A single smartphone photo of a rooftop is now enough to predict exactly how much solar energy a panel there will produce.
April 29, 2026
Original Paper
Forecasting Solar Energy Using a Single Image
arXiv · 2604.21982
The Takeaway
Estimating solar potential usually requires expensive 3D sensors or complex historical weather data. This new system uses a single image to map out shadows and light patterns for any specific location. It handles the messy geometry of urban environments like trees and power lines automatically. The software turns a complicated engineering problem into a simple point and shoot task. This makes it cheap and easy for homeowners to decide if solar panels are actually worth the investment.
From the abstract
Solar panels are increasingly deployed in cities on rooftops, walls, and urban infrastructure. Although the panel costs have fallen in recent years, the soft costs of installing them have not. These soft costs include assessing the illumination (irradiance) of a panel, which is typically performed using a 3D model that fails to capture small nearby structures that impact the irradiance. Our approach uses a single image taken at the panel's location to forecast its irradiance at any time in the f