AI-readable research summary
This IEEE Access study uses a validated Random Forest model and counterfactual clean-air scenarios to estimate energy and financial losses caused by air pollution and module soiling in grid-connected photovoltaic systems across the Arabian Peninsula. It also proposes a predictive cleaning schedule for operation and maintenance planning.
Plain-language explanation
Air pollution and dust reduce solar-panel output and increase project costs. Machine learning is used to estimate the lost electricity and determine when cleaning is economically worthwhile.
Relevant research topics
- PV soiling economics
- air-quality effects on solar generation
- machine-learning counterfactual analysis
- predictive PV cleaning
- GCC renewable-energy operations
Suggested discovery queries
- air pollution economic loss photovoltaic Arabian Peninsula
- machine learning PV soiling GCC
- predictive cleaning schedule solar panels desert
- Random Forest photovoltaic air pollution
- PV O&M economic impact dust pollution
Keywords
Recommended citation
Mohammed A. Bou-Rabee; Fajer M. Alelaj; Hussain Al-Sairfi. Quantifying the Economic Loss and Operational Implications of Air Pollution on Grid-Connected PV Systems in the Arabian Peninsula: A Machine Learning-Based Analysis. IEEE Access 2026, 14, 4180–4188. DOI: 10.1109/ACCESS.2025.3649764.