WEBVTT - Building Bespoke Weather Forecasts 0:00:15.316 --> 0:00:22.516 Pushkin. Here's the thing I did not know about weather 0:00:22.596 --> 0:00:28.316 forecasts until very recently. They basically all come from the government. Sure, 0:00:28.356 --> 0:00:30.836 you may have your favorite weather app, your favorite TV 0:00:30.996 --> 0:00:35.796 weather person, but their forecasts are almost entirely driven by 0:00:35.876 --> 0:00:40.556 data that's collected and analyzed by government agencies. And you know, 0:00:40.676 --> 0:00:43.596 it makes a certain kind of sense. Gathering the data 0:00:43.676 --> 0:00:46.876 you need to make a useful forecast has traditionally been 0:00:47.276 --> 0:00:51.876 a huge expensive undertaking, and having a reliable forecast is 0:00:51.996 --> 0:00:55.596 really valuable for lots of people in lots of different settings. 0:00:55.636 --> 0:00:58.396 So it's good that the government does the work and 0:00:58.516 --> 0:01:02.836 makes forecasts freely available to everybody. But the government is 0:01:03.236 --> 0:01:06.476 the government, and we shouldn't expect it to tailor forecasts 0:01:06.476 --> 0:01:09.556 for different businesses, or even to build forecasts that are 0:01:09.596 --> 0:01:12.436 really useful for people who live in other countries, in 0:01:12.516 --> 0:01:17.676 countries where the government can't afford to produce its own forecasts. Now, 0:01:17.836 --> 0:01:21.316 imagine what a private weather company could do. A company 0:01:21.316 --> 0:01:23.756 that relied not only on government data, but that went 0:01:23.796 --> 0:01:26.836 out and collected data on its own, A company that 0:01:26.876 --> 0:01:30.076 came up with forecasts that would not have been possible before. 0:01:34.796 --> 0:01:37.476 I'm Jacob Goldstein, and this is What's Your Problem, the 0:01:37.516 --> 0:01:40.756 show where entrepreneurs and engineers talk about how they're going 0:01:40.796 --> 0:01:43.356 to change the world once they solve a few problems. 0:01:43.876 --> 0:01:48.116 My guest today is Shimon Alphabets, co founder and CEO 0:01:48.236 --> 0:01:51.676 of tomorrow dot Io, a private company that plans to 0:01:51.716 --> 0:01:54.876 put a constellation of weather satellites into orbit in the 0:01:54.876 --> 0:01:58.516 next couple of years. Shimoon's problem, how do you build 0:01:58.556 --> 0:02:02.556 a private weather company from scratch? We realized it's from 0:02:02.556 --> 0:02:05.956 a jew political and cost effective way, and all kind 0:02:05.956 --> 0:02:08.276 of the only way to solveet is to go to space. 0:02:09.236 --> 0:02:12.076 Shimon and his co founders launched tomorrow dot Io in 0:02:12.156 --> 0:02:16.276 twenty sixteen. The company hasn't launched its satellites yet, but 0:02:16.356 --> 0:02:20.116 it already provides weather related advice for companies like Jet Blue, 0:02:20.356 --> 0:02:24.036 Uber and the NFL. Even before he thought of founding 0:02:24.036 --> 0:02:27.116 the company, weather was a big deal for Schimon When 0:02:27.116 --> 0:02:29.156 he was in his twenties. He was an officer in 0:02:29.196 --> 0:02:32.196 the Israeli Air Force. Whether it is obviously a huge 0:02:32.236 --> 0:02:35.996 deal for pilots for planes, and Shimon was constantly on 0:02:36.036 --> 0:02:41.636 the phone with meteorologists. The solution was, Hey, let's talk 0:02:41.636 --> 0:02:44.996 to a meteorologist three, four or five times, a day, Hey, 0:02:45.036 --> 0:02:46.796 what's going to happen here, what's going to happen there? 0:02:47.436 --> 0:02:49.956 And then I take the data, I analyze what it 0:02:49.956 --> 0:02:52.836 means for me, what it means for the organization. And 0:02:52.876 --> 0:02:54.836 I have to do it several times because the weather 0:02:54.876 --> 0:02:58.036 forecast is constantly changing, and I care about multiple locations 0:02:58.036 --> 0:03:01.236 and I care about multiple parameters. So that was a 0:03:01.356 --> 0:03:05.316 very archaic way of addressing challenges at scale. Calling the 0:03:05.356 --> 0:03:08.476 meteorologist and deciding what each plane should do does not scale. 0:03:08.516 --> 0:03:11.196 So in that universe you're not at scale yet, not scale, 0:03:11.236 --> 0:03:14.116 not efficient, not automatic. When there's a human in the loop, 0:03:14.196 --> 0:03:18.516 there will always be an error. Huh did you make mistakes? 0:03:19.356 --> 0:03:24.276 Of course everyone makes mistakes. I made a few of them. 0:03:24.876 --> 0:03:28.396 You know. I have colleagues that unfortunately lost their lives 0:03:28.436 --> 0:03:32.596 due to whether they did accidents. It was very unfortunate. 0:03:33.116 --> 0:03:35.596 It's just been there, you know. But I didn't think 0:03:35.596 --> 0:03:38.156 I'm going to start a company around it. Shimon moved 0:03:38.156 --> 0:03:40.436 to the US to go to business school, and one 0:03:40.516 --> 0:03:43.436 day a few of his friends, military veterans who like 0:03:43.516 --> 0:03:46.796 shimone wanted to start a company, started talking about the weather, 0:03:47.476 --> 0:03:52.276 and we started talking about past experiences, and everybody We're like, 0:03:52.316 --> 0:03:54.876 oh you also feel this way, Oh you also experienced that. 0:03:54.916 --> 0:03:56.796 And when we started looking at it, we said, okay, 0:03:57.036 --> 0:03:59.436 there is something here. We need to start looking into this. 0:03:59.716 --> 0:04:03.796 And let's try and understand whether you know how the 0:04:03.876 --> 0:04:07.596 technology how forecast is being generated, why is it limited 0:04:07.596 --> 0:04:11.556 in accuracy? And now let's look at how businesses make decisions. 0:04:12.596 --> 0:04:14.236 Do they do it in the same way we did 0:04:14.276 --> 0:04:16.356 it in the past, or is there a better way 0:04:16.356 --> 0:04:19.636 to do it? And what we found out led us 0:04:19.676 --> 0:04:22.276 to start a company. Well, what did you find out 0:04:22.316 --> 0:04:24.636 that led you to start a company? All right, that's 0:04:24.676 --> 0:04:27.316 where it's becoming interesting. So the first thing we found 0:04:27.356 --> 0:04:31.596 out is that climate change is here. That was in 0:04:31.676 --> 0:04:33.996 twenty sixteen. It wasn't cool to speak to speak about 0:04:33.996 --> 0:04:36.636 climate change back then. I mean I think it was cool. 0:04:36.956 --> 0:04:38.996 I think it was cool to me in twenty sixteen. 0:04:39.196 --> 0:04:41.716 Trust me, when I spoke to investors back at the 0:04:41.796 --> 0:04:44.076 time and you spoke about climate change, they were like, 0:04:44.156 --> 0:04:46.196 give me some sass solution. Don't talk to me about 0:04:46.236 --> 0:04:49.596 climate change. Okay, fair sass software as a service keep going. 0:04:49.716 --> 0:04:54.036 So we understood that the problem of managing whatever the 0:04:54.116 --> 0:04:57.876 challenges are is going to get bigger climate change equals 0:04:58.036 --> 0:05:01.196 weather events become more frequent and more volatile in any 0:05:01.196 --> 0:05:04.276 given ear in every part of the world. More hurricanes, 0:05:04.356 --> 0:05:07.876 more wildfires, more heat waves. Doesn't really matter where you are, 0:05:07.956 --> 0:05:12.436 there's some extreme phenomen it is going to happen more frequently. Okay, 0:05:13.236 --> 0:05:15.036 So that's one thing we'll learn. The second thing we'll 0:05:15.076 --> 0:05:19.796 learn is that the technology of forecasting weather, meaning what's 0:05:19.836 --> 0:05:26.716 responsible for the accuracy, is generated and dominated by government agencies. 0:05:27.436 --> 0:05:31.596 And as folks who served in the government for many years, 0:05:32.156 --> 0:05:36.116 we understood that there must be a way to privatize 0:05:36.716 --> 0:05:41.036 and innovate faster. And just to give an example, you know, 0:05:41.156 --> 0:05:44.996 NASA for decades innovated and paved the way to space right, 0:05:45.916 --> 0:05:49.916 But today you have SpaceX, who's augmenting the capability of 0:05:50.236 --> 0:05:54.156 a private company doing what the government has done for decades. Yeah, 0:05:54.356 --> 0:05:57.436 maybe not inventing the rocket from from scratch, but definitely 0:05:57.476 --> 0:06:00.556 taking all the decades of research and adjusting it to 0:06:00.756 --> 0:06:03.436 a commercial use case. What we found out is that 0:06:03.476 --> 0:06:06.996 there is an opportunity to create a SpaceX of weather. 0:06:07.556 --> 0:06:11.636 So SpaceX built rockets. You want to build weather forecasts. 0:06:11.636 --> 0:06:12.916 How do you do that? What do you need to 0:06:13.316 --> 0:06:17.916 make a weather forecast, you need three ingredients. On a 0:06:17.996 --> 0:06:23.276 very high level. You need observations that describe the atmospheric 0:06:23.276 --> 0:06:26.676 conditions in real time, the temperature, the wind pressure. Yeah, 0:06:26.756 --> 0:06:28.836 then you have a good real time description, right. The 0:06:28.916 --> 0:06:31.796 next thing you need is a model, an equation, a 0:06:31.876 --> 0:06:35.116 set of equations. Physical models doesn't really matter. The point 0:06:35.196 --> 0:06:37.756 is that you take the observations and you assimilate them 0:06:37.956 --> 0:06:40.636 into a model, and then the last thing you need 0:06:40.796 --> 0:06:43.636 is a computing power on which you process the model. 0:06:44.676 --> 0:06:48.796 The output of the model is a weather forecast. And 0:06:49.196 --> 0:06:52.596 what we found out is that there is an industry 0:06:52.596 --> 0:06:55.876 of weather forecasting companies, you know, big brands. You know, 0:06:56.036 --> 0:07:00.116 a blue logo, an orange logo, Acy Weather. Right. The 0:07:00.156 --> 0:07:04.156 point is that these guys are here since the sixties, seventies, 0:07:04.276 --> 0:07:08.916 maybe eighties. They just repackaged the forecast that the government 0:07:08.956 --> 0:07:15.436 agency or the government agencies publish every day, every hour whatever. 0:07:16.196 --> 0:07:18.756 So I'll say, I know, the weather forecast is like 0:07:18.796 --> 0:07:20.956 a classic thing to complain about. Oh the weather man 0:07:20.996 --> 0:07:22.636 said it would be Sunday and we had a picnic 0:07:22.636 --> 0:07:25.556 and it rain. I do feel like weather forecasts are 0:07:25.596 --> 0:07:29.516 pretty good, and clearly they've gotten better. Was there a 0:07:29.636 --> 0:07:35.516 particular weakness or failure or set of weaknesses or failures 0:07:35.516 --> 0:07:39.236 that you really thought you could improve. First of all, 0:07:39.276 --> 0:07:41.516 you set out to do this. If I may ask, 0:07:41.556 --> 0:07:44.396 where do you live, I live in New York. I 0:07:44.436 --> 0:07:47.676 live in New York City. Okay, so you're privileged because 0:07:47.716 --> 0:07:49.876 I am privileged. I'll be the first to say I'm 0:07:49.916 --> 0:07:52.916 in Boston. I'm as privileged as you are. Most of 0:07:52.956 --> 0:07:56.236 the world doesn't have Noah, the US government agency, the 0:07:56.276 --> 0:07:58.676 big rich country government agencies that do a pretty good 0:07:58.756 --> 0:08:01.316 job of forecasting exactly. And if you're a private company 0:08:01.316 --> 0:08:06.236 and you try to provide equally accurate forecast for the 0:08:06.276 --> 0:08:09.676 rest of the world, you're limited. You cannot provide it. 0:08:09.996 --> 0:08:12.156 So there is a global problem. So one thing you 0:08:12.196 --> 0:08:15.956 want to do better is provide better forecasts for people 0:08:16.116 --> 0:08:18.516 businesses who don't live in rich countries that have big, 0:08:18.556 --> 0:08:22.156 fancy weather agencies like NOAH in the US. That's one thing. 0:08:22.516 --> 0:08:25.556 The second thing is that even within the US, you know, 0:08:25.916 --> 0:08:30.116 the agency's main job is to save people's lives, Okay, 0:08:30.156 --> 0:08:34.236 it is not to optimize businesses. Right. That also seems reasonable, 0:08:34.276 --> 0:08:37.996 like absolutely, that's what I want them to be optimized for. Absolutely, 0:08:38.036 --> 0:08:41.876 we're on the same page here. But with some scientific 0:08:41.916 --> 0:08:46.156 improvement you can help businesses have better outcome, improve their 0:08:46.196 --> 0:08:50.876 top line, their bottom line, their safety, their efficiency. So 0:08:51.156 --> 0:08:53.236 there is a lot of room for improvement. The other 0:08:53.316 --> 0:08:55.996 element of it is that remember that I said, you 0:08:56.036 --> 0:08:59.916 know it's it's one thing to handle the forecast. The 0:08:59.956 --> 0:09:04.036 second thing is that once you improve either on the observation, 0:09:04.156 --> 0:09:06.276 on the modeling, on the computing power, and you get 0:09:06.276 --> 0:09:10.116 to more accurate forecasts, there is the are part of it, 0:09:10.276 --> 0:09:12.156 which is how you make decisions and how do you 0:09:12.156 --> 0:09:15.996 do it at scale? Right, So this is something that 0:09:16.036 --> 0:09:20.236 the government almost doesn't address at all, except maybe like 0:09:20.276 --> 0:09:22.836 when you need to evacuate a city for a hurricane 0:09:22.916 --> 0:09:28.716 or something, right, very rare circumstances, exactly exactly. Now, I'll 0:09:28.716 --> 0:09:32.116 give an example. A lot of company like utilities or airlines. 0:09:32.716 --> 0:09:35.316 They work in a very similar way to the way 0:09:35.356 --> 0:09:38.316 that I described in my military service. Some guy calling 0:09:38.396 --> 0:09:40.196 some other guy on the phone and being like, what 0:09:40.236 --> 0:09:42.916 should we do. You go to a metrologist, You speak 0:09:42.956 --> 0:09:45.316 to that meteorologist or get a report of road data, 0:09:45.356 --> 0:09:47.636 and then you have to do a full analysis of 0:09:47.636 --> 0:09:49.956 what it means and make a decision it's not scalable. 0:09:50.476 --> 0:09:53.076 Or if I have thousands of trucks driving in the country, 0:09:53.196 --> 0:09:56.236 or if I have thousands of miles of railways track, 0:09:56.796 --> 0:09:59.276 or if I have many airplanes in the air and 0:09:59.316 --> 0:10:02.476 I care about hundreds of airports globally, it's very hard 0:10:02.516 --> 0:10:07.476 to rely on five or ten even meteorologists on staff. Right. 0:10:09.676 --> 0:10:13.036 I've heard you say that a mistake you made early 0:10:13.116 --> 0:10:18.196 on was optimizing for accuracy, and that's really interesting to me, 0:10:18.276 --> 0:10:19.916 and I want you to tell me what that means. 0:10:22.036 --> 0:10:26.236 So at the beginning, we thought that if we just 0:10:26.396 --> 0:10:31.956 create a more accurate forecast, that's it. It's done. Deal 0:10:32.156 --> 0:10:34.596 with serve like that's a hugely valuable thing, right, even 0:10:34.636 --> 0:10:36.796 if you're a little bit more accurate, that's worth a 0:10:36.836 --> 0:10:39.476 ton of money to an airline or the NFL or 0:10:39.556 --> 0:10:43.036 any any number of really big companies. But what we 0:10:43.156 --> 0:10:47.076 found out, but we learned that most of the businesses 0:10:47.116 --> 0:10:51.756 that are impacted by weather do not know what to 0:10:51.796 --> 0:10:55.196 do with a weather forecast or with a weather data 0:10:55.276 --> 0:11:00.516 and they need the full loop, the translation to insights 0:11:00.596 --> 0:11:05.596 and decisions. And that's what helped us design our platform 0:11:05.956 --> 0:11:09.436 and the way we're operating today. So nobody understands hands 0:11:09.476 --> 0:11:12.796 how to read a weather forecast. Basically, how do you 0:11:12.796 --> 0:11:15.916 think from a business perspective? Yeah, so you realize from 0:11:15.916 --> 0:11:19.036 that that like, providing these people with a better weather 0:11:19.036 --> 0:11:21.316 forecast isn't actually going to help them solve their problem 0:11:21.356 --> 0:11:25.276 because they don't because they're not experts in analyzing the 0:11:25.356 --> 0:11:28.636 meaning of a weather forecast. Yeah. I mean you've named 0:11:28.636 --> 0:11:31.276 a lot of your clients publicly, right, I mean whatever, 0:11:31.356 --> 0:11:34.796 Delta and jet Blue and what Uber and the NFL. 0:11:34.836 --> 0:11:36.796 I guess the NFL isn't playing now, Like what do 0:11:36.836 --> 0:11:39.076 you telling JetBlue today? Like what do they want to 0:11:39.116 --> 0:11:43.476 know today? So you know, it's almost summertime. In the 0:11:43.516 --> 0:11:46.796 summer time, as you know, in the biggest hubs like 0:11:46.996 --> 0:11:52.236 JFK or Boston Logan, you have disruptions related to lightning 0:11:52.316 --> 0:11:56.196 strikes thunderstorms. Well, well exactly, they'll shut the airport down 0:11:56.276 --> 0:11:59.036 for hours and everything will be a total mess exactly. 0:11:59.196 --> 0:12:02.156 So instead of someone looking at a model and whatever, 0:12:02.476 --> 0:12:06.716 we're just basically providing a weekly calendar that says, expect 0:12:06.756 --> 0:12:09.556 the disruptions between dead time to dead time. Here are 0:12:09.596 --> 0:12:13.436 the recommendations to do. ABC staff more people here, staffless 0:12:13.476 --> 0:12:17.996 people there. So we actually go into the operational recommendations 0:12:18.156 --> 0:12:21.036 as a result of the expected disruption as a result 0:12:21.076 --> 0:12:23.876 of the weather forecast. Now, listen carefully to what I'm saying. 0:12:24.156 --> 0:12:26.676 It's as a result to the weather forecast. So if 0:12:26.756 --> 0:12:31.076 you're not relying on an accurate forecast, the business insight 0:12:31.236 --> 0:12:35.076 is useless. It's actually damaging. So there's no way to 0:12:35.196 --> 0:12:41.676 get around the need to improve the accuracy. Specifically, what 0:12:41.876 --> 0:12:46.556 are you better at forecasting than anybody else right now? 0:12:47.476 --> 0:12:54.036 Precipitation data. We provide global real time and now casting 0:12:54.356 --> 0:12:58.276 data that is providing a kind of like minute by 0:12:58.356 --> 0:13:01.356 minute forecast for a range of about six hours on 0:13:01.476 --> 0:13:05.796 every point on Earth, which is quite useful. For example, 0:13:06.436 --> 0:13:09.636 you have some sixty minutes minute by minute works that 0:13:09.756 --> 0:13:12.076 you have on some phones, but it's only in the 0:13:12.236 --> 0:13:14.996 US and in the UK. Yes, I do find I 0:13:15.116 --> 0:13:17.356 have that on my phone and I find it's pretty good. 0:13:17.916 --> 0:13:19.996 Dark Skies. I have Dark Skies on my phone and 0:13:20.076 --> 0:13:22.036 it's good. But you're saying, if I if I left 0:13:22.116 --> 0:13:25.356 the US, if I went on vacation to Mexico or something, 0:13:25.436 --> 0:13:29.476 it just wouldn't work. It's not available. It's just not available. 0:13:30.036 --> 0:13:32.996 And we created this thing on a global scale with 0:13:33.276 --> 0:13:36.316 longer time horizon. That's one example. And the other example 0:13:36.476 --> 0:13:39.916 is like quind, we forecast twind in higher accuracy for 0:13:40.036 --> 0:13:41.876 the next day, two days, three days, which is very 0:13:41.956 --> 0:13:44.596 useful for farms. I think, so okay, and are you 0:13:44.716 --> 0:13:47.956 just better at that because you're more focused on it 0:13:48.036 --> 0:13:50.396 and you've trained the models more than and it's more 0:13:50.436 --> 0:13:52.516 important to your clients than it is to say, a 0:13:52.596 --> 0:13:55.556 government agency, so you have an incentive to figure it 0:13:55.596 --> 0:13:59.236 out exactly that. I'm sure that if Noah wanted to 0:13:59.556 --> 0:14:03.196 double down on that, specifically Noah the government agency, they 0:14:03.236 --> 0:14:05.076 would have been able to do that. But they have 0:14:05.196 --> 0:14:08.396 no incentive, and you know, the pace of making a 0:14:08.476 --> 0:14:13.636 decision in a large organization, it's just not enabling them 0:14:13.716 --> 0:14:17.836 to move fast enough. The next problem Shimona's colleagues are 0:14:17.836 --> 0:14:20.556 trying to solve, how do you predict the weather for 0:14:20.716 --> 0:14:23.236 people who live in countries that can't afford a big 0:14:23.396 --> 0:14:27.196 national weather service like Noah to do that. Tomorrow, dot 0:14:27.276 --> 0:14:36.876 Io is going to go to space. That's the end 0:14:36.916 --> 0:14:39.836 of the ads. Now we're going back to the show. Tomorrow. 0:14:39.916 --> 0:14:44.036 Dot Io's next big project is putting a constellation of 0:14:44.116 --> 0:14:47.316 weather satellites into space. And there are two big questions 0:14:47.396 --> 0:14:50.716 I had about that. What problem will it solve and 0:14:51.036 --> 0:14:53.596 what's it going to take to make it happen. So 0:14:54.436 --> 0:14:56.436 the first thing I'll say, what motivated us to get 0:14:56.476 --> 0:15:00.476 to space. The main motivation was how do we optimize 0:15:00.516 --> 0:15:03.316 forecast and make it more accurate? And when we looked 0:15:03.356 --> 0:15:07.716 at the blend between okay, we have observations, we have models, 0:15:08.356 --> 0:15:11.356 we found out that the lack of observations on a 0:15:11.396 --> 0:15:15.196 global scale are the main reason why we cannot improve 0:15:15.236 --> 0:15:19.356 whether focussing significantly on a global scale. So the problem 0:15:19.476 --> 0:15:21.836 wasn't the models. The problem wasn't the computing power. The 0:15:21.876 --> 0:15:24.676 problem is just there's just not enough data when you 0:15:24.716 --> 0:15:27.276 get outside of what outside of the US, Europe, Japan, 0:15:27.436 --> 0:15:31.396 basically the data quality falls off. Yeah, okay. And the 0:15:31.556 --> 0:15:36.036 most important weather sensor that we identified and I think 0:15:36.236 --> 0:15:40.316 is agreed on all the community from NOAH to NASA 0:15:40.396 --> 0:15:44.356 to others, is Doppler radar. A Toppler radar, just to 0:15:44.396 --> 0:15:45.636 be clear, is it the one where you see a 0:15:45.676 --> 0:15:47.876 color like if it's raining really hard, it's red or 0:15:47.916 --> 0:15:52.436 something that stopple? Correct? Okay, Now, radars are looking out 0:15:52.476 --> 0:15:54.596 in the sky and they help us know where is 0:15:54.636 --> 0:15:58.356 the training in real time, how the cloud formation looks like. 0:15:58.516 --> 0:16:01.316 It gives you some kind of three D description of 0:16:01.356 --> 0:16:06.676 the atmosphere. Okay, now what we found out is that 0:16:06.996 --> 0:16:11.796 five billion people leave outside of radar coverage. Five billion. 0:16:11.916 --> 0:16:14.756 He goes out of the border to Mexico, all the 0:16:14.876 --> 0:16:19.196 way to southern South America, and basically you don't know 0:16:19.236 --> 0:16:22.156 where it's raining in real time, say for Africa, India 0:16:22.316 --> 0:16:24.956 and many other places. That is surprising to me. Maybe 0:16:24.996 --> 0:16:29.396 I'm naive, but like, were you surprised when you learned that, No, 0:16:29.596 --> 0:16:31.156 because I came from a place where it was not 0:16:31.676 --> 0:16:34.596 Oh you didn't have it either. You didn't have it either. Yeah, 0:16:34.636 --> 0:16:36.996 it was pretty broken most of the time. And it's 0:16:37.316 --> 0:16:40.396 not a new technology, right, it's a decades old. It's 0:16:40.436 --> 0:16:43.396 not a new technology. But the implication of not having 0:16:43.476 --> 0:16:48.596 it is huge. You cannot provide flood alerts. Pilots when 0:16:48.636 --> 0:16:51.436 they fly, for example, to Cancun, they don't know the 0:16:51.596 --> 0:16:54.436 weather in the route. It's a huge problem for the economy. 0:16:54.836 --> 0:16:57.716 The next point is that the oceans and the seas 0:16:58.636 --> 0:17:02.356 are not covered with radars, and every time, for example, 0:17:02.396 --> 0:17:05.556 a hurricane is formed over the Atlantic. The US government 0:17:05.756 --> 0:17:08.196 is flying airplanes over the eye of the storm to 0:17:08.396 --> 0:17:10.716 scan it with a radar so we can send it 0:17:10.796 --> 0:17:12.276 back to the model that as an understand if it's 0:17:12.276 --> 0:17:14.436 going to be category one, two or three, when and 0:17:14.516 --> 0:17:16.516 where it's going to eat, and whether we should evacuate 0:17:16.596 --> 0:17:21.436 Miami or New Orleans. So rest assured, nobody's flying any 0:17:21.516 --> 0:17:24.276 airplane over a typhoon or a cyclone in the East. 0:17:24.436 --> 0:17:26.796 So this is a huge in Asia. In Asia, they're 0:17:26.876 --> 0:17:28.876 not going out in Asia to get a really accurate 0:17:28.956 --> 0:17:31.116 forecast of where it's going to go. They can't afford 0:17:31.276 --> 0:17:33.516 to do that. But you can do it from space. 0:17:33.676 --> 0:17:36.476 Is that where this is going so exactly, So we 0:17:36.636 --> 0:17:40.476 realize that from a geopolitical and cost effective way and 0:17:40.556 --> 0:17:42.476 all kind of the only way to solve it is 0:17:42.516 --> 0:17:45.356 to go to space. The problem is that radars are 0:17:45.396 --> 0:17:48.916 pretty big. We actually the world has one radar in 0:17:49.036 --> 0:17:53.356 space today. It is called the GPM. It's a program 0:17:53.516 --> 0:17:57.436 by NASA with the collaboration of the Japanese agency. It's 0:17:57.556 --> 0:18:00.596 more than a billion dollar program that created one radar 0:18:00.676 --> 0:18:04.676 in space, a very sophisticated one. We have one radar 0:18:04.756 --> 0:18:08.036 in space today. That radar cost about a billion dollar 0:18:08.156 --> 0:18:11.916 if not more, and it samples every point on Earth 0:18:12.036 --> 0:18:14.956 every three days, So it's not very useful for hurricane 0:18:15.036 --> 0:18:18.996 forecasting because imagine you just sample the hurricanes moving too fast, 0:18:19.356 --> 0:18:22.516 or general weather forecasting. So what we were trying to 0:18:22.636 --> 0:18:26.476 do was to say, how can we take this huge 0:18:26.596 --> 0:18:29.596 radar and minimize it so we can put many of them. 0:18:30.716 --> 0:18:32.876 But we are a small company, we don't have a 0:18:32.956 --> 0:18:35.836 billion dollar How can we actually do it in a 0:18:35.916 --> 0:18:39.436 way that will be cost effective? And the goal is, 0:18:39.636 --> 0:18:42.596 of course, to monitor every point on Earth with a 0:18:42.716 --> 0:18:46.156 radar in almost real time, because when you do that, 0:18:47.036 --> 0:18:51.596 you are going to improve weather forecasting dramatically. You're going 0:18:51.676 --> 0:18:54.956 to improve hurricane cyclone typhoons, you are going to be 0:18:55.236 --> 0:18:58.676 able to provide flood alerts for every point on Earth. 0:18:59.436 --> 0:19:02.476 And it will improve also climate science because now climate 0:19:02.516 --> 0:19:05.516 scientists will have better understanding of what actually happen. No, 0:19:05.676 --> 0:19:07.596 I'm sold on why it would be useful. It seems 0:19:07.636 --> 0:19:09.756 like the hard thing is how do you do it exactly? 0:19:09.876 --> 0:19:12.956 So how do we do that? The first thing we 0:19:13.076 --> 0:19:15.236 did was to focus on the sensor. How can we 0:19:15.316 --> 0:19:19.116 build a sensor that we'll keep most, if not all, 0:19:19.156 --> 0:19:23.916 the characteristics of the radar. We looked at and how 0:19:23.996 --> 0:19:26.996 can we make it small enough so we can launch 0:19:27.036 --> 0:19:31.596 it a not a nano or micro satellite, but something 0:19:32.156 --> 0:19:35.676 smaller than you know, the stationary satellites, a low orbit. 0:19:36.236 --> 0:19:40.236 And bottom line, we've finished the development of the radar 0:19:40.836 --> 0:19:42.636 and in a few months we're going to launch the 0:19:42.676 --> 0:19:46.196 first satellite out of a constellation of about thirty And 0:19:46.316 --> 0:19:49.756 our constellation is going to have two types of sensors. 0:19:49.916 --> 0:19:52.196 One is the radar, the second is a microwave sounder. 0:19:52.716 --> 0:19:55.676 The combination of the two is going to provide a 0:19:55.876 --> 0:19:59.156 very good scientific result for every point on Earth. You 0:19:59.276 --> 0:20:02.036 sound very confident, like are you at a point where 0:20:02.076 --> 0:20:03.476 you know it's going to work or is it the 0:20:03.556 --> 0:20:05.636 kind of thing that you hope is going to work. No, 0:20:05.796 --> 0:20:07.836 we know it's going to work. The question is, okay, 0:20:07.916 --> 0:20:10.076 will it take us more time? Will we fail in 0:20:10.116 --> 0:20:12.356 the first lunch? Will we need to reiterate between one 0:20:12.436 --> 0:20:15.516 lunch to a number? But it is feasible, it is working. 0:20:15.876 --> 0:20:17.796 It is And how much is it going to cost 0:20:17.836 --> 0:20:21.316 you to get roughly thirty satellites up and monitoring the weather. 0:20:21.916 --> 0:20:29.476 Our early estimations, which so far given the inflation, are 0:20:29.556 --> 0:20:32.636 still are still in the same ballpark. We're looking at 0:20:33.156 --> 0:20:36.676 around one hundred million dollars for the entire constellation. So 0:20:36.876 --> 0:20:39.196 that's a big cost reduction. That's compared to what is 0:20:39.276 --> 0:20:41.916 it saying a billion for an existing one that only 0:20:41.996 --> 0:20:45.276 does once every three days? Yeah, what are the things 0:20:45.316 --> 0:20:47.156 that might go wrong? I mean, it seems like a 0:20:47.276 --> 0:20:50.116 quite hard thing that you're trying to do. I feel like, 0:20:50.276 --> 0:20:51.916 as you're describing it, it's like, oh, yeah, now, all 0:20:51.956 --> 0:20:54.156 we got to do is get these thirty satellites up 0:20:54.156 --> 0:20:56.676 into space and we're going to go But so imagine 0:20:56.716 --> 0:20:58.596 it's still going to be quite hard and lots of 0:20:58.636 --> 0:21:00.916 things can go wrong, of course, So you want me 0:21:00.956 --> 0:21:03.316 to give you examples of things that can go wrong? Yeah, 0:21:03.396 --> 0:21:06.676 what are you worried about? Okay, the rocket can explode 0:21:06.716 --> 0:21:10.476 in lunch. Sure. Classic second thing is that you know, 0:21:10.916 --> 0:21:14.636 we may have some communication malfunction. We may have some 0:21:16.436 --> 0:21:19.276 when we build our satellites and the radars. We may 0:21:19.756 --> 0:21:23.516 have to wait for longer than expected for chips to 0:21:23.636 --> 0:21:26.756 arrive or all kinds of chips. Radiance like supply chain, 0:21:26.836 --> 0:21:29.916 supply chain, supply chain issues is something pretty big right now. 0:21:30.636 --> 0:21:34.636 There are so many things that can happen. But are 0:21:34.716 --> 0:21:36.436 you sure the thing you built is going to work? 0:21:36.516 --> 0:21:38.356 All the things you've described as like, oh yeah, the 0:21:38.436 --> 0:21:40.516 rocket could blow up, that's not really our faulter, the 0:21:40.596 --> 0:21:43.276 chip oncome, that's not really our fault. Like, is it 0:21:43.476 --> 0:21:44.716 is it at the point where it's like, oh, yes, 0:21:44.796 --> 0:21:46.716 this will definitely work. Is it like that or is 0:21:46.716 --> 0:21:50.116 it possible that Okay, it's gonna work. It's gonna work. 0:21:50.316 --> 0:21:52.996 The question is is it going to be more expensive 0:21:53.076 --> 0:21:55.796 than we thought, It's going to take longer, and there 0:21:55.876 --> 0:22:00.876 might be you know, business implications on tomorrow. But it 0:22:01.116 --> 0:22:04.476 is going to work. It's not a question of science 0:22:04.756 --> 0:22:07.396 business like like might you run out of money before 0:22:07.436 --> 0:22:09.676 you can get it going? When you say business, everything 0:22:09.756 --> 0:22:12.876 can happen in that context. But this thing is working. 0:22:13.756 --> 0:22:16.356 Pending one hundred million to put a fleet of satellites 0:22:16.356 --> 0:22:19.876 into space, is it's still a lot for your business? 0:22:20.196 --> 0:22:23.476 It is a lot. And the market is very bad. 0:22:23.516 --> 0:22:25.996 It's probably the toughest market in the last twenty years 0:22:26.556 --> 0:22:30.676 for tech companies. The market for raising funding you mean, yeah, yeah. 0:22:31.116 --> 0:22:36.276 The investors are not very happy to see businesses that 0:22:36.916 --> 0:22:39.836 waste money or spend money or invest money, depending on 0:22:39.916 --> 0:22:44.036 how you look at it to build a solution, and 0:22:44.156 --> 0:22:49.116 it's definitely a challenge, and I just hope that, you know, 0:22:49.276 --> 0:22:53.876 the investment community will keep supporting us. We'll get to 0:22:53.916 --> 0:22:55.836 the lightning round in a minute, but before we do, 0:22:56.356 --> 0:22:58.756 I just want to say that what Shimone talked about 0:22:58.796 --> 0:23:01.916 in this episode is actually a really good example of 0:23:01.996 --> 0:23:04.796 a big idea that came up in an earlier episode 0:23:04.916 --> 0:23:07.836 of the show. It was the episode where I interviewed 0:23:07.876 --> 0:23:10.476 the founder of the company Rocket Left, and I was 0:23:10.556 --> 0:23:13.596 going on about how making rockets and satellites cheaper was 0:23:13.676 --> 0:23:15.716 a big deal, and he made the point that the 0:23:15.796 --> 0:23:19.036