The Nextspace™ Broadcast

Episode #005 Building satellites for thermal imaging with Satellite Vu

[Rachana, Host]
Hello and welcome to another episode of The Next Space Broadcast, brought to you by Reflex Aerospace. Today, we have two guests joining us from SatelliteVu, who operate in the high resolution thermal imaging space. And they are going to launch their first thermal imaging satellite in June 2023,. Fingers crossed. I hope everything works out great for you guys.

We have Tobias Reinicke, the co-founder and CTO of SatelliteVu joining us. He has a background in geography and GIS. And we also have Alex Gow, the sales director of SatelliteVu, who also has a background in geology. Alex and Tobias, welcome to the podcast.

[Satellite Vu]
Very much. Nice to meet you.

[Rachana, Host]
Great. So today's discussion is going to be very interesting because SatelliteVu operates in both the upstream as well as the downstream segments of space. On the upstream segment or the satellite segments, you guys are building thermal imaging payloads and on the user segment, which is the downstream segment, you are offering a lot of these image analytics and insights into infrastructure, water pollution and energy, using thermal imagery.

So perhaps we can alternate talking between these two themes, to keep it interesting for the listeners.

[Satellite Vu]
Of course!

[Rachana, Host]
So let’s dive right in and perhaps start with a little bit of introduction into what kind of thermal imaging satellites, in terms of spectral bands and spatial resolutions, that are currently in operation? And how much of this imagery is available commercially?

[Satellite Vu]
Yeah, it's a great place to start. Historically, the only commercial system available at the moment that we can get our hands on is the Landsat. And that gives you data of about a hundred meter pixel resolution. And so it's used as a broad area for surveys, etc, but it's quite limited in terms of its revisit. The types of applications we are focused on, this data doesn’t help with them.

It just doesn't apply enough resolution to solve some of these problems. There are a number of other commercial systems coming online in the next few years that are really targeting agricultural applications, but these are still quite low resolution. And so if you look at really what's commercially available, it has to be done with either an aerial or drone system at the moment to get down to that building level thermal measurements.

So there really is no alternative to what we're providing.

[Rachana, Host]
And so thereby, you're building your own satellite constellation eventually. And one of the biggest challenges as far as I know in building thermal imaging satellites is in minimizing the onboard thermal noise. Right. Are there any other requirements on the satellite bus that are unique to a thermal imaging system?

[Satellite Vu]
Yeah, it's unique to a high resolution thermal imaging system. Let's say Landsat, like we just talked about, is a satellite that can just hover up imagery as it goes above the Earth. But we have a much smaller, a much higher resolution swath. And because the ground is moving at seven kilometers a second underneath the satellite, we actually need to stop and stare and track the earth as we cover it.

So we have to move the satellite itself in space to track the point on the earth, which is pretty novel and doesn't necessarily get done in many other methodologies on other imagery or SAR satellites. So that's a big one. The other one for thermal specification is, the thermal detectors need to get corrected or the data needs to be corrected on non uniformity.

So there is going to be weird behaviors in the pixel responses according to what's happening on the ground and the light coming in. That needs to be corrected. And traditionally you can do that by taking imagery of big homogenous areas on the ground such as deserts, ice caps, etc. But we have actually on-board capability that allows us to capture data from an.

On-board pattern, which gives us a much more flexible system. And then finally we have a satellite that can take imagery day and night. And that's super exciting. Obviously, being able to take images at night is going to be really great. If you are doing daytime thermal imaging, it poses its own challenges in that we have a lot of solar reflection issues effectively, so we see a lot of reflection coming back into the spectrum that we're in.

So on the satellite again, we have a day filter which will cut that out. And those have been design choices that have been made throughout the time building the satellite.

[Rachana, Host]
Now that you mentioned onboard capability and a lot of this onboard processing, how does the whole data processing chain, the payload data processing chain work on-board the satellite?

[Satellite Vu]
So at the moment, regarding the design constraint, we are not in space yet, so the answer to that is it’s not. But when we go to space, the design of the payload processing is that the majority of the data or all the data will be downlinked by your usual satellite ground station mechanisms, and the data processing will be primarily done on the ground, in cloud.

There is a limited amount of usability of processing on the satellite initially. Typically, the onboard processing is done for minimizing data size, to increase or decrease data latency. We, for better or for worse, aren't a big data company. Our data is going to be fairly limited in size because we are such high resolution and fairly small swath.

So we are perfectly capable of downloading all the data at once. It doesn't mean that we don't want to do more onboard. And whilst compression and pre-processing of the data onboard is going to be something that we will definitely do, the more interesting things are looking at detecting hotspots and even detecting and outlining hotspots so that you can basically pass down that sort of information on a very low latency link to the customers.

So if you you're fighting fires and the satellite can do an automatic fire threshold detection, draw a polygon around it and send it to the fire fighter within minutes, that’s massive. And that's where we want to get to at some point.

[Rachana, Host]
So lots more requirement for having high computing FPGAs on board then. And speaking of image processing or data processing, Alex, perhaps this is a question for you. So how does the whole thermal image processing happen on ground and how do you see this evolve in the future?

[Satellite Vu]
It might be a better question for Toby, but I think the key thing I think we're going through at the moment is deciding what is the data format that our customers most want to use? What the processing level? And with thermal data, they're inherent inbuilt limitations around such as - does a customer need absolute temperatures? Are they able to use our data in a relative sense for relative temperature, simply comparing temperatures between different surface types? what do they actually need to know about the absolute temperature of an object on the ground? And that's kind of leading our approach to these processing levels. And the development steps were taken together and it's really customer driven in terms of that demand.

So those are the products we talk about in terms of how accurate and what is the sort of response of the thermal analysis on that product. Such as absolute temperature like Alex said. Prior to that, we do need to correct for things that any other satellite manufacturer and imager has to do. So we've got our geo-referencing pipeline.

We need to make sure that the pixels that we capture are on the right place on the Earth so that people can derive insights. The other process that we need to do is, we do that calibration on the ground using the data that we get from the space, and then we start processing against a massive database of known materials to create some of these products that we have.

[Rachana, Host]
So creating databases and calibration - which is the usual image processing stuff I would assume. And I'm assuming that you are currently focusing on building the thermal payload and not the rest of the satellite. And you are procuring the satellite platform commercially?

[Satellite Vu]
So we actually have a really good relationship with SSTL, Surrey Satellite Technology Ltd based out of the UK, Guildford. So the payload on the satellite is their design, procurement and their build. They have a relationship with a detector manufacturer which they've embedded into the design of their CARBONITE platform. And this is very much the reason why we've been as successful as we have been and have been so attractive to investors is because we're using something that's flown before in terms of the actual structure of the bus that has gone up many times like their CARBONITE series. SSTL is looking at doing a SAR product with their CARBONITE platform. So it very much used what we've done before and now need to spend the effort in making sure the payload works. Yes, there's different things we need to do in terms of power consumption and thermal outputs, but a lot of the prior work that would be very risky for us to have done ourselves is de-risked with heritage and parts that have flown in space already. So that's the relationship we have with SSTL and it’s working very well so far and we are keen to see the satellite wrapped up and shipped in May over to Vandenberg to get launched on the 10th of June.

[Rachana, Host]
Of course, SSTL has a fantastic track record! Apart from flight heritage, are there any other design considerations when you look for a commercial provider of the satellite bus?

[Satellite Vu]
We very much from the customers and users perspective, talking about what it is that they want, right? So there's no need to design something for the sake of designing a cool piece of technology. If no one's going to buy that, then you need to get away from it. So we are very much customer focused. Everyone wants high resolution, everyone wants lower latency.

Everyone wants smaller sized. Some of those are easier to do than others. Higher resolution would mean a slightly different satellite because it's a bigger mirror, etc. But when it comes to on-board, we talked about on-board already, that actually offers customers quite a big thing that they care about. So pre-processing, immediate data downlinking. We’re also talking about inter-satellite links and the hardware on the satellites as well.

And that's again big for us, which means we don't have any latency in terms of connecting to the ground station, uplinking schedules, etc. It's immediate whenever we want. And then for future iterations, we're looking at all sorts of things such as extra spectral bands in the detector, secondary detector, as well as larger capacity into satellite links, allowing us to download the payload data immediately.

So we are very much looking at the customers needs and trying to react to that. We will be working with SSTL clearly really, because we can't just say now we're going to put a whole new mirror on that and they turn around and say it's going to take forever. It's very much working with them saying what is realistic and what is actually going to meet the customer's needs.

[Rachana, Host]
Do you intend to eventually at some point, maybe into the far future build your own satellite platforms? Or do you just prefer to stay with the payloads?

[Satellite Vu]
We've had a good relationship with SSTL as a supplier. There's absolutely no reason for us to change that relationship and change the way we do it. I think we've progressed from being focused on the downstream customer interactions, making sure the data is correct, deploying the data and now we are basically ready to sell data already.

We may not have been in that position if we had hired payload manufacturers, engineers and started building our stuff ourselves. It is riskier for sure than getting the experts to do what they've got 10 years of experience already doing.

[Rachana, Host]
Maybe one last question about the commercial satellite platform - in what all stages of the satellite development do you wish to participate or do you usually participate? In the design reviews or the requirement reviews or at what all stages?

[Satellite Vu]
Absolutely everything. For better or for worse, we’re always there. We are the customer for SSTL particularly. At the design review, we put specifications together as to what it is that we require. At the initial critical and preliminary critical design reviews we’re there to make sure everything's going on track. And any adjustments that have been made, we are there to understand the limitations - sometimes the physical, sometimes the timely, and we have to make decisions about what gets done or not. But again, everything comes back to Alex and his team about what if we give up X, how does that affect when it comes to potential revenue and such commercial insights.

[Rachana, Host]
So at the end of the day, it's all about tradeoffs and what the customer wants.

[Satellite Vu]
Oh, absolutely. We don't need to build the 100% perfect satellite, first off. So let's get 80% that caters to the requirements and then we have another seven satellites to improve upon. So we're like working in the agile sort of methodology. So that's how we approach that as well.

[Rachana, Host]
Yeah, absolutely. Space is hard and nothing is really perfect in space. So if it works, then that's perfect enough. So I posed a lot of questions and probed into this topic because for a satellite manufacturer like Reflex, it's very interesting to know what goes on in the mind of the payload designer. At Reflex, I am a part of the engineering team and then we have these reviews and a lot of these discussions and meetings every week, every quarter.

And it's a good perspective to have and to think from the perspective of someone who's actually going to use the satellite platform as the payload manufacturer. Now maybe we can switch back to the data segment or the user data segment. So perhaps this is more of a sales question.

I'm assuming you also fuse optical or near-infrared or SAR or other kinds of imagery with your thermal imagery to achieve all these insights into water pollution or infrastructure or other areas. And if so, how do you procure these images? And do you see any inadequacies in terms of spectral bands or spatial resolution or frequency of imaging, or geographical coverage in the images of these other bands?

[Satellite Vu]
It’s a very interesting area and it kind of changes depending on the application we're looking at. But we were quite lucky in the sense that a thermal image is an optical image. And it's quite simple for someone to look at it and kind of intuitively understand what is hot and what is cold. It is quite a common thing that people come across..

But I think the key thing that we have to do is put the data into context of where we're looking. So quite often in terms of simple use of other datasets, it's all about providing context. So like using an optical base map or something to provide that context there. What are you looking at? What is providing that thermal change? So typically we're still using mostly sort of open source datasets to do that work at this stage.

But we've very much taken a kind of first approach, in a commercial sense, to find partners that have other optical payloads where our thermal data could be really complementary. We got a number of opportunities whereby we can complement an optical system by filling in that night time gap. So you can imagine monitoring something during the day and then being able to fill in the hours of darkness with the thermal sensor. There are lots of other applications where we can provide that next added value step by answering the next question.

So imagine you identify something in your SAR or optical sensors. Perhaps it's a ship that's coming to pull. You really want an optical insight. You've got to really get to understanding what's going on the outside of structures or physical objects if you want to know - like is the engine of the ship on or off, that's something that the thermal can help with.

So quite a number of cases are developing around that kind of tipping and queuing kind of use case whereby our data really well complements other existing data sets. The other thing we're looking at in the future, like what's coming online in future as well, because I think with the proliferation of hyperspectral sensors, that's really interesting for us. Because with our data, as we mentioned earlier, to get to those of more in depth analytical products where we're looking at absolute temperatures, we need to understand surface material and quite a lot of detail.

So potentially we definitely see a use in the future where a high resolution hyperspectral system could help build us a greater understanding of what those different surface materials are, and then the data that we would use within our data production workflow to build that absolute product. But again, it's all customer driven and really it's got to be led and guided by the customers that are going to be using it.

[Rachana, Host]
Wow, that seems like a million different possibilities and seems to be a very exciting space. And when procuring these different kinds of imagery, do you face any issues or any obstacles or any inadequacies?

[Satellite Vu]
I think it’s the usual ones like the cost of very high resolution data is a very common thing. It's hard to get away from that. I think the proliferation of optical sensors is definitely helping with that. But again, it depends on the application and the use case that it's got to fit within the value of the information you're deriving from that.

And I think we try to use open source as much as possible. Toby mentioned a few things like improving geo-locational accuracy - we are using quite a bit of Sentinel data at the moment in our production workflow just to improve the geolocation accuracy of our data that’s from a free data source.

And then it is perhaps that some customers might need higher levels of geolocation or attitude and in that case, we might look to procure some more premium data sets to provide that added value.

Just to add in, we've seen that if we were to try and consume various radar data sets where some of the providers are still using emails to communicate in terms of tasking and understanding how you get that. So if that's a one off kind of R&D perspective, then it’s fine. But once you want to put that into a pipeline or into a production pipeline, that's just impossible.

So that is definitely an interesting activity because we're just going through how to expose tasking to our customers via API and we've got to that now. So it's good to see what the rest of the industry is doing and to be on some of them are just not ready to be ingested into a production system.

[Rachana, Host]
Speaking of high cost and the perceived value of these imagery, have you ever faced any challenges in onboarding, let's say potential customers of thermal data products who have never used satellite based services before?

[Satellite Vu]
Yeah, it's a really interesting one. Upon joining this company, I wasn't necessarily prepared for that challenge of potentially bringing a brand new data source to the market. So there is a lot of customer education that is required because I think quite often people haven't necessarily thought about how they might use a dataset like this at this resolution, at this kind of frequency that we are able to provide.

So we've definitely been helped by a couple of things. We've had a test platform essentially, we've been flying on an aerial system. So being able to build up this archive of data to be able to provide to potential customers, to help them with that journey of understanding how our data can be used, has been invaluable. The second part of this thing is that we've had a lot of success with a program that we developed to actually provide that data to our customers.

It’s called an early access program. There are a few other companies that have had success in programs like this. The key benefit I think we can provide is we have a huge archive, about 3000 scenes or so of thermal data, which really helps these customers to develop, test, iterate and that kind of thing.

So that essentially we can be commercially ready as soon as the satellite launches to start providing data into their workflows and that they will know instinctively how is this data going to help solve the problems that they might have.

[Rachana, Host]
At the end of the day, I would say sales is hard. Sometimes I feel building satellites or tech in general and doing technical work is way easier. I sometimes hang out with our sales team so especially in space, it can be very hard.

[Satellite Vu]
It can be seen as a very collaborative effort. And I think it's something we've done quite well is the combination of sales and technical. I think there's quite often a battle, isn't there, between commercial and technical or product sides of the companies.

It’s been worthwhile and we stay friendly.

[Rachana, Host]
Yeah, absolutely. Can you probably give an estimate in orders of magnitude how much money potential customers of your thermal data products are willing to spend on these kinds of monitoring solutions or insights?

[Satellite Vu]
Yeah, absolutely. That's actually been another great success of our early access program. We have included actually an agreement for a purchase option. So it's actually an indication of the size of the contract that they might be willing to pursue. And so far we've got about 57 customers as of this morning that signed up to our program that totals about just over a hundred million in purchase options.

So with these 57 customers, we’ve got about just over 100 million in purchase options. The interesting thing with this program is it's not just getting defense customers or just getting commercial customers. It's a really broad range of customers. Some of the larger interests initially, I think probably on the defense side, but we are definitely seeing a lot of interest in build-to-buy.

[Rachana, Host]
Congratulations on your large customer base! That's certainly very impressive. So circling back to the satellite segment, and assuming that you would have done some sort of a market survey in selecting a satellite platform and evaluating the options, how do you see the typical commercially available satellite platforms fairing in terms of their suitability towards thermal payloads?

[Satellite Vu]
So we've been approached, as you can imagine, by various payload manufacturers and satellite manufacturers because we have a need and they think that they have a solution. There's always optionality and based on what they're saying, they can do whatever it is that we want them to do. But there's always a question about cost, right?

Our current agreement with SSTL works really well for us. The bus is exactly the right size for us, both in limiting weight for launch costs and agility. So when we look at the sort of bus that we care about, it needs to be agile enough to do the whole movement in space to track the earth correctly and not spend too much time trying to do that versus not being too heavy versus having enough redundancy on it.

I don't think it's anything massively special that we're doing that we would need from a bus. It just needs to meet the requirements that this specific payload might have obviously in terms of power and thermal basis. I think it's interesting that on the thermal basis, we haven't necessarily had as much of an offer from satellite manufacturers looking at being really good at thermal dissipation. But that that could change, especially with more and more competitors coming on line, building some of their own, and also outsourcing some of their own designs that companies in the bus manufacturing world will start looking at this more seriously. So we did this survey of the markets a long time ago and SSTL was still by far the best and most advanced. And that hasn't changed since.

[Rachana, Host]
Do you see a lot of other thermal payload manufacturers such as companies like SatelliteVu that also might offer thermal imagery analytics? Or do you think it's some sort of a winner takes all kind of a scenario or is there space for multiple players?

[Satellite Vu]
There's definitely space. And Alex also opined that there is definitely space. Because there's quite a big range from where drones and airplanes can work and where Landsat currently is. So anywhere between zero and a hundred meters is fair game. We are at a certain level, but that by definition precludes us from doing wide area coverage. Whereas some of the other competitors, I’d actually say friends and not really competitors, because some of them are 70 meters and are doing really nice wide area agricultural monitoring.

Some of them are 40-50 meters doing water, stress, etc. So it's all collaborative and I think it's also going to be complementary. A lot of it also for somewhat seeding the market and helping with the education of the end user because like Alex said, it's going to customers saying we can solve a problem we didn't even know we could solve for you.

It could get solved within a day. And so I see all that as a nice combination of companies working in the same sort of domain that can work together.

You have this very specific application with very complementary stuff. You mentioned some of the low resolution systems being designed for fire detection, but they're not going to be suitable for monitoring the fire once it's been detected and providing real time information to the firefighters on the ground. And that's where our sensor can come in.

So once you detected the fire, then you have a high resolution ability to be able to see all the individual hotspots in the fire. One of the things that our sensor has got that’s quite unique is it's actually a video sensor. So it can detect things like speed and motion detection up to minutes worth of video.

So that's something that's really piqued the interests of those firefighters - can we estimate the speed and the direction of where this fire is progressing as it grows? So it's a great example of a collaborative effort now.

[Rachana, Host]
That sounds fantastic and I am really looking forward to the 10th of June which is your launch date. Looking forward to the result and the interesting images from your satellite. So looking forward and fingers crossed. Thank you for a lot of very valuable insights. Tobias & Alex, it's been a really nice session with you guys and hope at some point in future we could also be able to collaborate and do something fun in the thermal imaging space.

[Satellite Vu]
Thank you for your time!