WEBVTT - Fighting Wildfires from Space 0:00:15.356 --> 0:00:28.156 Pushkin. I'm Jacob Goldstein and this is What's Your Problem 0:00:28.356 --> 0:00:31.796 show about people using technology to solve problems that matter. 0:00:32.476 --> 0:00:35.796 My guest today is Johnny Dyer. He's the co founder 0:00:35.836 --> 0:00:39.756 and CEO of a company called Muon Space. Newon Space 0:00:39.836 --> 0:00:44.156 was founded in twenty twenty one, and the company designs, builds, 0:00:44.156 --> 0:00:48.516 and operates satellites. Their first big project is a constellation 0:00:48.596 --> 0:00:52.636 of satellites called fire Sat. And Johnny's problem is this, 0:00:53.516 --> 0:00:56.476 how do you build satellites that can capture data from 0:00:56.596 --> 0:01:00.876 space to help manage wildfires around the world in near 0:01:01.036 --> 0:01:04.956 real time. In our conversation, Johnny and I also talked 0:01:04.996 --> 0:01:08.076 about his company's work with the US Department of Defense, 0:01:08.556 --> 0:01:12.916 and more generally, the global geopolitics of satellites, which basically 0:01:12.956 --> 0:01:17.316 means the US versus China in space. To start, we 0:01:17.396 --> 0:01:20.876 talked about a satellite company called Skybox. Johnny joined that 0:01:20.956 --> 0:01:24.556 company just after it was founded in two thousand and nine. 0:01:24.716 --> 0:01:28.956 Up to around that time, satellites had mostly been giant, expensive, 0:01:29.036 --> 0:01:31.956 bespoke things, but this was a moment when a few 0:01:31.996 --> 0:01:34.396 people were starting to think that satellites could get much 0:01:34.396 --> 0:01:37.676 smaller and much cheaper. Johnny told me that the idea 0:01:37.756 --> 0:01:40.716 was partly inspired by the emergence of the iPhone. 0:01:40.876 --> 0:01:43.516 You shrink cameras down enough, you shrink compute down enough, 0:01:43.796 --> 0:01:46.036 all of a sudden you have this thing that is 0:01:46.156 --> 0:01:49.596 possible in a much smaller package than was ever possible before. 0:01:50.116 --> 0:01:52.316 And so there was a strong analogy. We thought with 0:01:52.356 --> 0:01:54.956 satellites that if you can use these commercial technologies, you 0:01:54.996 --> 0:01:57.316 can do a lot of the things that these big 0:01:57.356 --> 0:02:00.236 billion dollar systems are doing in a much smaller package. 0:02:00.796 --> 0:02:02.756 If you can do it in a smaller package, everything 0:02:02.796 --> 0:02:07.636 gets faster, cheaper, because most of the challenge of getting 0:02:07.636 --> 0:02:10.196 stuff in space is launching, and that on a per 0:02:10.276 --> 0:02:12.796 kilogram basis, like it just costs per kilogram to get 0:02:12.796 --> 0:02:15.356 stuff in space. If you make it smaller, everything gets better. 0:02:16.996 --> 0:02:18.556 And so we, you know, we did this and we 0:02:18.556 --> 0:02:20.556 were very successful at it. We ended up building twenty 0:02:20.596 --> 0:02:23.556 one satellites that were you know, took data of the 0:02:23.596 --> 0:02:26.836 same quality that literally, you know, one hundred million dollar 0:02:26.916 --> 0:02:30.876 systems before us were collecting. We got bought by Google 0:02:32.036 --> 0:02:34.916 and in the process we learned a lot about what 0:02:34.956 --> 0:02:37.076 it takes to do this, what works, what doesn't work. 0:02:38.076 --> 0:02:41.956 But also, you know, there there was sort of a 0:02:41.956 --> 0:02:46.316 lot of kind of frustrations we had about the fact 0:02:46.316 --> 0:02:49.116 that we solved this problem, this technical problem, and figured 0:02:49.116 --> 0:02:52.036 out how to deploy these things in space, but we 0:02:52.116 --> 0:02:54.996 really were only applying it to one small use case, 0:02:55.036 --> 0:02:57.756 which was this high resolution visible imagery. Think about what 0:02:57.796 --> 0:02:59.516 you see in Google Maps. So that's what we were doing. 0:02:59.516 --> 0:03:03.196 We're taking like submeters roughly one meter resolution visible images 0:03:03.236 --> 0:03:04.196 like you see Google Maps. 0:03:04.436 --> 0:03:06.276 So when I look on Google Maps and I see 0:03:06.276 --> 0:03:09.876 the trampoline in my backyard, which I do, Uh, is 0:03:09.916 --> 0:03:11.716 that you taking that picture? 0:03:11.836 --> 0:03:13.516 So probably the trampoline in your backyard. 0:03:13.516 --> 0:03:15.596 Probably not that was probably taken it from an aircraft 0:03:15.596 --> 0:03:18.356 because that's probably more like ten centimeter imagery. 0:03:19.156 --> 0:03:20.196 But if you go to. 0:03:20.556 --> 0:03:22.756 A big trampoline, yeah, I mean you would see it 0:03:22.796 --> 0:03:23.396 in our imagery. 0:03:23.436 --> 0:03:24.796 You would definitely see a trampoline. 0:03:25.636 --> 0:03:27.476 If you go a little bit outside a major urban 0:03:27.476 --> 0:03:30.076 area where it's too expensive to go collect aircraft imagery, 0:03:30.116 --> 0:03:31.876 all of that imagery and Google Maps would be the 0:03:31.876 --> 0:03:34.716 type of stuff we were collecting. So you can go 0:03:34.956 --> 0:03:36.556 search around Google Maps and you can see a bunch 0:03:36.556 --> 0:03:40.636 of that stuff. And so you know, we got we 0:03:40.676 --> 0:03:44.076 went through that journey. Eventually it ended, but stuck in 0:03:44.116 --> 0:03:46.916 the back of my head was we've shown, you know, 0:03:46.996 --> 0:03:49.476 we've shown a different paradigm for doing this, and there's 0:03:49.516 --> 0:03:53.156 so many possible applications of that new paradigm. 0:03:53.196 --> 0:03:55.436 So so kind of the basic narrative of how you 0:03:55.476 --> 0:03:58.916 get to muon just to collapse it is Skybox gets 0:03:58.916 --> 0:04:01.796 acquired by Google, and then at some point after that 0:04:01.876 --> 0:04:04.396 you get a call from somebody who wants to build 0:04:04.436 --> 0:04:09.596 satellites to track methane emissions, this project called Methane and Set, 0:04:09.916 --> 0:04:11.876 which seems like it is sort of what puts you 0:04:11.916 --> 0:04:14.956 on the path to starting mewon. The company're running, Now, 0:04:15.476 --> 0:04:17.356 how did that happen? What happened there? 0:04:18.156 --> 0:04:20.716 I got a call from some people I knew from 0:04:20.756 --> 0:04:24.636 Skybox at the Environmental Defense Fund saying we think there's 0:04:24.636 --> 0:04:27.476 an opportunity, you know, approaching the problem the way that 0:04:27.756 --> 0:04:31.276 companies like Skybox did, to go build a system that 0:04:31.316 --> 0:04:33.556 can map methane globally in the world. And this is 0:04:33.596 --> 0:04:35.996 you know, a huge first order a greenhouse driver. It's 0:04:36.036 --> 0:04:38.276 in the near term, it's the most important greenhouse gas, 0:04:38.276 --> 0:04:41.076 even more important than CO two. And we don't know, 0:04:41.316 --> 0:04:44.036 we don't there's no good source of data for actually 0:04:44.036 --> 0:04:46.316 how much is getting omitted by all these different sources 0:04:46.356 --> 0:04:49.956 where not quantitatively at least, And so, you know, that 0:04:50.116 --> 0:04:52.396 was a really exciting prospect for me to be part 0:04:52.436 --> 0:04:54.436 of that because it seems like a really important problem 0:04:54.516 --> 0:04:57.076 that needed to be solved. It was also really interesting 0:04:57.516 --> 0:05:00.636 to me that here we are in this world where 0:05:00.676 --> 0:05:04.356 there's a global nonprofitia the Environmental Defense Fund, so philanthropically 0:05:04.356 --> 0:05:08.756 funded nonprofit that is basically believes they can go out 0:05:08.756 --> 0:05:11.396 and build old what you know, traditionally would have been 0:05:11.516 --> 0:05:13.756 only the realm of a government, like a major government 0:05:13.756 --> 0:05:17.916 project like a NASA mission or an e submission, And 0:05:17.956 --> 0:05:20.436 so that just seemed like an extremely compelling prospect, like, 0:05:20.476 --> 0:05:22.516 if you can do that kind of thing and apply 0:05:22.516 --> 0:05:24.236 it in all these different ways, it's going to blow 0:05:24.236 --> 0:05:26.676 the door open on the types of things we imagined 0:05:26.716 --> 0:05:27.516 doing from space. 0:05:27.556 --> 0:05:29.836 And so for all those reasons. 0:05:29.436 --> 0:05:31.356 I was really excited to you know, be part of 0:05:31.396 --> 0:05:35.556 Methane SAD and join the advisory board for it. And 0:05:35.596 --> 0:05:38.476 we went through this long process of basically, for lack 0:05:38.516 --> 0:05:41.276 of a better term, trying to recreate some of the 0:05:41.316 --> 0:05:43.636 things about what we did at Skybox, but with this 0:05:43.716 --> 0:05:47.116 totally different outcome in mind. And it was really hard. 0:05:49.036 --> 0:05:51.676 And one of the primary reasons it was really hard 0:05:51.956 --> 0:05:56.156 was that at Skybox everything was within our control and 0:05:56.236 --> 0:05:59.356 we built everything ourselves. We literally, you know, we were 0:05:59.396 --> 0:06:01.756 literally building the circuit boards that went in the satellites. 0:06:01.796 --> 0:06:04.036 We wrote all the software, we were building the cameras 0:06:04.036 --> 0:06:05.276 that went into the telescope. 0:06:06.916 --> 0:06:07.116 You know. 0:06:07.516 --> 0:06:12.316 Environmental Defense Fund does not have a deep aerospace engineering 0:06:12.316 --> 0:06:14.236 function that can go build all this stuff. And so 0:06:14.276 --> 0:06:17.356 they essentially went out to the market and they said, Okay, well, 0:06:17.716 --> 0:06:20.516 companies like Skybox and Planet exist. There must be now 0:06:20.516 --> 0:06:23.316 a rich ecosystem of suppliers in the market that we 0:06:23.356 --> 0:06:25.996 can go buy what we need to go do this mission. 0:06:27.236 --> 0:06:29.196 The long and the short of it is that is 0:06:29.236 --> 0:06:32.756 not true. And so what they what we kind of 0:06:32.836 --> 0:06:36.636 ran up against was the state of the overall ecosystem 0:06:36.756 --> 0:06:39.996 was still very much like that old mainframe in space, 0:06:40.076 --> 0:06:45.076 you know, billion dollar ecosystem or these little tiny cottage 0:06:45.116 --> 0:06:48.276 industry startups that we're trying to build some small piece 0:06:48.316 --> 0:06:50.956 of a component or a little bit of software or something. 0:06:51.796 --> 0:06:54.596 And the thing about space is really the hardest part 0:06:54.916 --> 0:06:57.876 in many ways is integrating all these things together and 0:06:57.916 --> 0:07:00.556 making them work as a system that can ultimately deliver 0:07:01.156 --> 0:07:03.956 you know, an answer or a solution to a problem. 0:07:05.236 --> 0:07:07.036 And so you know, if you fast forward and we 0:07:07.076 --> 0:07:09.556 spent like five years helping edf kind get up the 0:07:09.596 --> 0:07:12.876 learning curve doing that, and it was I would say, ultimately, 0:07:12.996 --> 0:07:15.116 you know, successful in the sense that a satellite got built, 0:07:15.156 --> 0:07:18.356 it got launched, it collected data. It was way slower, 0:07:18.396 --> 0:07:20.436 it was way more expensive, it was way harder than 0:07:20.436 --> 0:07:26.196 everybody thought, and it really kind of oriented me towards 0:07:26.236 --> 0:07:29.356 there's a huge opportunity here. Like you know, we learned 0:07:29.396 --> 0:07:31.596 how to solve a lot of these problems at Skybox. 0:07:31.996 --> 0:07:34.516 There's clearly a need and so we have this opportunity 0:07:34.556 --> 0:07:37.596 to frankly flood the sky with you know, entirely new 0:07:37.636 --> 0:07:41.076 types of sensors collecting data that could be incredibly impactful 0:07:41.156 --> 0:07:46.076 on how we manage the planet. But the supply chain, 0:07:46.116 --> 0:07:49.956 the ecosystem to go execute that efficiently. You know, when 0:07:49.956 --> 0:07:52.356 we started Mwon, I felt had not mature, it had 0:07:52.396 --> 0:07:54.276 did not exist at the state that it needed to 0:07:55.316 --> 0:07:57.076 to realize that. And so that was a lot of 0:07:57.116 --> 0:07:59.516 the kind of origin thought process that led us to 0:07:59.516 --> 0:08:02.876 start the company, is we can go build an entity 0:08:03.356 --> 0:08:06.396 that is really able to deliver on these really hard, 0:08:06.476 --> 0:08:09.556 difficult type of missions, but in the way that we 0:08:09.596 --> 0:08:11.636 did it at Skybox. So we're ten times faster and 0:08:11.636 --> 0:08:13.756 ten times cheaper. And if we do that, it's going 0:08:13.796 --> 0:08:15.836 to blow the door open on the types of applications 0:08:15.836 --> 0:08:16.876 people are doing in space. 0:08:16.956 --> 0:08:18.916 And that's what we're ultimately trying to do. 0:08:19.836 --> 0:08:23.476 And so you create me on in twenty twenty one, 0:08:23.596 --> 0:08:27.516 is it right? And the first project that I'm aware 0:08:27.556 --> 0:08:31.236 of that you were working on is fire SAT. Was 0:08:31.236 --> 0:08:34.796 that sort of part of the creation of the company. 0:08:34.956 --> 0:08:37.636 Well, it predated the creation of the company a little 0:08:37.636 --> 0:08:39.956 bit in the sense that what it came out of 0:08:40.196 --> 0:08:43.836 was there's a group of people I worked with at 0:08:43.836 --> 0:08:46.236 Google when I was at Google and research that we're 0:08:46.276 --> 0:08:51.036 looking at how to is kind of AI applications, so 0:08:51.316 --> 0:08:52.756 looking at how they could take a lot of the 0:08:52.756 --> 0:08:56.756 AI work going on and applied to very particular impact 0:08:56.756 --> 0:09:01.236 applications like climate, like wildfire. One of the biggest problems 0:09:01.236 --> 0:09:05.476 with wildfire is there's these data gaps. It's very hard 0:09:05.516 --> 0:09:10.476 to understand just how little they know when they're making 0:09:10.516 --> 0:09:14.156 decisions during a wildfire, like where the fire is, how 0:09:14.196 --> 0:09:16.436 fast it's moving, how hot, it's burning, what's in danger. 0:09:16.956 --> 0:09:20.596 Usually it is largely from reports coming in from boots 0:09:20.596 --> 0:09:20.996 on the ground. 0:09:21.036 --> 0:09:22.556 They have firefires on the line. 0:09:22.916 --> 0:09:24.556 Did the end of the day come in and say, 0:09:24.556 --> 0:09:26.316 this is what we saw, this is roughly where the 0:09:26.316 --> 0:09:28.676 fire line was, and people are hand drawing it on maps. 0:09:28.676 --> 0:09:30.556 That's literally often like it's. 0:09:30.516 --> 0:09:32.876 Nineteen fifty or at nineteen hundred. 0:09:32.716 --> 0:09:33.396 Nineteen hundred. 0:09:33.396 --> 0:09:35.036 It really is not that different than I think the 0:09:35.076 --> 0:09:38.996 way wildfires were fought in nineteen hundred. And you know, 0:09:40.396 --> 0:09:44.156 if you think about most elements of society, most elements 0:09:44.196 --> 0:09:47.916 of our lives, they've progressed dramatically past that point. You know, 0:09:47.916 --> 0:09:49.516 we could pull up a map on our phone that 0:09:49.716 --> 0:09:52.196 has incredible near real time date on traffic. 0:09:52.316 --> 0:09:54.276 I mean, let me ask us a dumb question about that. 0:09:55.996 --> 0:09:59.836 They fly planes over wildfires. Once these images of that, 0:09:59.956 --> 0:10:02.836 can the planes not give them pretty good data about 0:10:02.836 --> 0:10:05.116 what's happening? At least once they know it's there. 0:10:05.036 --> 0:10:05.436 They can. 0:10:05.636 --> 0:10:08.556 At times, the planes are very limited, so they they're 0:10:08.796 --> 0:10:11.076 off not position in a place where they can get 0:10:11.076 --> 0:10:13.556 them to an active fire fast enough to get the 0:10:13.596 --> 0:10:15.716 data they need. So there's all those challenges, and they 0:10:15.716 --> 0:10:18.676 often can't fly due to the conditions too, so if 0:10:18.676 --> 0:10:21.756 it's too smoky, they can't fly. If there's really high winds, 0:10:21.796 --> 0:10:24.196 which was obviously the case in the LA fires last year, 0:10:24.196 --> 0:10:26.036 so they weren't able to fly the aircraft over those 0:10:26.036 --> 0:10:27.036 fires because the winds. 0:10:26.876 --> 0:10:27.556 Were too high. 0:10:28.196 --> 0:10:31.916 So they can provide very good situational awareness data, but 0:10:31.956 --> 0:10:34.036 they are very limited in a lot of ways, both 0:10:34.076 --> 0:10:36.916 from a cost per perspective, from sort of a breadth 0:10:36.996 --> 0:10:40.756 and geographic passy perspective, and then just from an operational perspective. 0:10:41.676 --> 0:10:44.676 The thing that satellites give you that is unique as 0:10:44.716 --> 0:10:46.556 this kind of persistent overhead view. 0:10:46.676 --> 0:10:48.436 Right A satellite's giving you this. 0:10:48.476 --> 0:10:51.756 You know, constant kind of persistent overhead map like view 0:10:51.796 --> 0:10:53.916 of where the fire boundary is, how hot it is, 0:10:53.956 --> 0:10:57.716 how fast it's moving, and that's just, you know, really 0:10:57.756 --> 0:11:00.876 transformational for detecting the fires early. You don't have to say, hey, 0:11:00.876 --> 0:11:02.196 I'm going to go fly a plane and look for 0:11:02.236 --> 0:11:04.996 a fire. The satellite's going to cover the space and 0:11:05.036 --> 0:11:07.276 detect a fire if it starts. And that's one of 0:11:07.316 --> 0:11:09.676 the goals of firesat is to build to attack to 0:11:09.716 --> 0:11:12.796 fire within about twenty minutes of its starting, and then 0:11:12.796 --> 0:11:15.316 once it's burning we have this you know, ongoing time 0:11:15.436 --> 0:11:18.836 series of understanding of how it's moving, which is going 0:11:18.916 --> 0:11:21.276 to be absolutely transformational in terms of how they think 0:11:21.316 --> 0:11:26.236 about positioning resources, how to manage risk. The other thing, 0:11:26.396 --> 0:11:28.436 the other part of this that I think is important, 0:11:28.556 --> 0:11:32.356 is that the goal is not to eliminate fire like 0:11:32.436 --> 0:11:35.916 fire is really important. In fact, we don't have enough 0:11:35.916 --> 0:11:38.036 fire in many in California, we don't have enough fire. 0:11:38.516 --> 0:11:41.436 Historically there was a lot more natural wildfire, and we've 0:11:41.516 --> 0:11:42.996 kind of eliminated that. 0:11:43.476 --> 0:11:46.476 Just to be clear about that, like the ideas, California, 0:11:46.676 --> 0:11:49.476 like much of the world, all of the American West, 0:11:49.636 --> 0:11:52.716 evolved to burn, to happen right, fires periodically, and we 0:11:52.756 --> 0:11:55.916 had this century essentially of not letting anything burn that's right, 0:11:55.916 --> 0:11:59.436 and you get too much fuel, too much underbrush, and 0:11:59.476 --> 0:12:01.476 then when there is a fire, it's too hot and 0:12:01.516 --> 0:12:03.076 it burns too big in a way that it would 0:12:03.116 --> 0:12:05.236 not have if we had let fires burn in the 0:12:05.236 --> 0:12:05.796 first place. 0:12:05.956 --> 0:12:08.596 Perfect, man, you've clearly studied this topic. 0:12:08.796 --> 0:12:11.796 Yeah, it's really interesting, right, it's not entirely intuitive, but 0:12:11.956 --> 0:12:14.196 not into about it and it's like, oh interesting, Yeah. 0:12:14.276 --> 0:12:15.956 I spend a lot of time in the Sierras where 0:12:15.956 --> 0:12:18.996 It's like you see like Manzanita are like pumping out 0:12:19.116 --> 0:12:20.876 oil because they want there to be a fire. 0:12:21.076 --> 0:12:23.276 Yeah, and Manzanita is like a blow torch when it 0:12:23.276 --> 0:12:26.676 starts on fire. So yeah, so yeah, I mean that's 0:12:26.676 --> 0:12:28.876 a huge problem. And I think the point is that 0:12:29.996 --> 0:12:32.196 it's not simple enough to say when a fire starts, 0:12:32.236 --> 0:12:34.836 put it out. There has to be a decision made 0:12:34.996 --> 0:12:37.876 about there's you know, the way that this has best 0:12:37.916 --> 0:12:40.516 been described to me. We work with an advisor named 0:12:40.556 --> 0:12:42.396 Kate Dargan. He used to be the fire chief of California, 0:12:42.396 --> 0:12:44.436 and she talks about good fire and bad fire. Right 0:12:44.876 --> 0:12:46.756 when you get to what you were describing, where you 0:12:46.796 --> 0:12:50.116 have these over fuel loated forests that burst into flame 0:12:50.596 --> 0:12:53.196 and are burning basically so hot that they're killing everything 0:12:53.196 --> 0:12:54.276 in a very unhealthy way. 0:12:54.276 --> 0:12:57.116 That's bad fire, and like you want it. 0:12:57.156 --> 0:12:59.596 You don't want that to burn, But we need a 0:12:59.596 --> 0:13:02.476 lot more low intensity fire through the forest to keep 0:13:02.476 --> 0:13:05.996 the forest healthy. And so right now, there's basically no 0:13:06.116 --> 0:13:08.956 way for the fire agencies to distinguish that for the 0:13:09.156 --> 0:13:12.396 most part. I mean, they're typically because of the risks involved, 0:13:12.396 --> 0:13:14.356 they're just going to try and put the fires out 0:13:14.396 --> 0:13:16.436 because there's so much at risk. 0:13:16.836 --> 0:13:20.116 Well, like politically, if you think about it, politically, you're 0:13:20.116 --> 0:13:22.396 never going to get in trouble for putting the fires, right, 0:13:22.916 --> 0:13:25.596 But if you're like, well, you know we made the call, 0:13:25.836 --> 0:13:28.476 and you know our model said it should burn, like, 0:13:28.876 --> 0:13:31.756 that's just not going to play if anything bad happens. 0:13:31.476 --> 0:13:33.716 That's right exactly. Yeah. 0:13:33.836 --> 0:13:36.756 Kate's big thing is if we can measure the intensity 0:13:36.796 --> 0:13:38.836 on a near real time basis, we can make way 0:13:38.836 --> 0:13:43.316 better decisions about how we deploy resources to combat the 0:13:43.356 --> 0:13:45.996 bad fire while allowing the good fire to burn. And 0:13:46.076 --> 0:13:48.956 that's that's a very heavily kind of risk based decision 0:13:49.076 --> 0:13:52.076 process that needs to be much better informed by data. 0:13:52.196 --> 0:13:56.076 And I think that's in many ways we love fire 0:13:56.116 --> 0:13:59.076 Set because I think it is such a tangible example 0:13:59.316 --> 0:14:03.836 of the power of these space based data collection systems 0:14:03.876 --> 0:14:07.316 to not only tell us something about the world or 0:14:07.396 --> 0:14:10.956 you know, oh that's interesting, but actually drive decision making 0:14:10.996 --> 0:14:13.516 on the ground. We now have actionable data that can 0:14:13.556 --> 0:14:16.516 be used to say we're going to position firefighters here 0:14:16.556 --> 0:14:19.036 instead of there, and that's not only going to protect this, 0:14:19.556 --> 0:14:21.436 you know, this town, but it's also going to allow 0:14:21.476 --> 0:14:22.796 this other part of the forest to burn. 0:14:22.836 --> 0:14:24.916 So there's less risk next year that it's going to burn. 0:14:25.836 --> 0:14:28.356 Right. So you say we now have actionable data, but like, 0:14:28.596 --> 0:14:31.036 we don't literally have it now, right, because the project 0:14:31.076 --> 0:14:34.996 is still ongoing. And so just to be clear, the 0:14:34.996 --> 0:14:37.876 goal of the project is to have So it's an 0:14:37.876 --> 0:14:42.716 infrared image, right, which makes sense of every piece of 0:14:42.716 --> 0:14:45.116 the earth out of resolution. You said about the size 0:14:45.116 --> 0:14:47.556 of a swimming pool, right, which is a nice image. 0:14:47.876 --> 0:14:50.716 Yeah, the actual resolution is a lot bigger than that. 0:14:50.756 --> 0:14:52.956 It's about fifty meters, so think about half of a 0:14:52.956 --> 0:14:55.956 football field. But we can see we can detect a 0:14:56.116 --> 0:14:59.316 fire within that fifty meters down to about the size 0:14:59.316 --> 0:15:01.236 of a swimming pool. So if there was a swimming 0:15:01.236 --> 0:15:04.196 pool size fire on half a football field, we would 0:15:04.196 --> 0:15:04.996 detect that fire. 0:15:05.116 --> 0:15:09.036 Okay, and to do that of the whole earth every. 0:15:08.876 --> 0:15:10.276 Twent the minutes, that's right. 0:15:10.396 --> 0:15:11.836 It sounds like a lot. 0:15:12.116 --> 0:15:13.036 It is a lot of year. 0:15:13.516 --> 0:15:16.956 It is a lot, right. And so so you start 0:15:16.996 --> 0:15:19.916 this company five years ago around the time this project 0:15:19.956 --> 0:15:23.796 is kind of coming into view, right, and you the 0:15:23.836 --> 0:15:25.716 company and the project sort of get going together. 0:15:25.796 --> 0:15:26.596 Yes, that's right, yep. 0:15:28.436 --> 0:15:29.956 And so I mean you talked about how you had 0:15:29.956 --> 0:15:32.076 solved a lot of these things at Skybox. But plainly 0:15:32.076 --> 0:15:34.956 there's a lot to figure out here. So when you 0:15:35.036 --> 0:15:37.556 launch the company, what do you have to figure out 0:15:37.796 --> 0:15:38.436 to do this? 0:15:38.596 --> 0:15:40.156 Yeah, so there's a couple of things. I think one 0:15:40.196 --> 0:15:43.156 thing is be able to build a small and low 0:15:43.236 --> 0:15:47.876 cost infrared camera, which is a critical enabler for this 0:15:47.956 --> 0:15:51.156 to work. And that's something that we bid off very 0:15:51.156 --> 0:15:53.516 early in the process, very much using again the same 0:15:53.596 --> 0:15:55.316 kind of approach that we use at Skybox. 0:15:55.316 --> 0:15:56.236 At Skybox, we were. 0:15:56.196 --> 0:15:58.276 Much we were focused on visible imagery, which is a 0:15:58.276 --> 0:16:02.516 different thing that's very much a solved problem now for space. 0:16:03.236 --> 0:16:05.676 But if you ask anybody when we started the company, 0:16:05.716 --> 0:16:07.916 what does it take to build like a very high 0:16:08.676 --> 0:16:11.716 sense it'sivity infrared imager from space, they'd probably tell you 0:16:11.836 --> 0:16:15.156 it's like a ten to thirty million dollar problem per unit. 0:16:15.396 --> 0:16:17.196 Wait, you mean it's going to cost you ten million 0:16:17.196 --> 0:16:18.716 dollars for each camera? 0:16:19.716 --> 0:16:21.516 Yeah, I mean if you went out to Lockheed or 0:16:21.596 --> 0:16:24.116 Northrope or whoever builds these things, because you know commercially 0:16:24.116 --> 0:16:24.716 they're not built. 0:16:25.076 --> 0:16:26.836 Yeah, that's what they would have told you. That's what 0:16:26.916 --> 0:16:27.116 you know. 0:16:27.196 --> 0:16:29.396 In many ways, like the government is paying today for 0:16:29.436 --> 0:16:30.396 that type of payload. 0:16:32.156 --> 0:16:33.036 And we couldn't do. 0:16:33.036 --> 0:16:35.716 That because, you know, ultimately, to get to that twenty minutes, 0:16:35.756 --> 0:16:38.916 which everybody agrees was a critical goal, you need like 0:16:38.996 --> 0:16:41.876 fifty satellites and so if you're if just the camera 0:16:41.916 --> 0:16:44.796 on each satellite costs twenty million dollars, it's pretty hard 0:16:44.836 --> 0:16:46.236 to imagine that making sense. 0:16:46.956 --> 0:16:48.236 But we needed like a ten x. 0:16:48.276 --> 0:16:49.876 I mean, we needed to get this thing down to 0:16:49.996 --> 0:16:52.596 like a million dollars or you know, no more than 0:16:52.636 --> 0:16:55.276 two million dollars. And so again we had to go 0:16:55.356 --> 0:16:57.916 to the out and say, like, what are technologies that 0:16:57.956 --> 0:17:01.636 have been developed for other industries that we can apply 0:17:01.796 --> 0:17:04.196 to this problem that haven't been used in space before, 0:17:04.196 --> 0:17:06.796 because typically there's a lot of industries that have spent 0:17:06.836 --> 0:17:10.236 billions of dollars on technology and getting the cost down 0:17:10.236 --> 0:17:13.116 and the performance up. And so what we found was 0:17:13.156 --> 0:17:16.516 there was there had been work on It was largely 0:17:16.556 --> 0:17:19.556 for tactical military applications, so not things that go in space, 0:17:19.636 --> 0:17:23.236 but things like the night vision that a soldier wears 0:17:23.236 --> 0:17:26.236 in the field, where they're building hundreds of thousands of 0:17:26.236 --> 0:17:29.796 these things at fairly low cost, and the underlying camera 0:17:29.836 --> 0:17:33.516 technology is applicable to it's what we needed for this 0:17:33.876 --> 0:17:35.356 it's a very different way to do it. Again, it 0:17:35.396 --> 0:17:37.516 was another case of like we literally had people saying 0:17:37.516 --> 0:17:39.356 this will never work, you can't do it that way. 0:17:40.716 --> 0:17:43.236 While as you say that, well, I mean when people 0:17:43.276 --> 0:17:43.756 say that too. 0:17:43.956 --> 0:17:46.996 I love it when people tell me something's not possible, 0:17:47.036 --> 0:17:49.036 because that's just like that's a great challenge, like Okay, 0:17:49.036 --> 0:17:50.956 I'm gonna prove you wrong. So yeah, So that was 0:17:50.996 --> 0:17:54.396 a big challenge that we had to solve and we did. 0:17:55.156 --> 0:17:57.436 I think another challenge that we really had to solve, 0:17:57.876 --> 0:18:00.956 which is related to fire set, but it's also related 0:18:00.956 --> 0:18:05.156 to the bigger picture for the company is you know, 0:18:05.796 --> 0:18:10.916 these things produce enormous amounts of data, and they often 0:18:10.996 --> 0:18:13.516 are constrained in various ways in terms of the ability 0:18:13.516 --> 0:18:15.916 to get that data back to Earth and then into 0:18:15.916 --> 0:18:18.676 the hands of people that need it, and certainly on 0:18:18.876 --> 0:18:22.716 reasonable time scales, so like typical satellite systems maybe only 0:18:23.436 --> 0:18:25.316 might take an hour and a half or two hours 0:18:25.356 --> 0:18:27.236 from the time a picture is taken to when it's 0:18:27.276 --> 0:18:29.196 actually usable in somebody's hand. 0:18:30.116 --> 0:18:31.076 And again for the fire. 0:18:30.916 --> 0:18:32.516 Problem, obviously that's not going to work if we're going 0:18:32.596 --> 0:18:34.676 to put all these satellites up to fly over every 0:18:34.676 --> 0:18:36.556 fifteen minutes, Like, waiting an hour and a half for 0:18:36.636 --> 0:18:39.116 somebody to get that data is not helpful. So we 0:18:39.156 --> 0:18:40.796 had to put a lot of time and effort into 0:18:40.996 --> 0:18:43.996 thinking about how you can build extremely high bandwidth, extremely 0:18:44.036 --> 0:18:47.876 low latency pipelines basically to get data from satellites and 0:18:47.876 --> 0:18:50.516 out to users. And the reason I say it's more 0:18:50.556 --> 0:18:52.636 than just fire sat is because I do think that's 0:18:52.636 --> 0:18:55.076 something that is an unlock for a whole bunch of 0:18:55.116 --> 0:18:55.876 other things too. 0:18:56.876 --> 0:18:58.276 So how'd you figure that one out? 0:18:59.236 --> 0:19:01.276 So there's kind of two different pieces of it. There's 0:19:01.356 --> 0:19:04.596 kind of a phase one and a phase two. The 0:19:04.636 --> 0:19:09.476 phase one is clever, you know, basically clever archets picture 0:19:09.596 --> 0:19:11.916 of where we put antennas around the world, and how 0:19:11.956 --> 0:19:15.036 we design our radios to be able to continuously downlink 0:19:15.076 --> 0:19:18.036 while the cameras are collecting, which most satellites don't do. 0:19:18.116 --> 0:19:21.316