviews, vol. 179, p. 113276, 2023, doi: https://doi.org/10.1016/j.rser.2023.113276.

[7] A. Al-Janabi and N. Al-Azri, “Effect of recovering the industrial waste heat in Oman on energy and environment,” Energy Reports, vol. 6, p. 526, 2020, doi: https://doi.org/10.1016/j.egyr.2020.11.203.

[8] T. Zhong et al., “Assessment of solar photovoltaic potentials on urban noise barriers using street-view imagery,” Renew Energy, vol. 168, pp. 181–194, 2021, doi: https://doi.org/10.1016/j.renene.2020.12.044.

[9] S. Zhao, H. Chen, C. Wang, Y. Zhou, and Z. Zhang, “RGR-Net: Refined Graph Reasoning Network for multi-height hotspot defect detection in photovoltaic farms,” Expert Syst Appl, vol. 245, p. 123034, 2024, doi: https://doi.org/10.1016/j.eswa.2023.123034.

[10] A. Leonard, S. Wheeler, and M. McCulloch, “Power to the people: Applying citizen science and computer vision to home mapping for rural energy access,” International Journal of Applied Earth Observation and Geoinformation, vol. 108, p. 102748, 2022, doi: https://doi.org/10.1016/j.jag.2022.102748.

[11] M. B. Danbatta, N. Al-Azri, and N. Al-Rawahi, “Exploring the Impact of Solar Radiation on Environmental Dynamics in Oman Normalized Difference Vegetation Index (NDVI),” European Journal of Engineering and Natural Sciences, vol. 9, no. 1, pp. 15–19, 2024.