When you’re looking for a starter idea that can slow climate change, you can become an expert in home energy assessments. At least, that’s what happened to the founders of Kelvina French startup that uses computer vision and machine learning to facilitate home energy efficiency auditing.
Clémentine Lalande, Pierre Joly and Guillaume Sempé began studying home energy efficiency audits because renovations will have a huge impact on reducing energy and CO consumption.2 emissions. But, like the rest of the construction industry, most companies in this space do not use technology to improve their processes.
“There are 300 million homes to renovate over the next 30 years in Europe,” Lalande, CEO of Kelvin, told TechCrunch. “But the construction industry is the second least digitalized sector after agriculture.”
In France, the National Housing Agency (ANAH) has set the ambitious goal of reaching 200,000 renovated homes in 2024 alone. But craftsmen simply cannot keep up and, as a result, they are harming the climate. In more general terms, the regulatory landscape is favorable for this type of startups 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 Get intoanother home energy assessment startup based in Germany that TechCrunch coverednor does it want to be a customer-oriented product.
Instead, the startup has assembled a small team of engineers to create its own AI model specializing in home energy assessments using machine learning. The company uses open data, such as satellite images, as well as its own training data set with millions of photographs and energy assessments.
“We calculate more than 12 proprietary, semi-public or open data sources that provide information about the building and its thermal performance. That’s why 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, etc.,” Lalande said.
“We also do this with data we collect ourselves. “We have developed a remote inspection tool with a bot that tells the person there what photos and videos they should collect,” she added. “Then we have models that count radiators in videos, detect doors, detect ceiling height and 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. He allows you to use normal photos and videos, which means he doesn’t need a recent smartphone with a lidar sensor to record the details of a room.
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 making a decision.
In the company’s early tests, its home energy assessments were within 5% accurate of traditional assessments. And if it becomes the go-to tool for these audits, it will be much easier to compare one home to another and one renovation to another.
The startup has already raised €4.7 million ($5.1 million at current exchange rates), 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.
