Could ‘Google Maps of Heat Loss’ Help Decarbonise the UK?

“There is no scalable, cost-effective way to reliably figure out how much heat is being lost in the millions of buildings where we all live, work and play – let alone how to fix it and how much the repairs will cost,” says Lyons, co-founder of the tech start-up.

Since its launch in 2022, Kestrix has raised £1.7m from a mix of innovation grants and angel investors. It recently won Interior of the apartment award for net zero emissions innovation and caused some excitement around the difficult problem of home retrofitting.

The interest in Kestrix is ​​focused on its new approach to measuring heat loss in buildings at a rapid pace and on a large scale. Lyons says this will be essential if we are to meet net zero emissions targets. A total of 29 million homes in the UK need to be retrofitted, according to the UK Green Building Council. But EPCs overestimate energy use by 300%, and on-site surveys are prohibitively expensive, sometimes costing more than £275 for a home visit.

Lyons and her co-founder Matt Goodridge are unable to resolve the huge question marks over how such a massive refurbishment programme can be funded and delivered. Part of their solution is to provide much-needed data to help social landlords plan and prioritise work, and eventually work towards mapping heat loss.

“We’re building a retrofit data layer, like the ‘Google Maps of heat loss,’” Lyons says. Kestrix uses thermal drones and artificial intelligence to build 3D models of building heat loss and reveal retrofit opportunities in seconds without requiring site visits.

Lucy Lyons I met my co-founder Matt Goodridge at Carbon 13 Venture Builder, a program where you come in as a solo entrepreneur and you meet other founders in the same room and you’re all challenged to build new ventures that have the potential to reduce or avoid 10 million tons of carbon emissions per year. I worked at tech startups in Germany – although I’m from Boston – and I had the opportunity to work at Plan A, which was the first B2B carbon accounting software platform to launch in Europe.

Then in the UK I did a masters in sustainability and entrepreneurship and then I joined Carbon 13. I think the biggest lesson for me when I was working at these other startups was when you were first starting out, it’s less about what you’re building and more about who you’re building it with and what kind of relationships you have with those people.

That was my reason for joining the Carbon 13 accelerator: there were a lot of like-minded people there.

Matt has a background in high-tech product management. He worked at Google for 10 years and has a college degree in engineering and computer science with a focus on computer vision. He also had an interest in buildings and retrofitting. But it wasn’t until we decided to work together that he revealed he was working on a 3D heat loss model for residential construction. He also had a hobby with drones and wondered if it would be possible to detect leaks in buildings using drones.

That’s when the light bulb went off for me and I realized this was a non-invasive, highly technical way, specific to a building’s asset class, to figure out how to decarbonize multiple buildings at once.

We hear from everyone that EPCs are not fit for purpose – they don’t give you a clue as to how much it costs to run a house, how to fix it, or even what’s wrong with it or where the heat is coming from. We’ve pitched our idea to a lot of people in the home building world and the response we’ve had from suppliers and contractors is ‘if you build it, we’ll buy it’.

A series of grants from Innovate UK have enabled us to develop an algorithm that can quantify heat loss from thermal images. Rapid Thermal Performance Assessment (RaThPA) AI technology can estimate energy loss in kWh/m²/year of each home in a property provider’s inventory. This allows asset managers to prioritize which buildings require retrofitting.

It basically takes thermal analysis to the next level. It analyzes the thermal image captured by the drone and calculates the heat loss quantitatively, so it estimates the U-values ​​of individual components of building materials and provides a measure of the overall space heating requirement or heat loss.

This is incredibly useful if you’re a housing provider like Peabody who’s working on one of our projects and you’ve got between 100 and 4,000 homes that you need to decarbonise. You can scan them all with our technology and find out from AZ which home is the most leaky and which one needs support without having to do a lot of fieldwork. This is really important when housing providers are bidding on the Social Housing Decarbonisation Fund where you need to make sure that the properties that are part of the bid are EPC D or below.

I have spoken to property providers who submit 1,000 offers for houses and then carry out PAS 2035 assessments on all of them only to find that half of them have an EPC rating of B, not D, forcing them back to the drawing board – after wasting hundreds of thousands of pounds on PAS 2035 assessments.

We are working on pilots with nine major housing providers, including Clarion Homes, Peabody and Places for People. We are also working with the National Trust to test the algorithm and improve its accuracy.

Kextrix currently employs 12 people. We have scanned around 1,900 homes with a drone and these images go through our system and the data is returned to the housing provider. We have a specialist thermographer and a surveyor who can help identify thermal anomalies.

We basically sell surveys and depending on the detail of the data you can get a full thermal assessment that is a small fraction of the price of most thermography. Once this is up and running at scale we will do a combination of software and data licensing. So if you are a housing provider you can use the API to connect our analytics software to your existing asset management systems.

Housing providers will also be able to license the dashboard to help organize their data. We are still finalizing our commercial arrangements.

The algorithm is still being refined – it’s a never-ending journey, optimizing algorithms. We’re really focused on accuracy. We want Kestrix to become reliable enough to be used as a national standard for home heat loss, given that there aren’t enough skilled people or resources and time to go into every home and figure out what we need to do.

The idea is that we end up in a situation where we are mapping every home in the UK and the system is used by a variety of entities, such as housing providers, but also energy companies, lending institutions, government and installers.

We think we provide a plan of what needs to be done, and then the hard part begins. Of course, this does not solve all the problems. There are too few skilled people to do the modernization work, and the financial part is not available.

But people say you can’t manage what you can’t measure – and you can’t fund it either. So private finance, as well as subsidies, can’t be allocated until we can make a business case for why they should be allocated and where, and then use that data to track progress and confirm that the funds are actually being used to reduce emissions and address fuel poverty.

We are still working on analyzing the properties we scanned. Once the algorithm development is complete, we will be able to quickly understand what is the priority in the 3,000 building set and then we will start to see the return on investment.

I hope that data can give us the push that we need. As I said, it does more to unlock funding than anything else. And if you unlock funding, you create a lot more stability in the supply chain, and that’s really what’s needed to scale the workforce.