# Rooftop solar potential from satellite and aerial data A roof suits solar panels when its area, tilt, orientation and shading fit and enough solar radiation reaches it. Databases such as PVGIS derive that radiation from satellite images. AI on satellite imagery can detect existing panels, and machine learning can estimate rooftop area at scale. In solar cadastres such as Styria's, the roof geometry comes from airborne laser scanning. ## How a rooftop solar analysis works A roof suits solar panels when it has enough usable area, a favourable tilt and orientation, little shading from neighbouring buildings and trees, and when enough sunlight reaches the site over the year. An analysis answers these points roof by roof. The solar cadastre of the Austrian region of Styria shows how this works in practice. A high-resolution surface model from airborne laser scanning describes the roofs. GIS methods then calculate the annual direct and diffuse radiation on a 1 by 1 metre grid and sort the roofs into three classes: very well suited, well suited and suited. For photovoltaics, the result includes the expected annual yield and the peak power in kWp [1]. Satellites contribute in two ways. Their images are the basis of solar radiation databases such as PVGIS [2]. And deep learning on satellite imagery can find existing solar panels and estimate their size [8]. Machine learning and geospatial analysis have also been used to estimate rooftop area and solar potential for the whole globe [7]. **Figure:** The radiation is computed on the roof model itself. Satellite radiation data, with a resolution of a few kilometres, is too coarse for single roofs. Detecting existing panels by AI is a separate layer. Illustrative street, not real data. The European Solar Rooftops Initiative aims to unlock the large and underused solar potential of roofs in the EU [9]. ## Data and satellites - **Solar radiation:** Satellite-based, METEOSAT, about 4 km resolution, long time series (PVGIS) - **Roof shape:** Airborne laser scanning, results on a 1 m grid (Styria) - **Very high resolution satellite:** 30 cm per pixel (Pléiades Neo) - **Free optical satellite:** 10 m per pixel (Sentinel-2) **Solar radiation.** The European Commission's PVGIS tool estimates solar radiation from METEOSAT satellite data, at about 4 km resolution below the satellite, and offers long time series [2]. The Copernicus Atmosphere Monitoring Service provides time series of solar radiation for a chosen point, which helps to plan both large solar farms and rooftop installations [3]. **Roofs and existing panels.** Commercial satellites such as Pléiades Neo record images at 30 cm resolution [5]. The DeepSolar framework analysed satellite imagery with deep learning to locate solar panels and estimate their size across the contiguous United States [8]. ## What you get - **A suitability class per roof**, from very well suited to suited [1]. - **Expected yield and peak power** for each classified roof [1], as a basis for offers or for advice to citizens. - **A map of existing installations**, to see where panels already exist and where the potential is still open [8]. Energy companies can use such results to decide where to offer systems, which [automating the sales of renewable energy systems](https://leto.space/use-cases/renewable-energy-sales/) describes. Municipalities can use them to inform citizens and to plan their own buildings. ## Limits **Limits** - **Satellite radiation is coarse:** Satellite-based radiation data has a resolution of a few kilometres \[2]. Shading by a neighbouring building or tree must come from a detailed surface model of the roofs. - **One image shows no tilt:** A single image from above shows the outline of a roof, not its tilt. Tilt and orientation need elevation data, which in Styria comes from laser scanning \[1]. - **What a map cannot show:** A map does not show the load capacity of a roof, its condition, who owns the building or whether the grid connection has capacity. These points need a check on site and with the grid operator. ## How we help Regional cadastres, satellite archives, commercial imagery and AI providers all offer parts of this analysis. In [strategy and use cases](https://leto.space/consulting/strategy/) we work out what the result must decide and which data source gives the accuracy you need at a price that fits. [Spacegraph](https://leto.space/spacegraph/), our discovery platform, has use-case categories such as "Object detection & counting" and "Site selection & spatial planning". ## Related use cases - [Automating the sales of renewable energy systems](https://leto.space/use-cases/renewable-energy-sales/): Which data helps sales teams find the right buildings. - [Selecting sites for solar parks and wind farms](https://leto.space/use-cases/site-selection/): How satellite data narrows the search for larger sites. - [Satellite data for energy and utilities](https://leto.space/industries/energy-and-utilities/): All use cases for energy companies. ## Frequently asked questions ### Which data does a rooftop solar analysis need, and how current is it? It needs a model of the roofs with their tilt, orientation and shading, and solar radiation data for the site. In Styria, for example, the model comes from airborne laser scanning, and the radiation is calculated on a grid of 1 by 1 metre [1]. Satellite-based radiation data covers long time series, up to 30 years or more [2]. The roof model is only as current as the survey or imagery it is built from, so check its date. ### Can free Sentinel-2 images find suitable roofs? Hardly. Sentinel-2 records its finest bands at 10 m per pixel [4], too coarse to show the shape of a single roof. Commercial satellites such as Pléiades Neo reach 30 cm [5], and the aerial imagery used by the Copernicus Emergency Management Service 10 to 20 cm [6]. ### How do we start? Check first whether your region already publishes a solar cadastre, as Styria does [1]. If it does, the task is often to combine it with your own data, not to build a new map. If it does not, a pilot over one district shows which data source gives the accuracy you need at a price that fits. Our [consulting overview](https://leto.space/consulting/) shows the path from the problem to operation. ## Sources 1. [Solarpotenzial Steiermark, Land Steiermark, accessed 2026-10-06](https://www.technik.steiermark.at/cms/ziel/99241573/DE/) 2. [PVGIS: Data sources and calculation methods, European Commission, Joint Research Centre (JRC), accessed 2026-10-08](https://joint-research-centre.ec.europa.eu/photovoltaic-geographical-information-system-pvgis/general-information/data-sources-calculation-methods_en) 3. [Solar energy, Copernicus Atmosphere Monitoring Service (CAMS), accessed 2026-10-06](https://atmosphere.copernicus.eu/solar-energy) 4. [Sentinel-2: Facts and figures, European Space Agency (ESA), accessed 2026-10-06](https://www.esa.int/Applications/Observing_the_Earth/Copernicus/Sentinel-2/Facts_and_figures) 5. [Pléiades Neo, European Space Agency (ESA), Earth Online, accessed 2026-10-06](https://earth.esa.int/eogateway/missions/pleiades-neo) 6. [Using Earth Observation Data, Copernicus Emergency Management Service, accessed 2026-10-06](https://mapping.emergency.copernicus.eu/about/using-of-earth-observation-data/) 7. [High resolution global spatiotemporal assessment of rooftop solar photovoltaics potential for renewable electricity generation (Joshi et al., Nature Communications 12, 5738), Nature Communications, 2021-10-05](https://doi.org/10.1038/s41467-021-25720-2) 8. [DeepSolar: A Machine Learning Framework to Efficiently Construct a Solar Deployment Database in the United States (Yu et al., Joule 2, 2605 to 2617), Joule, 2018-12-19](https://doi.org/10.1016/j.joule.2018.11.021) 9. [EU Solar Energy Strategy, COM(2022) 221 final, European Commission, EUR-Lex, 2022-05-18](https://eur-lex.europa.eu/legal-content/EN/TXT/HTML/?uri=CELEX:52022DC0221) Page: