![Kelvin wants to help save the planet by applying AI to home energy audits | TechCrunch](https://cheapuggs.net.co/wp-content/uploads/2024/06/Kelvin-wants-to-help-save-the-planet-by-applying-AI.jpg)
When you’re looking for a startup idea that could slow climate change, you might become an expert at home energy assessments. At least, that’s what happened to the founders of Kelvin, a French startup that is using computer vision and machine learning to make it easier to audit homes for energy efficiency.
Clémentine Lalande, Pierre Joly and Guillaume Sempé started looking at home energy efficiency audits because renovations are going to have a massive impact on reducing energy consumption and CO2 emissions. But, like the rest of the construction industry, most companies in this space don’t use technology to improve their processes.
“There are 300 million homes to renovate over the next 30 years in Europe,” Lalande, Kelvin’s CEO, told TechCrunch. “But the construction industry is the second least-digitized sector after agriculture.”
In France, the National Housing Agency (ANAH) has set an ambitious goal of reaching 200,000 renovated homes in 2024 alone. But craftspersons simply can’t keep up, and it hurts the climate as a result. More generally, the regulatory landscape is favorable for this kind of startup in Europe.
Founded in October 2023, Kelvin is a pure software play. The company doesn’t want to build a marketplace of service providers, and unlike Enter, another home energy assessment startup based in Germany that TechCrunch covered, it doesn’t want to be a customer-facing product either.
Instead, the startup has put together a small team of engineers to create its own AI model specialized in home energy assessments using machine learning. The company uses open data, such as satellite images, as well as its own training dataset with millions of photos and energy assessments.
“We compute more than 12 proprietary, semi-public or open data sources that provide information on the building and its thermal performance. So we’re using fairly standard segmentation techniques, analyzing satellite images with machine learning models to detect specific features, such as the presence of adjoining buildings, solar panels, collective ventilation units and so on,” Lalande said.
“We also do this on data we collect ourselves. We’ve developed a remote inspection tool with a bot that tells the person who is in there, the photos and videos they should collect,” she added. “We then have models that count radiators in videos, detect doors, detect the ceiling height, and will determine the type of boiler or the ventilation unit.”
Kelvin doesn’t want to use 3D technologies like lidar because it wants to build a tool that can be used at scale. It lets you use normal photos and videos, which means that you don’t need a recent smartphone with a lidar sensor to record a room’s details.
The startup’s potential clients could be construction companies, the real estate industry or even financial institutions that want to finance home renovation projects — financiers, in particular, might be looking for accurate assessments before they make a decision.
In the company’s first tests, its home energy assessments have been accurate within 5% of old-fashioned assessments. And if it becomes the go-to tool for these audits, it will become much easier to compare one home to another and one renovation to another.
The startup has now raised €4.7 million ($5.1 million at today’s exchange rate), with Racine² leading the round and a non-dilutive investment from Bpifrance. Seedcamp, Raise Capital, Kima Ventures, Motier Ventures and several business angels also participated in the round.
![](https://techcrunch.com/wp-content/uploads/2024/06/kelvin_cofounders_1.jpeg)