An AI and multi-criteria framework for siting renewable energy systems enhanced by graphene photovoltaics in a coastal City

This research analyzed and evaluated the factors affecting the productivity of solar, wave, and wind renewable energy systems in the coastal city of Tonekabon. We employed statistical and machine learning methods, including Linear Regression and Random Forest, on a dataset of spatial, climatic, and physical data from the region. This analysis identified key indicators and predicted the optimal performance of energy systems. A correlation analysis was also conducted to examine the relationships between these indicators. For the first time in this region, the role of graphene-based photovoltaic (GPV) was investigated. The results indicate that indicators such as optimal building orientation, height, density, vegetation cover, and climatic parameters significantly impact renewable energy productivity. Furthermore, GPV demonstrated a 13.8% improvement in annual average efficiency compared to conventional silicon cells in Tonekabon’s humid climate. This research proposes a framework for improving urban design and promoting sustainable energy development in coastal cities like Tonekabon.