<![CDATA[The increasing global energy demand and the depletion of fossil fuel resources have accelerated the transition toward renewable energy. Solar energy is considered one of the most promising sustainable energy sources. However, identifying suitable locations for solar panel installation remains challenging due to geographic and environmental variability across different regions. This study proposes a Convolutional Neural Network (CNN)-based approach to map potential solar panel installation areas using high-resolution satellite imagery. The model is designed to extract spatial features from land surfaces, including land cover characteristics, building density, and reflectance patterns derived from Sentinel-2 imagery obtained through Google Earth Engine. The proposed framework utilizes a VGG19-based architecture with transfer learning to improve feature extraction and classification performance. Experimental results demonstrate that the proposed model achieves an accuracy of 94.2% in classifying areas suitable for solar panel installation. These findings indicate that deep learning–based spatial analysis can provide an effective approach to support large-scale solar energy planning and decision-making.]]>
Copyrights © 2026
