# Automating the sales of renewable energy systems Parts of selling solar and other renewable energy systems can be automated by combining data on buildings, roof suitability, solar radiation and existing installations. Solar cadastres rate roofs and estimate their yield. AI on satellite imagery can detect panels that already exist. Sales teams can then rank prospects before anyone visits a site. ## The task Selling solar and other renewable energy systems to building owners takes work before the first offer: finding buildings that suit a system, checking the roof, estimating the yield and finding out whether a system already exists. When these checks run by hand, every prospect that turns out not to fit costs that work again. Automation moves these checks to the start of the process. Data on every building in a sales region is combined, each building is scored, and the team works through a ranked list instead of a map. ## Which data helps - **Roof suitability**: regional solar cadastres sort roofs into suitability classes and estimate their yield [1]. How these analyses work is explained in [finding rooftops suited to solar power](https://leto.space/use-cases/rooftop-solar-potential/). - **Solar radiation**: how much sunlight reaches each location over the year, from satellite-based databases such as PVGIS [2]. - **Existing installations**: deep learning on satellite imagery can locate panels and estimate their size [3]. A roof that already carries a system is a different sales case, for example for storage or an upgrade. - **Your own data**: customer records, contract end dates and grid information, which no satellite provides. ## How the automation works 1. **Define the target**: the sales region, the customer segment and the product, for example commercial roofs for photovoltaics with storage. 2. **Collect the layers**: roof suitability, radiation and existing installations for every building in the region. 3. **Score and rank**: the layers are combined into a score per building, using fixed rules or a model trained on past sales. 4. **Hand over**: the ranked list goes into the CRM, with the key facts per building, so the team prepares each contact with data. 5. **Learn**: the results of each contact flow back into the scoring. **Figure:** A higher score means a more promising contact. Roofs that already carry panels are flagged as a case for storage or an upgrade. Illustrative list, not real data. ## Limits **Limits** - **The roof itself needs a site check:** Data narrows the list, but it does not show the condition or load capacity of a roof. A technical check on site remains part of every offer. - **Data ages:** Roof models and imagery show the state at the date of the survey or image. Buildings and panels added since then are missing. - **Personal data:** Linking roof data to the owners of private homes creates personal data \[4]. The process needs a legal basis and a clear rule for how data is used. ## Our client project in this sector One of our four anonymised client projects covers this topic, at an energy company. It used Earth observation and AI. ### Client project in energy and utilities - **Topic:** Automating the sales of renewable energy systems. ## How we help A ranked list is useful only once it reaches the CRM and the daily sales routine. In [strategy and use cases](https://leto.space/consulting/strategy/) we test the business case for your sales region; in [implementation](https://leto.space/consulting/implementation/) we run the pilot with KPIs and take it into daily sales work. To find providers of roof analyses and imagery, [Spacegraph](https://leto.space/spacegraph/), our discovery platform, has an industry category "Energy & Utilities". ## Related use cases - [Finding rooftops suited to solar power](https://leto.space/use-cases/rooftop-solar-potential/): How roof suitability is calculated, and what the data cannot show. - [Selecting sites for solar parks and wind farms](https://leto.space/use-cases/site-selection/): The same logic for larger sites: layers, criteria and a ranked shortlist. - [Satellite data for energy and utilities](https://leto.space/industries/energy-and-utilities/): All use cases for energy companies. ## Frequently asked questions ### Which data sources can feed an automated sales process for solar systems? Roof suitability and yield from a solar cadastre, such as the one published for Styria [1], solar radiation for each location [2], and a map of the panels that already exist [3]. Your own customer and grid data complete the picture. ### Does data protection law apply to roof data? It does as soon as the data relates to an identified or identifiable natural person, for example when roof data is linked to the owner of a private home [4]. Clarify the legal basis with your data protection officer before the first campaign. ### How do we start? Start with one sales region and one product, and compare the ranked list with the results of your current approach over a few months. This shows whether the data improves the hit rate before you integrate it into your CRM. Our [consulting overview](https://leto.space/consulting/) shows the path from the problem to the pilot. ## 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. [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) 4. [Regulation (EU) 2016/679 (General Data Protection Regulation), Article 4(1), European Union, EUR-Lex, 2016-04-27](https://eur-lex.europa.eu/eli/reg/2016/679/oj/eng) Page: