Transcript
The following transcript is autogenerated so may contain errors.
Matt Nally
On this week’s episode, we have Nick, who’s the director. Absolutely. So thanks for coming on.
Nic Cory
Thanks very much, man. Thanks for having me.
Matt Nally
For those that don’t know, you want to give us a bit of background as to who you are and what you do at Absolar.
Nic Cory
Yeah, of course, from a personal point of view, I’m an accountant by training. But gave that up a long time ago, I did my degree in real estate at College of estate management a number of years ago now, three years ago, joined up with a few colleagues from University of Southampton from engineering and computer science, really, with a mission set out at AB solar to help accelerate the change to renewable energy across property. Interesting.
Matt Nally
And I suppose the three topics we’re going to cover today around this later will be the sort of future of the built environment. And we’re looking at solar specific solar, specifically on different buildings. But one of the first things I thought was really interesting with what you’re doing is the use of AI. And I suppose changing how you survey buildings in the first place. How do you how do you use AI to cover that process versus going out on site?
Nic Cory
Yeah, indeed. And it’s the the artificial intelligence, the various aspects are incredibly useful for how you repeat something at scale. You know, any surveyors are no, looking at one building, the results are normally pretty obvious. If suddenly, you’ve got 1000 buildings to look at, you need a bit of help to start assessing that. So we use a lot of our base data is LiDAR, if you’ve come across that, if not, in our case, it’s lasers bounced off a plane helps us understand the built environment underneath in sort of minut detail allows us to build a 3d model of what’s going on on the ground. We then have various bits of AI that can detect from those models. What’s a roofline? What’s a dormer window, what’s a skylight? So you can start to understand the makeup of a roof, which is obviously important when you’re looking at solar PV. So you can understand what are the roof assets? Which way is it facing? What’s What’s the pitch of that roof? Start to overlay a bit of satellite imagery. And you can essentially plot each solar panel, how much? How much can you fit on a roof across an entire city won’t go we actually measure in sort of five kilometre blocks. We then use a lot of radiation modelling to say how much power can a rooftop generate at every half hour across any given period of time. So you can begin to understand how much electricity can any rooftop generates within a particular environment? And then the rest is sort of pretty simple. pretty complex, but but in theory, pretty simple maths and business cases to then say, and should you actually go ahead and do that?
Matt Nally
How does it change the number of properties you might actually visit? And do a proper traditional surf roof survey on I suppose in terms of understanding whether solar can be fitted?
Nic Cory
Yeah, so I’m PV in particular allows you very quickly to say, is there enough Is there enough power that’s going to be generated on this rooftop compared to the the electricity consumption inside to even warrant investigating whether whether PV is suitable, so it allows you, you know, we within Uppsala, typically we can look at sort of 2000 buildings a day, and quickly whittled down which ones are those that are actually interesting to people? And which ones should they sort of park and either discount or kind of put at the back of the queue, particularly with emerging technologies, it’s key to get those quick wins first, to kind of get the adoption rates up and get everyone happy that technology does work. And we’re increasingly employing that in sort of air source heat pumps, identifying where is there space to instal that, you know, with all the noise requirements, for example, you can’t have them looking at a neighbor’s window. So allows you just to identify where they can go, or perhaps more importantly, where they can’t go where there are restrictions.
Matt Nally
Essentially, how does that compare to bidding 2000 a day? How does that compare to, I suppose, old process where it was literally just going out?
Nic Cory
Yet, we still do manual surveys, we still sort of for those that are suitable, we still go out we do three a day. So you can see the difference that you can get to and so recently, I think we did a study of Basingstoke there the entire sort of borrower of Basingstoke, you know, within within a week that’s it, you’ve understood where and Basingstoke is good and bad, as opposed to what would have been a two year study for a surveyor looking at buildings as
Matt Nally
a massive difference, is that is there an element then of? I suppose the question that we asked in every industry around AI is, could it replace surveyors long term? Or is it you’re always going to need that? Yeah,
Nic Cory
pretty confident that it won’t, you know, what it helps you do is do that identify stage pretty quickly. So it does, it helps you, it gives you a bit of shortcuts, you still need to go out and actually look at that building, if you are going to be doing a design or a specification. And it’s the grand old problem of real estate, you might have, you know, the nothing’s homogenous, you might have two buildings that are identical next to each other, actually, the tenants are different, the occupants is different, there’s, there’s a surrounding environment that’s slightly different, therefore, the requirements are totally different. So you still need that, that personal touch, that there’s no point training AI to to act over something that’s not entirely homogenous data set for the whole, the whole process, so helps you at the beginning of the stage, definitely needs to hand over to surveyors when you when you start getting getting into actually action.
Matt Nally
Yeah, I suppose it’d be interesting. With the development of smart buildings, and under this is a long way off. But obviously, there are some newer buildings are much smarter. And I know how many people are on each floor, how many people have scanned in what their usage of different things is, I suppose that could start to feed in the future. But you’re right, I think he’s always gonna need someone to actually have feet on the ground, see what’s going on?
Nic Cory
Yeah, it does. And also, you know, even our data, we gather data every two years, it’s out of date, you know, buildings change, if you’ve got a picture up to actually look, before you send your containers of panels to go on the roof, you’ve got a picture up and do that manual survey
Matt Nally
on that, on that note about containers or panels, I was walking through a field the other day that had what looks like 30 lorry loads of solar panels just in crates in a field. I’ve been there a long time. So I was intrigued as to what they were for. Well, I suppose what are the limitations of AI? Then? Is it is it the datasets in the first place? And
Nic Cory
yeah, you’ve got to train it. You know, it’s taken us two and a half years to get to the point where we can really realistically point at a roof and get results back that we’re comfortable with even then it’s kind of it’s a nine out of 10 success rate. And if you go and say it’s 90%, accurate, great, sounds wonderful. But actually looking at 10 buildings, that means one of your results is just slightly weird. It only takes one you know, if you’re looking at a portfolio and you look at a couple of results that look weird. As surveyors, we tend to say, well, I don’t trust the whole thing. So so it doesn’t need that the quality of data is reasonably good. AI is particularly bad, you know, it does miss it does. It doesn’t perform as you expect all the time. Therefore, you still need that manual review process that actually correct some of its errors.
Matt Nally
Is that something you are supposed to get better over time identifying? Yeah, sort of the odd anomalies, I suppose that are in the data or when the results are? Yeah,
Nic Cory
exactly. And we run two different types of calculation within within episode or when we’re looking at a property and that allows us to pick out well there’s there’s two disagreements here within the different AI model. So it allows us to spot spot those errors. But it needs it needs a human to sit in and resolve the argument that the two machines are having with each other.
Matt Nally
And with I suppose just continuing on the AI side of things, what do you think the changes will be as we go on? Because I suppose we obviously made quite your you’ve made quite good advancements are ready with being able to scan on scale, or analyse on scale. Yeah. What other applications? Do you think there might be going forward? Whether in this space or elsewhere? Because it’s quite an unknown area?
Nic Cory
It certainly is it certainly it’s certainly going to be opened up to more and more people, you know, at the moment, it’s still quite a novel thing. And surveyors get access to our type of stuff. But but but the end users don’t sort of get the instant access. And that will come with time. You’ve seen with open AI, kind of as soon as general public start to get access with AI, then come the mass adopters, but then also come the debates over over whether it’s whether it’s a good a good thing or not. We’re seeing a lot more rolling into actually monitoring our systems performing as expected. So am I getting value for money from what I’ve put in? And actually that’s where AI does have a good role to play, because on day one, you can feed in all the parameters that’s not going to change. And then you can get quick alerts as to when something’s going wrong within a system as opposed to What has happened in the last 10 years and solar PV and the system goes wrong, people turn it off, and they never turn it back on again. Which is, which is obviously frustrating. Yeah, definitely.
Matt Nally
So with the, I suppose case study was, I think you’d think it was the in Southampton, you’ve done a site already, haven’t you from start to finish? Yeah.
Nic Cory
So yeah, we’ve done like loads of sites from from start to finish. Yeah.
Matt Nally
How, how accurate? Have you found the, I suppose the analysis process through to, you know, when you’ve when you’re looking at how things are performing after installation, so And has it matched quite well to?
Nic Cory
It does so so it matches the radiation predictions. We also we also feed in what what are used, it’s, I can’t remember, it’s an acronym of N rail can’t remember the full name of it. So we feed in sort of industry standard calculations as well into that radiation data. So so it gives us a bit of robustness. There’s one site we are monitoring, in particular, because it has, we’ve put PV panels on every side of the roof, including the north side, which is, you know, bordering on on wrong, but actually, for that site was was the right solution because of a low pitch and high energy consumption. And it is, it’s within two to three kilowatts a month accurate, which is incredible accuracy. So we’re quite proud of that one, keeping to track that it only goes wrong when we have a serious weather event, when actually, there’s a heatwave, or we’ve got really bad weather for a while, in which case, we kind of have to allow allow for a bit of difference. There
Matt Nally
was an interesting point, there actually, is that getting more tricky than with weather patterns, seemingly being a bit all over the place at the moment.
Nic Cory
I can talk to that site. And in particular, it averages out to still being still being in line with expectations. So we have the kind of the extreme weather events that, you know, you can argue whether are one off or not, but actually, it’s still averaging out as as, as you would expect. So don’t see a material impact from
Matt Nally
everything. Okay, that’s my final question on this, then, on this particular part of it is, how’d you decide? Is it through the analysis process or later on between potential using solar or the heat pump side or installation? Where does that fit into the process,
Nic Cory
and our analysis will produce essentially summary business cases for interventions, so becomes quite, quite obvious early on, if you’re looking for financial payback, which ones are those that are going to be of interest, and how they interplay with each other. There are still restrictions outside of a business case as to whether you want to go ahead with something solar PV can be done when you’ve got occupants in the building, you know, isn’t going to isn’t going to impact on the tenancy. Obviously, going in and re insulating or changing a heating system means landlords are not going to be making those interventions. So the we present the information so here’s the impact it will have. But it has to be down to that end user as to how that fits into the realities of the building. How
Matt Nally
much does this suit commercial versus residential? Is it beneficial to both in the same way? Or does it suit sort of maybe a commercial, industrial industrial area better? It’s highly
Nic Cory
suited to commercial because each commercial property is so different, you know, the profile of an occupant within a commercial building, as well as the rooftop is so different, it does need that kind of bespoke assessment. Residential, you can actually start to apply some rules to various types of property and types of occupants. And so the NAI assessment is useful for a portfolio and then you can sort of start to extrapolate out. So you get less use on a per property basis on residential, but you get very good at sort of, if you’re trying to assess a city or or kind of, you know, a social housing portfolio works very well, for commercial works all the way down to each individual rooftop.