• Monali Mahajan
• Divya Satish Bhavsar
• Khushi Manish Kshatriya
• Prachi Sachin Mehetre
• Samruddhi Parag Narkhede

The increasing global demand for renewable energy calls for intelligent, data-driven methods to optimize solar farm site selection. This study presents an automated framework integrating Landsat-8 satellite imagery, geospatial analysis, and deep learning to identify suitable solar installation areas. Using six input bands — Red, Green, Blue (RGB), Near-Infrared (NIR), Normalized Difference Vegetation Index (NDVI), and slope — a custom U-Net++ segmentation model classifies land into four suitability zones: Unsuitable, Loose, Medium, and Strict. The fine-tuned model achieved an accuracy of 89.6% and a mean Intersection over Union (mIoU) of 0.56, demonstrating strong generalization across varying terrains. The system integrates Google Earth Engine (GEE) for preprocessing and a React–Leaflet interface for real-time visualization, offering a scalable and sustainable approach to automated solar site planning and renewable energy mapping.

Deep Learning, Geospatial Analysis, Google Earth Engine (GEE), Landsat-8, Remote Sensing, Renewable Energy, Solar Farm Site Selection, Spatial Segmentation, Sustainable Development, U-Net++.

"Radiant: Solar Farm Site Selection Using Satellite Images", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.d538-d543, November-2025, Available :http://www.jetir.org/papers/JETIR2511357.pdf

"Radiant: Solar Farm Site Selection Using Satellite Images", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppd538-d543, November-2025, Available at : http://www.jetir.org/papers/JETIR2511357.pdf