When you’re looking for a startup idea that could slow down climate change, you might become an expert in home energy assessments. At least, that’s what happened to its founders Kelvina French startup that uses computer vision and machine learning to make it easier to control homes for energy efficiency.
Clémentine Lalande, Pierre Joly and Guillaume Sempé started looking at home energy efficiency audits because renovations will have a huge impact on reducing energy consumption and CO2 emissions. But like the rest of the manufacturing industry, most companies in this space are not using technology to improve their processes.
“There are 300 million homes to be renovated in the next 30 years in Europe,” Lalande, CEO of Kelvin, 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 houses by 2024 alone. But the craftsmen simply cannot keep up, and as a result it is hurting the climate. More generally, the regulatory landscape is favorable for this type of startup in Europe.
Founded in October 2023, Kelvin is a pure software play. The company does not want to create a market of service providers, and unlike Enteranother Germany-based home energy rating startup that TechCrunch coveredit also doesn’t want to be a customer-facing product.
Instead, the startup assembled a small team of engineers to build its own AI model that specializes in home energy assessments using machine learning. The company uses open data, such as satellite imagery, as well as its own training dataset of millions of photos and energy ratings.
“We calculate more than 12 proprietary, semi-public or open data sources that provide information about the building and its thermal performance. So we use fairly standard segmentation techniques, analyzing satellite images with machine learning models to detect specific features, such as the presence of adjacent buildings, solar panels, collective ventilation units and so on,” said Lalande.
“We also do this with data we collect ourselves. We have developed a remote inspection tool with a bot that tells the person who is there, the photos and videos to collect,” he added. “We then have models that measure radiators on video, detect doors, detect ceiling height and will determine the type of boiler or ventilation unit.”
Kelvin doesn’t want to use 3D technologies like lidar because he wants to create a tool that can be used at scale. It lets you use regular photos and videos, which means you don’t need a recent smartphone with a lidar sensor to record the details of a room.
The startup’s potential customers could be construction companies, the real estate industry, or even financial institutions looking to finance home renovation projects — financiers, in particular, may be looking for accurate estimates before making a decision.
In the company’s first tests, its home energy ratings were accurate to within 5% of old-fashioned ratings. And if it becomes the go-to tool for these checks, it will make it 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 angel investors also participated in the round.
