SolarMap AI: An AI-Based System for Personalized Solar Planning

Abstract: With the rapid growth in energy demand and the urgent need for sustainable energy sources, solar power has emerged as one of the most promising renewable energy options in India. However, widespread rooftop solar adoption in Maharashtra remains below its potential, primarily due to the lack of simple, reliable, and personalized assessment tools accessible to non-technical users. This paper presents SolarMap AI, an intelligent web-based platform that leverages artificial intelligence to simplify and personalize the complete solar planning process. The platform integrates real hourly solar irradiance and temperature data from the NASA POWER API with a pre-trained Random Forest (RF) machine learning model to estimate annual energy output. It performs financial analysis by computing installation costs per Ministry of New and Renewable Energy (MNRE) benchmark rates, PM Surya Ghar Yojana government subsidies, return on investment (ROI), payback period, and 25-year degradation-adjusted net savings. A site suitability score (0-9) is calculated using a Multi-Criteria Decision Making (MCDM) Weighted Sum Model across four factors: Solar Resource (GHI), Payback Period, Bill Coverage, and Roof Condition. Experimental evaluation across four Maharashtra cities — Mumbai, Pune, Nagpur, and Kolhapur — validates the system. The RF model achieves an R² score of 0.9400 after hyperparameter tuning. Results demonstrate that SolarMap AI successfully provides end-to-end personalized solar planning, empowering ordinary users to make informed decisions about rooftop solar adoption.

Keywords: Solar energy, Random Forest, NASA POWER API, MCDM, Rooftop solar, Machine learning, PM Surya Ghar Yojana, Maharashtra, Renewable energy, Energy prediction, Financial analysis