If you are looking for a start-up idea that might decelerate climate change, you may turn out to be an expert in assessing your home energy consumption. At least that was the case with the founders Kelvina French start-up that uses computer vision and machine learning to make it easier to audit homes for energy efficiency.
Clémentine Lalande, Pierre Joly and Guillaume Sempé have began looking at home energy efficiency audits because renovations will have a huge impact on reducing energy consumption and CO emissions2 emissions. However, like the remainder of the construction industry, most corporations in this industry do not use technology to improve their processes.
“There will be 300 million homes to renovate in Europe over the next 30 years,” 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 homes in 2024 alone. But craftsmen simply cannot sustain, and as a result, it is harming the climate. More generally, the regulatory landscape favors these kinds of start-ups in Europe.
Founded in October 2023, Kelvin is a pure software play. The company does not want to build a market of service providers and more Enterone other home energy assessment startup based in Germany Covered by TechCrunchnor does it want to be a customer-facing product.
Instead, the startup assembled a small team of engineers to create its own artificial intelligence model specializing in assessing home energy use using machine learning. The company uses open data reminiscent of satellite imagery, in addition to its own training dataset containing hundreds of thousands of images and energy assessments.
“We calculate over 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 imagery with machine learning models to detect specific features such as the presence of neighboring buildings, solar panels, collective ventilation units, etc.” – said Lalande.
“We also do it based on data that we collect ourselves. We have developed a remote inspection tool equipped with a bot that informs the person there what photos and videos they should collect,” she added. “Then we have models that count radiators in the videos, detect doors, detect ceiling heights and determine the type of boiler or ventilation unit.”
Kelvin doesn’t want to use 3D technologies like lidar because it wants to build a tool that could be used on a large scale. It allows you to use regular photos and videos, which suggests you do not need the latest smartphone with a lidar sensor to capture room details.
The startup’s potential customers could include construction corporations, the real estate industry, and even financial institutions looking to finance home renovation projects – financiers in particular could also be looking for accurate assessments before making a decision.
In the company’s first tests, the accuracy of home energy estimates was inside 5% of old-fashioned estimates. And if this becomes the important tool of such audits, it should be much easier to compare one house with one other and one renovation with one other.
The startup has now raised €4.7 million ($5.1 million at today’s exchange rates), with Racine² leading the round and Bpifrance making a non-dilutive investment. Seedcamp, Raise Capital, Kima Ventures, Motier Ventures and several angel investors also participated in the round.