WEBVTT - Seeing Data From Space

0:00:15.316 --> 0:00:22.916
<v Speaker 1>Pushkin. I'm looking right now at the Google Maps satellite

0:00:22.916 --> 0:00:25.556
<v Speaker 1>image of my block, of my house and the houses

0:00:25.796 --> 0:00:28.116
<v Speaker 1>next to my house, and I can tell from looking

0:00:28.116 --> 0:00:29.996
<v Speaker 1>at the picture that it is at least a year

0:00:30.036 --> 0:00:33.076
<v Speaker 1>or so old. I know this because last summer, my

0:00:33.156 --> 0:00:35.636
<v Speaker 1>kids and I watched as our next door neighbors had

0:00:35.676 --> 0:00:38.396
<v Speaker 1>the time of their lives in their brand new above

0:00:38.476 --> 0:00:42.036
<v Speaker 1>ground pool, and in this satellite picture on Google Maps,

0:00:42.556 --> 0:00:45.636
<v Speaker 1>there is no pool. This is fine. I don't need

0:00:45.676 --> 0:00:48.156
<v Speaker 1>to look at Google Maps to know that my neighbors

0:00:48.156 --> 0:00:50.676
<v Speaker 1>are living their best lives now, and I perhaps am not.

0:00:51.436 --> 0:00:55.956
<v Speaker 1>But there are other instances, other use cases, if you will,

0:00:56.236 --> 0:00:59.396
<v Speaker 1>when you might want satellite images that are updated more

0:00:59.436 --> 0:01:03.396
<v Speaker 1>frequently than every year or so. For example, if you

0:01:03.476 --> 0:01:05.916
<v Speaker 1>were a hedge fund who wanted to know how many

0:01:05.996 --> 0:01:08.916
<v Speaker 1>cars were in the parking lot of every home depot

0:01:08.956 --> 0:01:13.356
<v Speaker 1>in America last weekend, or an NGO monitoring deforestation in

0:01:13.396 --> 0:01:16.396
<v Speaker 1>the Amazon, or a government that wanted to see if

0:01:16.436 --> 0:01:19.476
<v Speaker 1>foreign troops were massing near your border. If you were

0:01:19.516 --> 0:01:22.596
<v Speaker 1>any of those things, you might want satellite images that

0:01:22.636 --> 0:01:25.996
<v Speaker 1>are updated much more frequently than once a year. You

0:01:26.076 --> 0:01:31.916
<v Speaker 1>might even want a new picture from space every single day.

0:01:33.996 --> 0:01:36.916
<v Speaker 1>I'm Jacob Goldstein and this is What's Your Problem, the

0:01:36.956 --> 0:01:39.876
<v Speaker 1>show where I talked to entrepreneurs and engineers about how

0:01:39.876 --> 0:01:42.196
<v Speaker 1>they're going to change the world once they solve a

0:01:42.236 --> 0:01:47.596
<v Speaker 1>few problems. My guest today is Will Marshall, the co

0:01:47.716 --> 0:01:51.676
<v Speaker 1>founder and CEO of Planet. Planet is a private company

0:01:51.916 --> 0:01:54.716
<v Speaker 1>and they own a fleet of over two hundred satellites

0:01:54.876 --> 0:01:58.436
<v Speaker 1>that takes a picture of the entire Earth every day.

0:01:58.916 --> 0:02:01.996
<v Speaker 1>Will's current problem how to turn a daily picture of

0:02:02.036 --> 0:02:06.316
<v Speaker 1>the Earth into useful information. Will started his career as

0:02:06.356 --> 0:02:09.196
<v Speaker 1>an engineer at NASA, and while he was there in

0:02:09.236 --> 0:02:11.716
<v Speaker 1>a colleague came up with the idea for Planet. But

0:02:11.756 --> 0:02:16.476
<v Speaker 1>to get started, they faced a simple, massive problem. Satellites

0:02:16.556 --> 0:02:21.356
<v Speaker 1>were way, way, way too expensive, about a billion dollars

0:02:21.436 --> 0:02:24.316
<v Speaker 1>per satellite, and they knew they'd never be able to

0:02:24.316 --> 0:02:27.116
<v Speaker 1>get a whole fleet of satellites into space at that price.

0:02:27.436 --> 0:02:30.276
<v Speaker 1>So they asked themselves a question, what's something that is

0:02:30.316 --> 0:02:34.236
<v Speaker 1>a lot like a satellite, but much cheaper. We had

0:02:34.556 --> 0:02:38.196
<v Speaker 1>looked at a phone and said, well, that's got most

0:02:38.476 --> 0:02:41.996
<v Speaker 1>of the ingredients of a satellite. If you look at

0:02:41.996 --> 0:02:45.196
<v Speaker 1>a smartphone, it has GPS telling you where you are,

0:02:45.276 --> 0:02:49.396
<v Speaker 1>It has cameras, It has hard drives, it has accelerometers,

0:02:49.556 --> 0:02:52.356
<v Speaker 1>It has rate gyros that used for gaming, so people

0:02:52.396 --> 0:02:54.636
<v Speaker 1>know when they're tipping the thing. Actually, that's kind of

0:02:54.676 --> 0:02:56.996
<v Speaker 1>handy for spacecraft. The only thing it doesn't have that

0:02:57.076 --> 0:03:00.556
<v Speaker 1>spacecraft has is continuous power supply. It has a battery, right,

0:03:00.596 --> 0:03:03.516
<v Speaker 1>but it doesn't have the ability to power itself. So

0:03:04.396 --> 0:03:07.196
<v Speaker 1>and it doesn't have a bright enough radio if you like.

0:03:07.316 --> 0:03:09.796
<v Speaker 1>It's it's radio is the most short range, whereas we

0:03:09.836 --> 0:03:13.676
<v Speaker 1>need a more substantive radio. But it has a lot

0:03:13.716 --> 0:03:17.276
<v Speaker 1>of ingredients. But also it doesn't cost a billion dollars

0:03:17.356 --> 0:03:19.476
<v Speaker 1>on the plus, well that's the other thing. Yeah, so

0:03:19.516 --> 0:03:22.316
<v Speaker 1>because maybe because five hundred dollars not five hundred million dollars.

0:03:22.516 --> 0:03:25.716
<v Speaker 1>And so we thought it would be cunning to throw

0:03:25.756 --> 0:03:28.156
<v Speaker 1>some of these phones in space and see what happened

0:03:28.196 --> 0:03:30.156
<v Speaker 1>to them. And we did. This is when we're as

0:03:30.636 --> 0:03:32.676
<v Speaker 1>you like, put it in a box with the solar

0:03:32.716 --> 0:03:36.716
<v Speaker 1>panel and a stronger radio, yeah exactly, binger, and then

0:03:36.756 --> 0:03:39.716
<v Speaker 1>put it into space. They were tumbling around and they

0:03:39.716 --> 0:03:42.596
<v Speaker 1>took a few pictures of the Earth with the cameras

0:03:42.596 --> 0:03:45.236
<v Speaker 1>on the phone, just with their regular smartphone here. Yeah,

0:03:45.436 --> 0:03:48.956
<v Speaker 1>and then we had amateur radio observers pick up the

0:03:49.036 --> 0:03:53.476
<v Speaker 1>signals from these, they're like texting the selfie of the

0:03:53.516 --> 0:03:56.836
<v Speaker 1>Earth batter Yes, And then we recompiled all the bits

0:03:56.836 --> 0:03:59.116
<v Speaker 1>of the pictures into a picture of the Earth. And

0:03:59.116 --> 0:04:01.196
<v Speaker 1>then then we were like, oh, okay and dipso did

0:04:01.196 --> 0:04:03.636
<v Speaker 1>it work? Yes, it worked. The phones worked just fine

0:04:03.676 --> 0:04:07.196
<v Speaker 1>in space. We flew three of them, three Google Nexus ones,

0:04:07.556 --> 0:04:09.716
<v Speaker 1>because they were easier to hack at than the iPhone.

0:04:09.916 --> 0:04:11.996
<v Speaker 1>And that was when we decided, okay, we could do

0:04:12.036 --> 0:04:14.516
<v Speaker 1>this very differently, but it's probably makes more sense as

0:04:14.556 --> 0:04:18.436
<v Speaker 1>a private company because NASA set about doing exploration and science,

0:04:18.556 --> 0:04:21.516
<v Speaker 1>but this was more applied. This is more about commercial

0:04:21.956 --> 0:04:26.596
<v Speaker 1>benefits or humanitarian benefits or it's very applied in nature.

0:04:26.636 --> 0:04:28.596
<v Speaker 1>And so we thought we could do it a little

0:04:28.596 --> 0:04:31.196
<v Speaker 1>bit faster outside of NASA. So we left NASA to

0:04:31.236 --> 0:04:34.036
<v Speaker 1>do this project of setting out this goal of launching

0:04:34.036 --> 0:04:36.276
<v Speaker 1>about one hundred satellites to image the whole Earth every

0:04:36.276 --> 0:04:40.396
<v Speaker 1>single day. So you leave NASA at this moment when

0:04:40.716 --> 0:04:43.796
<v Speaker 1>a satellite costs a billion dollars, so you need something

0:04:43.836 --> 0:04:47.876
<v Speaker 1>between a five hundred dollars smartphone and a billion dollars satellite, right,

0:04:47.916 --> 0:04:49.636
<v Speaker 1>So what is the thing you've got to build, like

0:04:50.196 --> 0:04:52.116
<v Speaker 1>more or less, how much does it have to cost?

0:04:52.156 --> 0:04:53.716
<v Speaker 1>How cheap do you have to be able to make

0:04:53.716 --> 0:04:55.356
<v Speaker 1>a satellite when you set out for it to work,

0:04:55.436 --> 0:04:58.676
<v Speaker 1>we thought that we could do it of order a

0:04:58.756 --> 0:05:01.676
<v Speaker 1>couple of hundred thousand dollars per satellite, and so to

0:05:01.836 --> 0:05:05.596
<v Speaker 1>get from a billion to three hundred thousand all the

0:05:05.596 --> 0:05:09.476
<v Speaker 1>way down, Like, can you just tell me maybe one

0:05:10.876 --> 0:05:14.276
<v Speaker 1>problem you solved, like one thing you had to figure out? Obviously,

0:05:14.556 --> 0:05:16.996
<v Speaker 1>I'm sure you had to figure out a thousand things,

0:05:17.036 --> 0:05:19.236
<v Speaker 1>a billion things to save a billion dollars, but like,

0:05:19.316 --> 0:05:22.196
<v Speaker 1>what's one little problem you solved on their way? One

0:05:22.356 --> 0:05:26.556
<v Speaker 1>is radios. So the smallest radio that would work in

0:05:26.556 --> 0:05:28.956
<v Speaker 1>the frequency band that is designated for satellites to do

0:05:28.996 --> 0:05:32.316
<v Speaker 1>Earth imaging costs more than a million dollars I think

0:05:32.356 --> 0:05:35.676
<v Speaker 1>a few million dollars and was bigger than our entire

0:05:35.756 --> 0:05:37.996
<v Speaker 1>satellite is meant to be. And we were like, well,

0:05:38.116 --> 0:05:39.716
<v Speaker 1>damn it, that's not going to work because most of

0:05:39.716 --> 0:05:41.956
<v Speaker 1>the satellite needs to be our telescope. We need to

0:05:41.996 --> 0:05:44.876
<v Speaker 1>scram it into a little motherboard and have a little

0:05:44.876 --> 0:05:48.276
<v Speaker 1>antenna on the side. And by the way, that that

0:05:48.316 --> 0:05:51.596
<v Speaker 1>system would only produce about a few megabits a second,

0:05:51.836 --> 0:05:56.036
<v Speaker 1>and we needed gigabits a second, so it was not

0:05:56.156 --> 0:05:58.596
<v Speaker 1>only too expensive and too massive, it didn't even do

0:05:58.636 --> 0:06:01.636
<v Speaker 1>the job. And so we built our own radios from scratch,

0:06:01.836 --> 0:06:04.836
<v Speaker 1>designed these antenna that was based on pieces of wire,

0:06:04.876 --> 0:06:07.636
<v Speaker 1>but their machine learning designs so that they even though

0:06:07.636 --> 0:06:10.836
<v Speaker 1>it's just like a paper clip, almost we now get

0:06:11.196 --> 0:06:13.876
<v Speaker 1>it's the perfect paper clip. Yes, it's a perfect dedesigned

0:06:13.876 --> 0:06:17.596
<v Speaker 1>paper clip. And we can now get one point eight

0:06:17.676 --> 0:06:20.996
<v Speaker 1>gigabits a second over a thousand kilometer arrange, which is

0:06:21.076 --> 0:06:23.916
<v Speaker 1>unheard of. And how much does it cost? How much

0:06:23.956 --> 0:06:26.836
<v Speaker 1>does it cost of order a thousand dollars thousand dollars

0:06:26.876 --> 0:06:30.756
<v Speaker 1>instead of a million, Yeah, exactly. You know, we didn't

0:06:30.796 --> 0:06:33.916
<v Speaker 1>take space grade components. We took components that we knew

0:06:33.956 --> 0:06:36.876
<v Speaker 1>of work in a vacuum and tried them and had

0:06:37.036 --> 0:06:40.476
<v Speaker 1>instead of trying to put all our energies into one spacecraft,

0:06:40.556 --> 0:06:42.356
<v Speaker 1>we would build lots of them and if one or

0:06:42.396 --> 0:06:45.276
<v Speaker 1>two spacecraft die, it's not the end of the world either.

0:06:45.436 --> 0:06:49.396
<v Speaker 1>So by doing that it enabled us to leverage the

0:06:49.516 --> 0:06:52.116
<v Speaker 1>latest technologies. Because if you don't care so much, if

0:06:52.156 --> 0:06:54.916
<v Speaker 1>it's for sure going to work. You know, you just

0:06:54.956 --> 0:06:57.596
<v Speaker 1>want it to be like eighty percent probable of working

0:06:57.676 --> 0:07:00.716
<v Speaker 1>or ninety percent probable of working. You can take bigger risk,

0:07:00.756 --> 0:07:03.836
<v Speaker 1>which actually means you can more use more latest gadgets tree. Yeah,

0:07:03.876 --> 0:07:06.476
<v Speaker 1>so that's a bigger idea. So by using cheaper components,

0:07:07.116 --> 0:07:10.436
<v Speaker 1>it's okay if they fail, because you're launching one hundred

0:07:10.476 --> 0:07:15.076
<v Speaker 1>satellites and if ninety five of them naked, that's just fun.

0:07:15.436 --> 0:07:17.116
<v Speaker 1>That's just fine. And let me give you a concrete

0:07:17.116 --> 0:07:19.156
<v Speaker 1>example of the last launch we did just a few

0:07:19.156 --> 0:07:23.356
<v Speaker 1>weeks ago on a SpaceX rocket. We launched forty four

0:07:23.476 --> 0:07:27.716
<v Speaker 1>satellites and one of them hasn't worked, and we barely

0:07:28.596 --> 0:07:31.796
<v Speaker 1>you know, blinked as an organization, you know it was.

0:07:32.236 --> 0:07:35.076
<v Speaker 1>In fact, that's part of the place they're they're built

0:07:35.076 --> 0:07:38.476
<v Speaker 1>to fail. What how is there some amount of time

0:07:38.596 --> 0:07:41.116
<v Speaker 1>like you expect ten percent failure rate or five percent

0:07:41.196 --> 0:07:42.916
<v Speaker 1>or do you have that sort of penciled down? You know,

0:07:42.996 --> 0:07:45.716
<v Speaker 1>I've I've asked the team to shoot for more like

0:07:45.796 --> 0:07:48.916
<v Speaker 1>ten percent or twenty percent failure rate, but we've never

0:07:48.956 --> 0:07:52.676
<v Speaker 1>achieved that. We've always been much lower. You need to

0:07:52.716 --> 0:07:56.356
<v Speaker 1>take more risks, you need to make the right or

0:07:56.396 --> 0:07:59.476
<v Speaker 1>whatever right, right, right right. That's really just that we're

0:07:59.516 --> 0:08:02.796
<v Speaker 1>being too conservative. So you build the satellites. It works.

0:08:02.956 --> 0:08:05.356
<v Speaker 1>You got your cheap satellites. Now you got to get

0:08:05.396 --> 0:08:10.156
<v Speaker 1>them to space. Yes, correct. We call it piggybacking, piggyback payloads.

0:08:10.796 --> 0:08:13.156
<v Speaker 1>So obviously there's a big satellite paying for most of

0:08:13.156 --> 0:08:15.236
<v Speaker 1>the cust of the bucket, and we say, well, there's

0:08:15.236 --> 0:08:16.756
<v Speaker 1>a little bit of space there, can we shove a

0:08:16.756 --> 0:08:19.556
<v Speaker 1>few satellites in. It's like we're hitchhikers. So it's like

0:08:19.556 --> 0:08:21.516
<v Speaker 1>we're going to the Florida and we're sticking up our

0:08:21.516 --> 0:08:23.636
<v Speaker 1>thumb and saying, hey, can we can we come up

0:08:23.636 --> 0:08:26.996
<v Speaker 1>with you guys? Well, and your satellites are in fact small, right,

0:08:27.076 --> 0:08:29.596
<v Speaker 1>just like yeah, very small. Tell me what one looks like.

0:08:29.716 --> 0:08:31.236
<v Speaker 1>It is about the size of a loafer bread is

0:08:31.276 --> 0:08:35.396
<v Speaker 1>ten by ten by thirty centimeters. It weighs about five kilograms,

0:08:35.676 --> 0:08:38.796
<v Speaker 1>So it's so tiny for a satellite, tiny, smaller than

0:08:39.196 --> 0:08:42.476
<v Speaker 1>anybody would think of a satellite being absolutely, you can

0:08:42.516 --> 0:08:44.396
<v Speaker 1>take them on our hand luggage. In fact, that's how

0:08:44.436 --> 0:08:46.236
<v Speaker 1>we did get them to the launch site. Early on.

0:08:46.276 --> 0:08:48.596
<v Speaker 1>You checked them on the you carried out, just carried

0:08:48.636 --> 0:08:50.596
<v Speaker 1>them on a carry on luggage. Yeah, you put them

0:08:50.596 --> 0:08:52.916
<v Speaker 1>in the overhead or just put them in the overhead.

0:08:53.076 --> 0:08:54.916
<v Speaker 1>I mean we wrap them up a bit and stuff,

0:08:54.916 --> 0:08:57.436
<v Speaker 1>and we have to tell you really have carried them

0:08:57.436 --> 0:09:00.516
<v Speaker 1>on the plane. Oh yeah, yeah to the launch site. Yeah.

0:09:00.556 --> 0:09:05.276
<v Speaker 1>So I mean in a sense like the satellites are cool,

0:09:06.556 --> 0:09:10.076
<v Speaker 1>but you're a data business, right, Your business is not

0:09:10.276 --> 0:09:13.476
<v Speaker 1>really launching satellites. It's selling data and specific So you

0:09:13.516 --> 0:09:17.636
<v Speaker 1>take a picture of the whole earth every day. Who

0:09:17.676 --> 0:09:19.036
<v Speaker 1>do you sell it to? What do you do with it?

0:09:19.356 --> 0:09:21.636
<v Speaker 1>So the biggest one is agriculture, the one I just mentioned,

0:09:21.636 --> 0:09:24.756
<v Speaker 1>and we help them improve efficiency by twenty or forty percent,

0:09:25.076 --> 0:09:28.396
<v Speaker 1>decrease use of fertilizer, similar sort of amounts. So that's

0:09:28.396 --> 0:09:32.796
<v Speaker 1>a big deal for big industry like that forestry. We

0:09:32.836 --> 0:09:37.876
<v Speaker 1>work with mapping like Google, help improve the maps, civil

0:09:37.916 --> 0:09:41.836
<v Speaker 1>government with disaster response, so floods, fires, earthquakes. We help

0:09:42.236 --> 0:09:46.276
<v Speaker 1>countries monitor marine protected areas and coral reef zones and

0:09:46.316 --> 0:09:51.596
<v Speaker 1>make sure that there's not illegal fishing. Insurance, hedge funds.

0:09:52.156 --> 0:09:56.596
<v Speaker 1>Spying comes to mind, like our intelligence agencies clients of yours,

0:09:56.676 --> 0:10:00.516
<v Speaker 1>Yes they are, but we take a super important principle

0:10:00.556 --> 0:10:03.796
<v Speaker 1>which is why I think it's different than the classical

0:10:03.876 --> 0:10:07.396
<v Speaker 1>way the earth imaging can be used in this arena,

0:10:07.476 --> 0:10:11.556
<v Speaker 1>which is non exclusivity. We can provide that data because

0:10:11.556 --> 0:10:14.356
<v Speaker 1>we scan automatically. We are not mainly just taking task

0:10:14.396 --> 0:10:18.556
<v Speaker 1>for a specific location for a specific customer, say the CIA.

0:10:18.676 --> 0:10:21.676
<v Speaker 1>You know, we are scanning the whole earth, and if

0:10:22.156 --> 0:10:25.156
<v Speaker 1>they want to buy it, that's okay. But other people

0:10:25.196 --> 0:10:28.156
<v Speaker 1>could also buy the same thing, and that's really important.

0:10:28.276 --> 0:10:30.396
<v Speaker 1>Let me ask you about privacy though, is there a

0:10:30.396 --> 0:10:33.596
<v Speaker 1>creepy version of your company? Not that you're that version,

0:10:33.636 --> 0:10:35.636
<v Speaker 1>but like, do you know what I'm saying? Basically, the

0:10:35.676 --> 0:10:38.116
<v Speaker 1>answer is, we don't really get into personal privacy. And

0:10:38.276 --> 0:10:42.596
<v Speaker 1>here's why. With five hundred kilometers up. That's like me

0:10:42.796 --> 0:10:48.156
<v Speaker 1>in San Francisco pointing my camera at Los Angeles and

0:10:48.276 --> 0:10:51.556
<v Speaker 1>expecting to see personal details. It turns out you can't.

0:10:51.596 --> 0:10:55.276
<v Speaker 1>You're too far away that pixel size. Maybe that will

0:10:55.356 --> 0:10:58.156
<v Speaker 1>go in half in time, you know, but you're still

0:10:58.196 --> 0:11:01.236
<v Speaker 1>not going to be identify a person. You know, even

0:11:01.276 --> 0:11:03.436
<v Speaker 1>if it goes in ten x, you still won't be

0:11:03.476 --> 0:11:06.796
<v Speaker 1>able to identify a person. So we're a very long

0:11:06.876 --> 0:11:10.556
<v Speaker 1>way from being able to do anything like that. After

0:11:10.596 --> 0:11:13.796
<v Speaker 1>the break Will's next big problem? How do you turn

0:11:13.836 --> 0:11:26.076
<v Speaker 1>a picture of the earth into useful, actionable information. That's

0:11:26.116 --> 0:11:28.116
<v Speaker 1>the end of the ads. Now we're going back to

0:11:28.116 --> 0:11:31.636
<v Speaker 1>the show. So I want to talk about some of

0:11:31.676 --> 0:11:34.876
<v Speaker 1>the problems you haven't figured out how to solve yet,

0:11:34.916 --> 0:11:37.316
<v Speaker 1>and I think in particular with the data business. Right,

0:11:37.316 --> 0:11:39.956
<v Speaker 1>I mean, it seems like that's really the sort of

0:11:39.996 --> 0:11:43.596
<v Speaker 1>frontier for you. Right. You have these pictures every day

0:11:43.596 --> 0:11:45.396
<v Speaker 1>of the earth, and it's sort of how do you

0:11:45.436 --> 0:11:49.676
<v Speaker 1>make them useful? Right? So what is something? Yeah, what's

0:11:49.676 --> 0:11:53.716
<v Speaker 1>a problem you haven't solved in that part of your business? Well? Many,

0:11:54.116 --> 0:11:59.276
<v Speaker 1>because the use cases are many, And you're right, a picture,

0:11:59.716 --> 0:12:02.596
<v Speaker 1>it can be useful, but most people, most of the

0:12:02.636 --> 0:12:05.876
<v Speaker 1>time want more than a picture. That agriculture of farmer

0:12:05.956 --> 0:12:08.196
<v Speaker 1>actually doesn't want the picture. They might look at it,

0:12:08.236 --> 0:12:10.316
<v Speaker 1>they know what their field look, but they more want

0:12:10.436 --> 0:12:12.956
<v Speaker 1>where do I should I add fertilizers? Where should I order?

0:12:14.676 --> 0:12:18.076
<v Speaker 1>The civil government doesn't want to have pictures. They want

0:12:18.076 --> 0:12:20.836
<v Speaker 1>to know where other roads that are still working after

0:12:20.836 --> 0:12:23.476
<v Speaker 1>the flood or the bridges down after the you know,

0:12:23.636 --> 0:12:25.716
<v Speaker 1>a hurricane or whatever said that they can send in

0:12:25.716 --> 0:12:28.876
<v Speaker 1>the relief supplies. So they want more detailed information that

0:12:28.916 --> 0:12:30.636
<v Speaker 1>it's in principle in those images, but you have to

0:12:30.636 --> 0:12:33.516
<v Speaker 1>extract out. So the big project across all of these

0:12:33.556 --> 0:12:37.796
<v Speaker 1>things that we're doing is something that I call queriable Earth.

0:12:37.996 --> 0:12:41.876
<v Speaker 1>Queriable like searchable, like a search query, searchable earth shot.

0:12:42.396 --> 0:12:46.676
<v Speaker 1>And the reason I think about it the way about this.

0:12:46.916 --> 0:12:51.716
<v Speaker 1>Google indexed what's on the Internet and made it searchable. Right.

0:12:51.756 --> 0:12:54.116
<v Speaker 1>It made a database of where all the pages are,

0:12:54.316 --> 0:12:57.716
<v Speaker 1>what contents are where, so that when you type in whatever,

0:12:57.956 --> 0:13:00.676
<v Speaker 1>you get an answer that's relevant. We have the ability

0:13:01.356 --> 0:13:04.516
<v Speaker 1>with the machine learning. The same tools that pick out

0:13:04.716 --> 0:13:07.676
<v Speaker 1>cats and dogs from pictures that you post online and

0:13:07.836 --> 0:13:10.476
<v Speaker 1>can pull that out is the same too. We can

0:13:10.596 --> 0:13:12.756
<v Speaker 1>use to put out this is a tree, this is

0:13:12.796 --> 0:13:15.116
<v Speaker 1>a road, this is a house, this is a building,

0:13:15.196 --> 0:13:18.436
<v Speaker 1>this is a ship. There's a plane out of our images.

0:13:18.916 --> 0:13:22.796
<v Speaker 1>So we call it object identification using computer vision or

0:13:22.836 --> 0:13:27.316
<v Speaker 1>machine learning or artificial intelligence is the broadest category. Then

0:13:27.436 --> 0:13:30.476
<v Speaker 1>you can imagine that the interface to our data becomes

0:13:30.516 --> 0:13:32.916
<v Speaker 1>less and less the imagery of the earth and more

0:13:32.916 --> 0:13:35.956
<v Speaker 1>and more a little search box and you can put in, hey,

0:13:35.996 --> 0:13:39.676
<v Speaker 1>how many roads are there in India? Give me a

0:13:39.716 --> 0:13:43.236
<v Speaker 1>plot of that, versus time, tell me where the deforestation

0:13:43.596 --> 0:13:46.236
<v Speaker 1>is between this month and last month in the Congo

0:13:46.276 --> 0:13:50.276
<v Speaker 1>basin or the Amazon. The kind of data that you

0:13:50.276 --> 0:13:52.116
<v Speaker 1>should be able to pull out and I call it yeah,

0:13:52.156 --> 0:13:56.196
<v Speaker 1>queriabile Earth. So that's the dream. That's the problem. It's

0:13:56.196 --> 0:13:59.236
<v Speaker 1>a big problem. I mean, it's fundamentally an AI machine

0:13:59.276 --> 0:14:01.676
<v Speaker 1>learning problem. Like, are you guys? Do you guys have

0:14:01.716 --> 0:14:04.356
<v Speaker 1>to solve that AI machine learning problem? Is it sort

0:14:04.356 --> 0:14:08.516
<v Speaker 1>of the frontier of machine learning and really turning images

0:14:08.596 --> 0:14:12.956
<v Speaker 1>into the data right or at least into language? I mean,

0:14:12.996 --> 0:14:15.836
<v Speaker 1>what has to happen? How do you solve that problem? Well,

0:14:15.956 --> 0:14:18.316
<v Speaker 1>luckily computer vision has come a long way and we

0:14:18.356 --> 0:14:20.156
<v Speaker 1>don't have to solve it all ourselves. We are doing

0:14:20.236 --> 0:14:23.516
<v Speaker 1>some of that machine learning ourselves, but we also work

0:14:23.556 --> 0:14:27.196
<v Speaker 1>with partners, especially because a lot of it's bespoke to

0:14:27.276 --> 0:14:30.556
<v Speaker 1>different regions, to different problems, statements. So we have done

0:14:30.556 --> 0:14:32.276
<v Speaker 1>some core things that we think a lot of people

0:14:32.316 --> 0:14:36.196
<v Speaker 1>are interested in, roads, building ships, planes, there's a number

0:14:36.236 --> 0:14:38.996
<v Speaker 1>more who are we going after? And just to be clear,

0:14:39.076 --> 0:14:41.276
<v Speaker 1>can anybody who wants to just go to your website

0:14:41.316 --> 0:14:45.436
<v Speaker 1>and search whatever how many roads are there in Michigan? No, No,

0:14:45.596 --> 0:14:49.196
<v Speaker 1>you can't. Actually you can sign on a trial account

0:14:49.196 --> 0:14:51.396
<v Speaker 1>and you can get some of these capabilities, but generally

0:14:51.636 --> 0:14:55.316
<v Speaker 1>this is set up for at the present more sophisticated users.

0:14:55.756 --> 0:14:57.716
<v Speaker 1>I don't mean to I don't know how sophisticate you

0:14:57.756 --> 0:15:00.356
<v Speaker 1>are personally sitting here in my closet recording a podcast.

0:15:00.396 --> 0:15:03.036
<v Speaker 1>I'm happy to be an unsophisticated US. But you know,

0:15:03.316 --> 0:15:07.756
<v Speaker 1>Google uses our APIs, and those big agg companies use

0:15:07.796 --> 0:15:11.236
<v Speaker 1>our APIs, and they have teams of people and but

0:15:11.236 --> 0:15:13.796
<v Speaker 1>but that's exactly the problem we're trying to crack, is

0:15:13.836 --> 0:15:16.756
<v Speaker 1>to help everyone to be able to have access to

0:15:16.796 --> 0:15:19.476
<v Speaker 1>this data, not just the big organizations that have teams

0:15:19.516 --> 0:15:22.556
<v Speaker 1>of people with PhDs in satellite imagery processing. You know,

0:15:22.596 --> 0:15:25.916
<v Speaker 1>we want to enable it to be that little insurance company,

0:15:25.956 --> 0:15:30.716
<v Speaker 1>that little that little ngo, that university team that's doing

0:15:30.756 --> 0:15:33.156
<v Speaker 1>research on penguins or whatever, you know, Like, we want

0:15:33.156 --> 0:15:35.756
<v Speaker 1>them all to be able to leverage the data. So

0:15:35.796 --> 0:15:37.796
<v Speaker 1>how do we make it easier to use How do

0:15:37.876 --> 0:15:40.156
<v Speaker 1>we help them to build the models that they need

0:15:40.356 --> 0:15:43.356
<v Speaker 1>and build So we're trying to build infrastructure that helps

0:15:43.356 --> 0:15:45.636
<v Speaker 1>them refine this data to make it useful. I mean,

0:15:45.676 --> 0:15:48.636
<v Speaker 1>you need like automation in the middle. Right, there's like

0:15:48.676 --> 0:15:50.636
<v Speaker 1>you got all the pictures, and then you got people

0:15:50.636 --> 0:15:52.876
<v Speaker 1>who want information out of the pictures, and right now

0:15:52.916 --> 0:15:56.156
<v Speaker 1>it's hard and expensive to get the information out of it,

0:15:56.716 --> 0:16:14.396
<v Speaker 1>and so you've got to automate a lot of that process. Bingo. Okay,

0:16:14.516 --> 0:16:16.676
<v Speaker 1>let's get back to the show. We're gonna close with

0:16:16.716 --> 0:16:20.276
<v Speaker 1>the lightning round. Okay, uh, just have a very few

0:16:20.396 --> 0:16:25.356
<v Speaker 1>quick lightning round for the end. What are the chances

0:16:25.396 --> 0:16:27.716
<v Speaker 1>that are Kardashian will go to space? Before you? What

0:16:27.876 --> 0:16:30.596
<v Speaker 1>is a Kardashian? Let me ask it another way, what

0:16:30.636 --> 0:16:33.156
<v Speaker 1>are the chances you'll go to space? I think that

0:16:34.396 --> 0:16:36.756
<v Speaker 1>there's a good chance that anyone that wants to go

0:16:36.796 --> 0:16:39.236
<v Speaker 1>to space will go if they really you know, in

0:16:39.276 --> 0:16:42.476
<v Speaker 1>our lifetime, do you want to go to space? Do

0:16:42.516 --> 0:16:44.316
<v Speaker 1>you want to? I would quite like to, but it's

0:16:44.316 --> 0:16:46.116
<v Speaker 1>not my main goal in life. I would love to

0:16:46.156 --> 0:16:47.876
<v Speaker 1>see the Earth. I'd especially enough to go around the

0:16:47.876 --> 0:16:51.436
<v Speaker 1>moon and look back at the Earth like four times

0:16:51.516 --> 0:16:53.636
<v Speaker 1>wider than the Moon in the sky and be able

0:16:53.636 --> 0:16:58.196
<v Speaker 1>to see the beautiful cradle of civilization. That's a good one.

0:16:58.476 --> 0:17:01.836
<v Speaker 1>Um Star Wars or Star Trek Star check for sure.

0:17:02.116 --> 0:17:04.796
<v Speaker 1>What's one piece of advice you'd give somebody trying to

0:17:04.876 --> 0:17:07.956
<v Speaker 1>solve a hard problem. Um, stick with it, you know.

0:17:08.236 --> 0:17:11.556
<v Speaker 1>I think the biggest thing that differentiates those succeed those

0:17:11.596 --> 0:17:13.876
<v Speaker 1>that don't less the idea than the timing, both of

0:17:13.916 --> 0:17:16.916
<v Speaker 1>which are important, but more of the staying power. It's

0:17:17.396 --> 0:17:21.036
<v Speaker 1>it's perseverance and I think, you know you've got to

0:17:21.236 --> 0:17:22.996
<v Speaker 1>do keep on going in the face of a lot

0:17:22.996 --> 0:17:24.916
<v Speaker 1>of people saying it's not possible. Good. Do you have

0:17:24.916 --> 0:17:27.996
<v Speaker 1>any favorite images that Planet has ever captured. I think

0:17:27.996 --> 0:17:31.796
<v Speaker 1>the very first image we ever captured is an Oregon

0:17:31.956 --> 0:17:37.076
<v Speaker 1>area of partially forested, partially agricultural lands, pasture lands, and

0:17:37.836 --> 0:17:40.036
<v Speaker 1>we could immediately see from that first picture that we

0:17:40.076 --> 0:17:43.476
<v Speaker 1>could identify individual trees in the field. And then we

0:17:43.476 --> 0:17:45.116
<v Speaker 1>were like, oh my god, we can we can do

0:17:45.156 --> 0:17:48.516
<v Speaker 1>this mission. You think you'll ever leave Planet? Leave planet?

0:17:48.556 --> 0:17:51.076
<v Speaker 1>Did you say? Yeah, like the moment when it will

0:17:51.116 --> 0:17:53.316
<v Speaker 1>be time for you to do something else. Last question,

0:17:53.356 --> 0:17:57.396
<v Speaker 1>it's it's definitely my life's work, and I'd be surprised

0:17:57.436 --> 0:18:00.516
<v Speaker 1>if we're not working here in some capacity for a while.

0:18:00.556 --> 0:18:04.596
<v Speaker 1>I mean, look, I enjoy it, and I think I'm

0:18:04.636 --> 0:18:12.956
<v Speaker 1>more likely to leave the planet than Planet. Will Marshall

0:18:13.156 --> 0:18:17.396
<v Speaker 1>is co founder and CEO of Planet, big news in

0:18:17.436 --> 0:18:20.236
<v Speaker 1>the What's Your Problem universe. This week we got our

0:18:20.236 --> 0:18:24.876
<v Speaker 1>own email address, It's problem at pushkin dot Fm. I

0:18:24.876 --> 0:18:26.676
<v Speaker 1>would love to hear what you think of the show.

0:18:26.756 --> 0:18:29.596
<v Speaker 1>If there's topics you want to cover, guests, you want

0:18:29.596 --> 0:18:32.436
<v Speaker 1>to hear, things you like us to do differently, Please

0:18:32.556 --> 0:18:36.996
<v Speaker 1>please do let us know again It's problem at pushkin

0:18:37.316 --> 0:18:42.076
<v Speaker 1>dot Fm. Today's show was edited by Robert Smith, produced

0:18:42.076 --> 0:18:46.036
<v Speaker 1>by Edith Russlo, and engineered by Amanda Kwong. I'm Jacob

0:18:46.036 --> 0:18:48.716
<v Speaker 1>Goldstein and we'll be back next week with another episode

0:18:48.756 --> 0:18:55.996
<v Speaker 1>of What's Your Problem