April 11, 2024 • 34 mins
Kai Marshland is the co-founder and chief product officer at WindBorne Systems. Kai's problem is this: How do you build weather balloons that can stay in the air for months at a time, and pair the data gathered by the balloons with AI to make weather forecasts that are way better than anything we have today?
See omnystudio.com/listener for privacy information.
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Speaker 1 (00:15):
Pushkin. Every day around the world, more than a thousand
weather balloons are launched into the sky. The balloons float
high up into the atmosphere, sending back information you know, temperature,
wind speed, air pressure, et cetera, and then a couple
hours later, the balloons pop. This is basically the way
(00:39):
weather balloons have worked for decades, and the information the
balloons send back is really useful for weather forecasts. But
the information the balloon send back is also pretty limited
because the balloons only stay in the sky for a
couple hours, they don't fly very far. If we could
figure out how to make balloons stay up for longer,
they could blow in the wind and travel thousands of miles.
(01:01):
They could travel across continents and across oceans and send
us back a lot more data and give us a
much clearer picture of what weather is coming our way.
I'm Jacob Goldstein and this is What's Your Problem, the
show where I talk to people who are trying to
make technological progress. My guest today is Kai Marshland. He's
(01:25):
the co founder and chief product officer of Windborne Systems.
Kai's problem is this, can you build weather balloons that
stay in the air for weeks or months instead of hours,
And can you pair the data from those balloons with
AI to make weather forecasts that are way better than
anything we have today. Kai got interested in balloons back
(01:45):
in twenty fifteen. He was a freshman at Stanford and
he joined the Student Space Initiative, which sounds kind of
fancy but in fact was basically a bunch of college
kids trying to build their own weather balloons.
Speaker 2 (02:02):
The first half dozen flights of our balloons were complete
and total failures.
Speaker 1 (02:08):
When do things start working?
Speaker 2 (02:10):
That would be back in June of twenty sixteen. This
is the end of my freshman year, and I think
our longest flight that year had been fourteen minutes, so
shorter than a normal weather balloon.
Speaker 1 (02:27):
Buy a lot, Buy a lot.
Speaker 2 (02:29):
And also the person who had started this project, who
then became my co founder, had just graduated and was
about to leave what we thought never to be seen again.
And school has ended. We can't even get into the
building because our key cards have stopped working, so we
(02:52):
have to tailgate someone in to get our balloon launch
equipment out. Go out to the middle of nowhere in
the central Valley of California, and if this launch didn't succeed,
windborne would not exist.
Speaker 1 (03:07):
Okay, so I can guess what happened next based on
that fact. But tell me what happened.
Speaker 2 (03:13):
Yeah. So it got to be about four am, and
we're out in the middle of this park, really cold,
and the sprinklers turn on. They start slowly swiveling around
towards our delicate electronics, and so I have to hurl
(03:33):
myself onto the sprinklers, getting soaked, just to save our electronics.
Speaker 1 (03:37):
It's like the nerd version of throwing yourself on a
grenade exactly.
Speaker 2 (03:40):
I really felt like I was in an action movie sequence.
Ah good, But that sacrifice really paid off because with
that flight, we managed to set the world record for
weather balloon endurance.
Speaker 1 (03:56):
How long did it stay up?
Speaker 2 (03:57):
It stayed up for seventy six hours?
Speaker 1 (04:00):
Wow, and your previous best.
Speaker 2 (04:02):
Was fourteen minutes exactly.
Speaker 1 (04:04):
So you're in college, how do you build weather balloons
that are better than whatever the federal government? Noah's launching
our you know, state of the art weather balloon.
Speaker 2 (04:12):
People. So the first big thing is that some new
consumer electronics have come out, in particular, things like micro
controllers and lightweight, low power satellite communications, and we realize
that we can use these innovations to make a balloon
(04:35):
smarter and to control its altitude.
Speaker 1 (04:38):
What's a micro controller.
Speaker 2 (04:39):
Micro controller is a super small computer that you can
put in any device to give it a brain.
Speaker 1 (04:49):
And they're cheap.
Speaker 2 (04:50):
They're dirt cheap. Anytime you hear the word Internet of things,
that means micro controlers.
Speaker 1 (04:56):
And nobody else was doing this at the time, Like
all the big, you know, well funded weather agencies weren't
sticking my micro controllers on their on their weather balloons.
Speaker 2 (05:06):
Well, with these big agencies, they are really incentivized to
keep things stable because weather is this really important thing
that billions of people depend on, and so they're not
going to go and say, hey, what crazy experiments can
we run.
Speaker 1 (05:24):
Their incentive is just like, don't screw it up exactly
the way we did it yesterday. Don't screw it up
and you won't get fired exactly. And so specifically, what
was it that you were doing that no one had
done before.
Speaker 2 (05:37):
Yeah, So it's a very simple concept that is really
hard to make work and practice. The way we control
our altitude is when it gets too high up, we
vent some of our gas so it has less lift.
When we fall down too far, we drop some ballast
so it stops falling. But the hard part about this
(06:00):
is it has to function at negative seventy degrees celsius.
That's the temperature of dry ice. You have to have
a lot of on board software. That's where the micro
controllers come in to do things like understand is this
just turbulence that you're hitting or is it actually a
real change in lift that we need to drop ballast
(06:21):
or vent gas to account for. And in fact, we
stayed up twenty four to seven. Every single time it
talked to us. Every five minutes, we had it play
an airhorn sound because we were, of course falling asleep
in the middle of them to see what it was doing.
Speaker 1 (06:39):
So, okay, so you set the record, you stay up
for what three days watching it? How far did it go?
Speaker 2 (06:46):
It flew all the way across the country and landed
out in the Atlantic Ocean. But the real reason why
we decided to form a company around this was because
we realized the impact this could have. We got into
this from the engineering side. The lands are fun, but
(07:07):
we realized, wait a secd eighty five percent of the
Earth's atmosphere is invisible to humanity. Weather is this crazy,
unpredictable thing, and we can solve that. And weather is
so much more than just do you bring an umbrella
to work tomorrow is the single most immediately destructive aspect
(07:29):
of climate change, and improving the weather forecast it of
course helps with adapting to climate change, things like predicting
where a hurricane will make landfall, but it can also
help with preventing climate change in the first place. If
you have a better weather forecast, you can better route
ships and planes to save a huge amount of fuel.
(07:53):
You can accelerate the transition to renewables because you know
when the wind will be blowing or the sun will
be shining. And we looked at this and said, no
one else has our balloon technology. If we don't do this,
no one will. And if we want away from this opportunity,
we can't live with ourselves.
Speaker 1 (08:13):
I mean, I buy that the stakes are high. I
buy that it could be very helpful, but like, why
wouldn't anybody else do it?
Speaker 2 (08:22):
Yeah, a lot of people are trying to improve the
weather forecast. But what's unique about Windborne is the combination
of our balloon technology with our AI weather forecasts, because
really those are the two levers to pull to increase
the accuracy of a weather forecast.
Speaker 1 (08:44):
You mentioned that eighty five percent of the world lacks
good weather data, which was surprising to me the first
time I heard it. But I would think, like, get
satellites do it. That's kind of I guess my naive
ish thought. It's like, I know there's a lot of
satellites looking down at the Earth all the time.
Speaker 2 (09:02):
I'm actually a big fan of the space industry. I
used to work at SpaceX. But the problem is the
laws of physics fundamental limit what satellites can measure. Take
for example, pressure. It turns out pressure is extremely important
for predicting the weather because it determines where the winds
are blowing, how the weather systems are moving. But a
(09:24):
satellite fundamentally cannot measure pressure from space because it's not
in the atmosphere. It can't see what's going on.
Speaker 1 (09:32):
So you start the company you're good at making weather
balloons that go up and stay up for a long time,
and that you can steer. I also read that you
launched thinking that you could collect data for a tenth
the cost of existing alternatives, which sounds compelling, but as
I understand was not compelling enough. Is that right?
Speaker 2 (09:54):
It is. We're now at one hundred and fifty times
more data per dollar than alternatives.
Speaker 1 (09:59):
Okay, was there some reason one tenth the cost was
not cheap enough.
Speaker 2 (10:04):
Yeah. When we started the company, we thought it would
be cheap enough. But it turns out when you really
look at the scale of weather data collection, you need
to really understand the atmosphere. You want ten thousand balloons
aloft concurrently, that's a balloon every sixty miles in the atmosphere.
(10:27):
And in order to get to that level of scale,
it's the difference between your company spending one hundred million
dollars a year and spending a billion dollars a year.
One was a lot more in reach.
Speaker 1 (10:41):
How do you drive down the cost to one one
hundred and fiftieth the cost? I mean, I'm sure it's
many many, many incremental you know, efficiency gains. But like,
what's an example of one.
Speaker 2 (10:51):
Yeah, Well, one of the big pieces is improving the
software that flies on it so that the balloon can
fly for longer. I talked about in the student group
that first flight lasting seventy six hours. Now our longest
flight can fly for over four days.
Speaker 1 (11:10):
Wow.
Speaker 2 (11:11):
And the longer you fly, well, the hardware costs stays
the same, so that means you're collecting a lot more data.
Speaker 1 (11:18):
Yeah. Yeah. So basically, make the balloon stamp for longer
is the fundamental way that you make it cheaper exactly,
And how do you make it fly longer?
Speaker 2 (11:27):
Yeah, Well, one of the big things is improving the
software to better decide when do you vent gas, when
do you drop ballast or really one of the other
big things is just making everything smaller and lighter, because
the smaller it is, the lighter it is, the less
chance of a leak, the less ballast you have to use.
(11:50):
And things have just shrunk down so far. It really
surprises me sometimes when I'm like, wait, that tiny thing
the size of a dime replaces the thing that was
the size of a dinner plate before.
Speaker 1 (12:06):
Yeah, that's amazing. So okay, so let's talk about where
you are today. Let's talk about sort of how it works.
How big are the balloons?
Speaker 2 (12:15):
So the balloon is two pieces. There's the envelope that's
the bag that holds all parts the balloon part of
the balloon, and then there's the main unit, which is
the electronics and the ballast.
Speaker 1 (12:33):
The stuff exactly, the balloon and the stuff the balloon part.
Speaker 2 (12:36):
Of the balloon. The balloon part of the balloon is
five and a half meters tall. So that's two and
a half three times the height of person, depending on
how tall you are.
Speaker 1 (12:47):
Yeah, so tall. Yeah, it's a big balloon. And how
how big is the stuff? How big is are the
sensors in the part that's not the.
Speaker 2 (12:56):
Yeah, that stuff is. I guess this is an audio thing,
so I would say about this big.
Speaker 1 (13:06):
The size of a basketball.
Speaker 2 (13:07):
Yeah, it's a roughly the size of a basketball. It
weighs just over four pounds, so about the weight of
a large duck. Okay, and is kind of long and skinny.
It kind of looks like a fish. I think of
it as a trout attached to a giant bag.
Speaker 1 (13:30):
How many of your balloons are in the sky right now? About?
Speaker 2 (13:34):
Yeah, there are a few dozen aloft right now.
Speaker 1 (13:37):
Okay.
Speaker 2 (13:37):
We launch around one hundred a month and are quickly
ramping that up.
Speaker 1 (13:41):
So where do you launch your balloons from?
Speaker 2 (13:43):
We launch them every day from three continents, South Korea,
paloelto New York and Cabo Verde.
Speaker 1 (13:50):
Cabo Verde is just off off the west coast of Africa.
Is that right?
Speaker 2 (13:53):
You got it. One of the reasons why we have
launch site in Cabo Verde right now. That's right where
a lot of hurricanes are forming, and so the fact
that we're collecting data around there is going to be
really impactful for better predicting the path of these hurricanes. Huh.
Speaker 1 (14:10):
So they start there and then they essentially travel across
the Atlantic and into the Americas, and if you can
understand what's going on there, ideally you can sort of
understand the hurricane where it's going to go in the
dream scenario, even just as it's becoming a tropical storm.
Speaker 2 (14:26):
Exactly. Yeah, Noah did an analysis of the Impactor data
had on the twenty twenty two hurricane season, and it
made the forecasts for Hurricane Fiona about twenty percent better.
Speaker 1 (14:43):
Now it's time for a few ads. After the ads,
Kai and I will talk about AI. Of course, we'll
also talk about Winborne's business, what they're selling, and we'll
talk about the company's quest to build balloons that can
stay in the air for months at a time and
make multiple trips around the world. What is your business
(15:16):
right now, like, what are you selling and who you're
selling it.
Speaker 2 (15:18):
To right now. Our business has two pieces to it.
We are selling the observations of the atmosphere we collect
to the government right now, so that those governments can
use this data to improve your weather forecast. And just
a couple of weeks ago, we announced our AI based
(15:40):
weather model, which is the world's most accurate global weather
model bar none.
Speaker 1 (15:45):
I feel like you need a little TM when you
say the world's most accurate global weather model bar none.
Speaker 2 (15:50):
We really do, we really do.
Speaker 1 (15:52):
So let's talk about that. Is that claim validated? I mean,
I know there was news about that just this year,
and congratulations, but also, how do I know that's true? Respectfully?
Speaker 2 (16:01):
Yeah, I love that question because anytime a weather company
makes a claim, you should look at it closely. So,
first off, we've published our results on our website and
so you can dig into some of the raw numbers there. Second,
we're in the process of submitting to weather bench which
(16:23):
is these benchmarks run by Google, which were the previous
holders of this record. So we're actively talking with them
right now about submitting our results getting them validated into
live up there. It's just a process that takes a
little while, so.
Speaker 1 (16:43):
Let's talk about the model you built. So I mean
generally when I talk to people who are working on AI,
they talk a lot about data, right, And it seems
like to some significant degree the models are kind of commoditized,
not quite, but like models are pretty similar, it seems
in many settings at least one to the other, and
the differentiator often ends up being the data. Is that
(17:06):
the case in this instance? I mean, do you think
you're the best. If you're the best because you have
all this data from all your balloons.
Speaker 2 (17:14):
I think that you're spot on. Data is the real
mote here, because what really sets us apart is the
ability to have all of this data that no one
else has and to use that both for training the
model but then also for running the model in real time.
Data isn't just about training. It's about essentially giving your
(17:35):
model the prompt of what's going to happen next, and
you need new data every single day for that.
Speaker 1 (17:44):
Just one thing to clarify. So, if you're selling the
data to governments, are they not sharing it widely? Like
they're paying for the data but they're not. But not
everybody can get at the data? Is that why it's
a mode for you?
Speaker 2 (17:59):
Yeah, so what they're using the data we sell them
for is putting it into conventional physics based weather model
that they then release. So they can't redistribute the data itself,
but the general public can benefit from its use in
(18:20):
these weather models.
Speaker 1 (18:21):
And so just to distinguish and this is a distinction
that's not particular to your company, but you mentioned the
sort of traditional physics based weather models. I mean, I
think it's worth spending just a moment here to distinguish, right,
like between the classic weather model, you know, the sort
of pre AI weather model, and the AI weather model. Like,
(18:43):
what's the basic difference between those two?
Speaker 2 (18:45):
Yeah, So a conventional physics based weather model, it takes
the initial state of the atmosphere and then runs a
bunch of fluid dynamics on it to simulate what's going
to happen to all of these different fluids.
Speaker 1 (19:01):
There's a sort of kind of classic sort of feels
like kind of nineteenth century deterministic. Give me the initial
condition and I'll tell you what's going to happen in
the future. It's that right, it's sort of rules based.
Speaker 2 (19:13):
Exactly exactly, and that is nice because you can see
the exact physics that is being used, but you need
compute clusters. They cost hundreds of millions of dollars in
order to run this because the atmosphere is so big.
(19:34):
And by contrast, a AI based weather model can run
on just a gaming laptop.
Speaker 1 (19:42):
Huh.
Speaker 2 (19:43):
And what it does, by contrast, is effectively picking out statistics.
Speaker 1 (19:49):
I mean, it's just it's machine learning. I presume it's
pattern matching exactly.
Speaker 2 (19:53):
It's our model is a transformer based architecture, the same
thing that powers chat GPT.
Speaker 1 (19:59):
Our A models in general better at this point than
the physics based traditional models.
Speaker 2 (20:04):
It depends on the use case. But if you're talking
about hurricanes, yeah, we ran a case study on Hurricane
Ian and our model would have predicted landfall by two
hundred kilometers closer.
Speaker 1 (20:21):
I mean, that's another one where like I'm intrigued by
what you said, but I'm very eager for I'm not
eager for this hurricane season to come, but like it
will resonate more with me when you do that prospectively, right,
of course, I mean, will you this year be predicting
where hurricanes are going to make landfall?
Speaker 2 (20:41):
We will be predicting that for public safety reasons. We
aren't going to be you won't tell me.
Speaker 1 (20:48):
Yeah you will, but you won't tell me we.
Speaker 2 (20:49):
Will know a hurricane. Okay, but fair, you of course
don't want to say, hey, don't listen to Noah about
these evacuation orders.
Speaker 1 (21:01):
No, no, fair that that is very responsible. So basically,
you're selling data. You are likely soon to be selling forecasts.
That's sort of the business. On the technical side, what
is the frontier? What are you trying to figure out
that you haven't figured out yet?
Speaker 2 (21:19):
Yeah, well, one of the big areas for innovation is
on the AI modeling side. We were kind of surprised
that our models did as well as they did because
there are a lot of quite frankly obvious things that
we haven't done, things like just increasing the amount of
(21:40):
compute we're using to train these models. We use something
like a fifteenth as much as Google did. So what
happens when you train it for longer?
Speaker 1 (21:51):
I mean, I'll say, on the AI side, it's not
obvious that it's optimal for you to be doing the
AI as well. Right, there's a universe where you are
optimizing the balloons and the data, and then someone else
like Google, who has all the computers and all the
AI knows what to do with doing the AI side.
Speaker 2 (22:12):
Of it, right, Yes, and no, I think that where
that falls apart is coupling our data with the models
much more closely. In that there's so much to be
done in terms of figuring out how to better take
advantage of our data into particular and also things like saying,
(22:34):
based on this weather model, where should we be flying
our balloons to improve the forecast? And we're already using
our own AI weather forecasts to do that flight plan
optimization to figure out where our balloons are going to fly.
So it's really this beneficial effect where the better our
weather forecast, the better we can fly our balloons. And
(22:56):
we can then target our balloons to fly to the
places that will most improve the weather forecast.
Speaker 1 (23:03):
That's a good feedback loop.
Speaker 2 (23:04):
There's also a lot to do on the balloon side
of things. I wish I could tell you about our
project that will increase flight time by another factor.
Speaker 1 (23:16):
Of ten, another factor of ten.
Speaker 2 (23:19):
Yeah, so what what are you at now?
Speaker 1 (23:21):
What's the like median flight time?
Speaker 2 (23:23):
Medium flight time is seven to ten days depending on
how we're targeting it.
Speaker 1 (23:30):
And so you think you're going to get to ninety days. Yep,
we around the world in eighty days. Yeah, you say
you wish you could tell me like you feel like
you're about to do it. Yeah, tell me, tell me
without telling me what you can't tell me.
Speaker 2 (23:44):
Okay, I'll do my best. So we have had some
very successful flight tests where we have demonstrated the ability
to fly without using any finite resources.
Speaker 1 (24:03):
So what what is the key finite resource? The the
lift gas, the what is it helium or hydrogen?
Speaker 2 (24:08):
What you used to keep Our balloons are compatible with
both helium and hydrogen, So which we use is dependent
on the country.
Speaker 1 (24:17):
When you say flying without any finite resource, that's what
I think of, yep.
Speaker 2 (24:22):
Okay, yeah, that and ballast.
Speaker 1 (24:25):
Oh right, So so you want to you can? I should?
I guess.
Speaker 2 (24:31):
I mean, there's heat there, leave it there and just say.
Speaker 1 (24:37):
If you get that, could you fly forever?
Speaker 2 (24:40):
That the dream someday, someday we're we're definitely ninety.
Speaker 1 (24:45):
Days for a weather balloon is sort of forever, right.
Speaker 2 (24:47):
It really is. And so, yeah, we've had some very
successful flight tests.
Speaker 1 (24:53):
What's the longest flight you've had to this point?
Speaker 2 (24:55):
Forty days?
Speaker 1 (24:57):
Forty days? Okay?
Speaker 2 (24:58):
Long?
Speaker 1 (24:58):
Yeah?
Speaker 2 (24:59):
Long? And that was without using this technology, was that
like a fluke. It was definitely on the side of
the bell curve. But we've had multiple month long flights.
Speaker 1 (25:11):
What why do your balloons usually what do you say fall?
Crash sounds a little extreme crash fall.
Speaker 2 (25:19):
Yeah, it's that they run out of ballast and lifting gas,
and so these finite resources have been used up. You
don't have a more ballast to drop, you don't have
a more gas event, and so you can no longer
control your altitude.
Speaker 1 (25:37):
What happens when it falls crashes comes down.
Speaker 2 (25:41):
So by the time it falls, it has used up
all of the ballast. So instead of weighing four pounds,
it weighs about two hundred grams.
Speaker 1 (25:56):
Two hundred grams is what half a pound?
Speaker 2 (25:58):
Ish? Yes, I'd looked it up. Zero point four to
four pounds.
Speaker 1 (26:04):
Okay. By the way, when you're getting rid of ballast,
is it just like sand or something? You just like
sprinkle sand out exactly? Okay, So it's half a pound,
so it wouldn't hurt if it hit me on the head?
Is that is that part of the reason half a
pound is important? Would it if it hit me on that?
Speaker 2 (26:21):
Is it? Anybody on that it's never hit anybody. We
do landing simulations and control where it lands to direct
it towards unpopulated areas. But remember it also has this
envelope attached to it, which acts like a parachute, so
it actually falls very slowly. It's very light and not
(26:45):
an issue.
Speaker 1 (26:46):
And then what happens. Then you have this big deflated
balloon sitting on the ground or floating in the ocean,
and is it just what happens to you?
Speaker 2 (26:54):
Yeah? So I love that question because it's a chance
to talk about how our balloons can reduce the amount
of waste going out into the world compared to the
half a million that are launched every year, of which
only a fifth are covered.
Speaker 1 (27:10):
Just get answer directly. I appreciate that you want to
contextualize it, but like, first, let's talk about what happens
with your balloons and then feel free to provide the bigger.
Speaker 2 (27:18):
Cart sounds good, sounds good? Yeah, yeah, So our balloons
are out in the world, and we recover as many
of them as we can. In the long term, we're
aiming to recover essentially all of them because we'll direct
them to specific landing sites.
Speaker 1 (27:36):
I mean, the ocean has got to be tough to write.
I presume when they fall in the ocean, for the
most part, you don't recover them.
Speaker 2 (27:42):
Is that right, exactly? And that's one of the reasons
why improving endurance is so exciting, because if you circumnavigate
multiple times, well, on the last leg, you bring it
down in a field, have somebody drive around and collect
all of them. They are about half million weather balloons
launched each year, and only a fifth of those are recovered.
(28:04):
So when each balloon flies for only two hours, well,
you have to launch a lot more balloons to collect
the same amount of data. So we really see this
as an opportunity to reduce the amount of stuff that's
going out there in the first place.
Speaker 1 (28:20):
Right, So there will actually be fewer balloons going into
the world if you succeed.
Speaker 2 (28:26):
Exactly.
Speaker 1 (28:28):
So, you're at this point where you've learned a lot.
You sort of feels like you're kind of on the
precipice of a lot more. And I want to talk
about sort of two futures. Right. One is a future
where where your company doesn't succeed for any number of
reasons with which you're truly more familiar than I. And
then the other is if you do succeed. Right, So,
(28:48):
in the sort of sad version where you don't succeed,
what are some reasons it might not work out?
Speaker 2 (28:52):
Yeah, I think that probably the biggest reason is that
scaling up hardware is hard. We need to increase manufacturing
by a factor of one hundred effectively, and.
Speaker 1 (29:06):
So it's scaling up that final assembly by a factor
of one hundred is complicated and hard and just kind
of classic hard building. A business gets more capital intensive exactly,
and the money before you can get the money exactly. Okay,
So that's an easy to imagine sad outcome. Let's talk
(29:26):
about the happy outcome. Like it works. You scale up
your balloons, stay up for months at a time. What's
the world look like? What are you doing in that scenario.
Speaker 2 (29:38):
We want everybody to see twice as far into the
future when it comes to weather. So making the ten
day forecast is accurate is the current five day forecast.
Making the twenty day forecast as accurate as the ten
day forecast, so we want people to see twice as
far into the future. We want to pinpoint where hurricanes
are going to make landfall a week in advance, and
(30:02):
we want day to day weather that businesses rely on
to be really accurate, things like never having to cancel
a flight last minute because a bomb cyclone popped up,
saving fuel with all of your shipping because you know
(30:24):
where there will be headwinds. We want to accelerate the
transition to renewables, and we want weather to go from
this crazy, unpredictable source of uncertainty to something that humans
just know about.
Speaker 1 (30:42):
We'll be back in a minute with the lightning round. Okay,
let's do the lightning round. Would you rather have it
be too hot or too cold?
Speaker 2 (31:03):
Too cold any day?
Speaker 1 (31:06):
Okay? The next one is multiple choice. What is your
favorite movie prominently featuring balloons? Wizard of Oz around the
World in eighty days, up the Red Balloon, or none
of the above.
Speaker 2 (31:20):
It's got to be up brilliant.
Speaker 1 (31:21):
Movie, Blimps, overrated or underrated?
Speaker 2 (31:27):
Ooh, so here, I've got to make a distinction between
blimps and Zeppelins because I actually used to work at
a zeppelin company.
Speaker 1 (31:37):
Is that the Larry Page Zeppelin company? It sure is
perhaps the only zeppelin company. Yeah, and so is the
distinction that a zeppelin has a rigid frame?
Speaker 2 (31:49):
Got it in? Won?
Speaker 1 (31:51):
Okay? So how about this. Let me reformulate it to
see if I get it this time. Airships overrated or underrated?
Speaker 2 (31:59):
Underrated? I thought that zeppelins are so cool. I don't
have a great mission driven answer here other than you know,
I think it's amazing. I read too many books growing
up which prominently featured airships.
Speaker 1 (32:18):
Isn't the isn't the Larry Page airship company dreams some
kind of cargo, like the idea that, for like really
heavy things, giant airships would be an efficient way to
move cargo.
Speaker 2 (32:29):
Full disclosure, It's been a long time since I worked there,
so I can't speak to that company in particular. But yeah,
faster deliveries than a ship, more efficient deliveries than a plane.
Speaker 1 (32:43):
Aha, It's like a niche an Until what's something besides
the weather that AI will be really good at predicting?
Speaker 2 (32:53):
Oh? Great question, let's see. Uh. I don't have a
good answer off the top of my head. I think
that it will be really interesting for economics in terms
of taking short term data, various real time indicators, and
(33:18):
making predictions about what the final readings are going to be.
Speaker 1 (33:24):
I'm sure a lot of very smart people are working
on that and they may in fact already have good
models and they're not telling us.
Speaker 2 (33:31):
I think that's likely.
Speaker 1 (33:32):
Is there anything else you want to say?
Speaker 2 (33:35):
I think that covers it. Yeah, great to be on
the show.
Speaker 1 (33:39):
Thanks for your time. It was lovely to talk with you.
Good luck.
Speaker 2 (33:41):
Thanks and if you ever are in Paloelto, you're welcome
to come see a balloon launch.
Speaker 1 (33:48):
Great. So do you still you launch from where you launch?
From that Air Force base or like or just from.
Speaker 2 (33:56):
From our part part?
Speaker 1 (33:57):
Are they easy? Yeah? From the parking lot, that's cool.
Speaker 2 (33:59):
Yeah.
Speaker 1 (34:00):
How much space do you need to launch a weather balloon?
Speaker 2 (34:03):
Not that much? About fifty by fifty feet. It's really
just a matter of making sure there's nothing that the
balloon will blow into right after releasing it.
Speaker 1 (34:13):
Uh huh. Seems like it'll be fun to see. Yeah,
I like a balloon. Kai Marshland is the co founder
and chief product officer of Windborne Systems. Today's show was
produced by Gabriel Hunter Chang and edited by Lydia Jean Kott,
who was engineered by Sarah Buguer. You can email us
(34:34):
at problem at Pushkin dot FM. I'm Jacob Goldstein and
we'll be back next week with another episode of What's
Your Problem,
Pushkin. Every day around the world, more than a thousand
weather balloons are launched into the sky. The balloons float
high up into the atmosphere, sending back information you know, temperature,
wind speed, air pressure, et cetera, and then a couple
hours later, the balloons pop. This is basically the way
(00:39):
weather balloons have worked for decades, and the information the
balloons send back is really useful for weather forecasts. But
the information the balloon send back is also pretty limited
because the balloons only stay in the sky for a
couple hours, they don't fly very far. If we could
figure out how to make balloons stay up for longer,
they could blow in the wind and travel thousands of miles.
(01:01):
They could travel across continents and across oceans and send
us back a lot more data and give us a
much clearer picture of what weather is coming our way.
I'm Jacob Goldstein and this is What's Your Problem, the
show where I talk to people who are trying to
make technological progress. My guest today is Kai Marshland. He's
(01:25):
the co founder and chief product officer of Windborne Systems.
Kai's problem is this, can you build weather balloons that
stay in the air for weeks or months instead of hours,
And can you pair the data from those balloons with
AI to make weather forecasts that are way better than
anything we have today. Kai got interested in balloons back
(01:45):
in twenty fifteen. He was a freshman at Stanford and
he joined the Student Space Initiative, which sounds kind of
fancy but in fact was basically a bunch of college
kids trying to build their own weather balloons.
Speaker 2 (02:02):
The first half dozen flights of our balloons were complete
and total failures.
Speaker 1 (02:08):
When do things start working?
Speaker 2 (02:10):
That would be back in June of twenty sixteen. This
is the end of my freshman year, and I think
our longest flight that year had been fourteen minutes, so
shorter than a normal weather balloon.
Speaker 1 (02:27):
Buy a lot, Buy a lot.
Speaker 2 (02:29):
And also the person who had started this project, who
then became my co founder, had just graduated and was
about to leave what we thought never to be seen again.
And school has ended. We can't even get into the
building because our key cards have stopped working, so we
(02:52):
have to tailgate someone in to get our balloon launch
equipment out. Go out to the middle of nowhere in
the central Valley of California, and if this launch didn't succeed,
windborne would not exist.
Speaker 1 (03:07):
Okay, so I can guess what happened next based on
that fact. But tell me what happened.
Speaker 2 (03:13):
Yeah. So it got to be about four am, and
we're out in the middle of this park, really cold,
and the sprinklers turn on. They start slowly swiveling around
towards our delicate electronics, and so I have to hurl
(03:33):
myself onto the sprinklers, getting soaked, just to save our electronics.
Speaker 1 (03:37):
It's like the nerd version of throwing yourself on a
grenade exactly.
Speaker 2 (03:40):
I really felt like I was in an action movie sequence.
Ah good, But that sacrifice really paid off because with
that flight, we managed to set the world record for
weather balloon endurance.
Speaker 1 (03:56):
How long did it stay up?
Speaker 2 (03:57):
It stayed up for seventy six hours?
Speaker 1 (04:00):
Wow, and your previous best.
Speaker 2 (04:02):
Was fourteen minutes exactly.
Speaker 1 (04:04):
So you're in college, how do you build weather balloons
that are better than whatever the federal government? Noah's launching
our you know, state of the art weather balloon.
Speaker 2 (04:12):
People. So the first big thing is that some new
consumer electronics have come out, in particular, things like micro
controllers and lightweight, low power satellite communications, and we realize
that we can use these innovations to make a balloon
(04:35):
smarter and to control its altitude.
Speaker 1 (04:38):
What's a micro controller.
Speaker 2 (04:39):
Micro controller is a super small computer that you can
put in any device to give it a brain.
Speaker 1 (04:49):
And they're cheap.
Speaker 2 (04:50):
They're dirt cheap. Anytime you hear the word Internet of things,
that means micro controlers.
Speaker 1 (04:56):
And nobody else was doing this at the time, Like
all the big, you know, well funded weather agencies weren't
sticking my micro controllers on their on their weather balloons.
Speaker 2 (05:06):
Well, with these big agencies, they are really incentivized to
keep things stable because weather is this really important thing
that billions of people depend on, and so they're not
going to go and say, hey, what crazy experiments can
we run.
Speaker 1 (05:24):
Their incentive is just like, don't screw it up exactly
the way we did it yesterday. Don't screw it up
and you won't get fired exactly. And so specifically, what
was it that you were doing that no one had
done before.
Speaker 2 (05:37):
Yeah, So it's a very simple concept that is really
hard to make work and practice. The way we control
our altitude is when it gets too high up, we
vent some of our gas so it has less lift.
When we fall down too far, we drop some ballast
so it stops falling. But the hard part about this
(06:00):
is it has to function at negative seventy degrees celsius.
That's the temperature of dry ice. You have to have
a lot of on board software. That's where the micro
controllers come in to do things like understand is this
just turbulence that you're hitting or is it actually a
real change in lift that we need to drop ballast
(06:21):
or vent gas to account for. And in fact, we
stayed up twenty four to seven. Every single time it
talked to us. Every five minutes, we had it play
an airhorn sound because we were, of course falling asleep
in the middle of them to see what it was doing.
Speaker 1 (06:39):
So, okay, so you set the record, you stay up
for what three days watching it? How far did it go?
Speaker 2 (06:46):
It flew all the way across the country and landed
out in the Atlantic Ocean. But the real reason why
we decided to form a company around this was because
we realized the impact this could have. We got into
this from the engineering side. The lands are fun, but
(07:07):
we realized, wait a secd eighty five percent of the
Earth's atmosphere is invisible to humanity. Weather is this crazy,
unpredictable thing, and we can solve that. And weather is
so much more than just do you bring an umbrella
to work tomorrow is the single most immediately destructive aspect
(07:29):
of climate change, and improving the weather forecast it of
course helps with adapting to climate change, things like predicting
where a hurricane will make landfall, but it can also
help with preventing climate change in the first place. If
you have a better weather forecast, you can better route
ships and planes to save a huge amount of fuel.
(07:53):
You can accelerate the transition to renewables because you know
when the wind will be blowing or the sun will
be shining. And we looked at this and said, no
one else has our balloon technology. If we don't do this,
no one will. And if we want away from this opportunity,
we can't live with ourselves.
Speaker 1 (08:13):
I mean, I buy that the stakes are high. I
buy that it could be very helpful, but like, why
wouldn't anybody else do it?
Speaker 2 (08:22):
Yeah, a lot of people are trying to improve the
weather forecast. But what's unique about Windborne is the combination
of our balloon technology with our AI weather forecasts, because
really those are the two levers to pull to increase
the accuracy of a weather forecast.
Speaker 1 (08:44):
You mentioned that eighty five percent of the world lacks
good weather data, which was surprising to me the first
time I heard it. But I would think, like, get
satellites do it. That's kind of I guess my naive
ish thought. It's like, I know there's a lot of
satellites looking down at the Earth all the time.
Speaker 2 (09:02):
I'm actually a big fan of the space industry. I
used to work at SpaceX. But the problem is the
laws of physics fundamental limit what satellites can measure. Take
for example, pressure. It turns out pressure is extremely important
for predicting the weather because it determines where the winds
are blowing, how the weather systems are moving. But a
(09:24):
satellite fundamentally cannot measure pressure from space because it's not
in the atmosphere. It can't see what's going on.
Speaker 1 (09:32):
So you start the company you're good at making weather
balloons that go up and stay up for a long time,
and that you can steer. I also read that you
launched thinking that you could collect data for a tenth
the cost of existing alternatives, which sounds compelling, but as
I understand was not compelling enough. Is that right?
Speaker 2 (09:54):
It is. We're now at one hundred and fifty times
more data per dollar than alternatives.
Speaker 1 (09:59):
Okay, was there some reason one tenth the cost was
not cheap enough.
Speaker 2 (10:04):
Yeah. When we started the company, we thought it would
be cheap enough. But it turns out when you really
look at the scale of weather data collection, you need
to really understand the atmosphere. You want ten thousand balloons
aloft concurrently, that's a balloon every sixty miles in the atmosphere.
(10:27):
And in order to get to that level of scale,
it's the difference between your company spending one hundred million
dollars a year and spending a billion dollars a year.
One was a lot more in reach.
Speaker 1 (10:41):
How do you drive down the cost to one one
hundred and fiftieth the cost? I mean, I'm sure it's
many many, many incremental you know, efficiency gains. But like,
what's an example of one.
Speaker 2 (10:51):
Yeah, Well, one of the big pieces is improving the
software that flies on it so that the balloon can
fly for longer. I talked about in the student group
that first flight lasting seventy six hours. Now our longest
flight can fly for over four days.
Speaker 1 (11:10):
Wow.
Speaker 2 (11:11):
And the longer you fly, well, the hardware costs stays
the same, so that means you're collecting a lot more data.
Speaker 1 (11:18):
Yeah. Yeah. So basically, make the balloon stamp for longer
is the fundamental way that you make it cheaper exactly,
And how do you make it fly longer?
Speaker 2 (11:27):
Yeah, Well, one of the big things is improving the
software to better decide when do you vent gas, when
do you drop ballast or really one of the other
big things is just making everything smaller and lighter, because
the smaller it is, the lighter it is, the less
chance of a leak, the less ballast you have to use.
(11:50):
And things have just shrunk down so far. It really
surprises me sometimes when I'm like, wait, that tiny thing
the size of a dime replaces the thing that was
the size of a dinner plate before.
Speaker 1 (12:06):
Yeah, that's amazing. So okay, so let's talk about where
you are today. Let's talk about sort of how it works.
How big are the balloons?
Speaker 2 (12:15):
So the balloon is two pieces. There's the envelope that's
the bag that holds all parts the balloon part of
the balloon, and then there's the main unit, which is
the electronics and the ballast.
Speaker 1 (12:33):
The stuff exactly, the balloon and the stuff the balloon part.
Speaker 2 (12:36):
Of the balloon. The balloon part of the balloon is
five and a half meters tall. So that's two and
a half three times the height of person, depending on
how tall you are.
Speaker 1 (12:47):
Yeah, so tall. Yeah, it's a big balloon. And how
how big is the stuff? How big is are the
sensors in the part that's not the.
Speaker 2 (12:56):
Yeah, that stuff is. I guess this is an audio thing,
so I would say about this big.
Speaker 1 (13:06):
The size of a basketball.
Speaker 2 (13:07):
Yeah, it's a roughly the size of a basketball. It
weighs just over four pounds, so about the weight of
a large duck. Okay, and is kind of long and skinny.
It kind of looks like a fish. I think of
it as a trout attached to a giant bag.
Speaker 1 (13:30):
How many of your balloons are in the sky right now? About?
Speaker 2 (13:34):
Yeah, there are a few dozen aloft right now.
Speaker 1 (13:37):
Okay.
Speaker 2 (13:37):
We launch around one hundred a month and are quickly
ramping that up.
Speaker 1 (13:41):
So where do you launch your balloons from?
Speaker 2 (13:43):
We launch them every day from three continents, South Korea,
paloelto New York and Cabo Verde.
Speaker 1 (13:50):
Cabo Verde is just off off the west coast of Africa.
Is that right?
Speaker 2 (13:53):
You got it. One of the reasons why we have
launch site in Cabo Verde right now. That's right where
a lot of hurricanes are forming, and so the fact
that we're collecting data around there is going to be
really impactful for better predicting the path of these hurricanes. Huh.
Speaker 1 (14:10):
So they start there and then they essentially travel across
the Atlantic and into the Americas, and if you can
understand what's going on there, ideally you can sort of
understand the hurricane where it's going to go in the
dream scenario, even just as it's becoming a tropical storm.
Speaker 2 (14:26):
Exactly. Yeah, Noah did an analysis of the Impactor data
had on the twenty twenty two hurricane season, and it
made the forecasts for Hurricane Fiona about twenty percent better.
Speaker 1 (14:43):
Now it's time for a few ads. After the ads,
Kai and I will talk about AI. Of course, we'll
also talk about Winborne's business, what they're selling, and we'll
talk about the company's quest to build balloons that can
stay in the air for months at a time and
make multiple trips around the world. What is your business
(15:16):
right now, like, what are you selling and who you're
selling it.
Speaker 2 (15:18):
To right now. Our business has two pieces to it.
We are selling the observations of the atmosphere we collect
to the government right now, so that those governments can
use this data to improve your weather forecast. And just
a couple of weeks ago, we announced our AI based
(15:40):
weather model, which is the world's most accurate global weather
model bar none.
Speaker 1 (15:45):
I feel like you need a little TM when you
say the world's most accurate global weather model bar none.
Speaker 2 (15:50):
We really do, we really do.
Speaker 1 (15:52):
So let's talk about that. Is that claim validated? I mean,
I know there was news about that just this year,
and congratulations, but also, how do I know that's true? Respectfully?
Speaker 2 (16:01):
Yeah, I love that question because anytime a weather company
makes a claim, you should look at it closely. So,
first off, we've published our results on our website and
so you can dig into some of the raw numbers there. Second,
we're in the process of submitting to weather bench which
(16:23):
is these benchmarks run by Google, which were the previous
holders of this record. So we're actively talking with them
right now about submitting our results getting them validated into
live up there. It's just a process that takes a
little while, so.
Speaker 1 (16:43):
Let's talk about the model you built. So I mean
generally when I talk to people who are working on AI,
they talk a lot about data, right, And it seems
like to some significant degree the models are kind of commoditized,
not quite, but like models are pretty similar, it seems
in many settings at least one to the other, and
the differentiator often ends up being the data. Is that
(17:06):
the case in this instance? I mean, do you think
you're the best. If you're the best because you have
all this data from all your balloons.
Speaker 2 (17:14):
I think that you're spot on. Data is the real
mote here, because what really sets us apart is the
ability to have all of this data that no one
else has and to use that both for training the
model but then also for running the model in real time.
Data isn't just about training. It's about essentially giving your
(17:35):
model the prompt of what's going to happen next, and
you need new data every single day for that.
Speaker 1 (17:44):
Just one thing to clarify. So, if you're selling the
data to governments, are they not sharing it widely? Like
they're paying for the data but they're not. But not
everybody can get at the data? Is that why it's
a mode for you?
Speaker 2 (17:59):
Yeah, so what they're using the data we sell them
for is putting it into conventional physics based weather model
that they then release. So they can't redistribute the data itself,
but the general public can benefit from its use in
(18:20):
these weather models.
Speaker 1 (18:21):
And so just to distinguish and this is a distinction
that's not particular to your company, but you mentioned the
sort of traditional physics based weather models. I mean, I
think it's worth spending just a moment here to distinguish, right,
like between the classic weather model, you know, the sort
of pre AI weather model, and the AI weather model. Like,
(18:43):
what's the basic difference between those two?
Speaker 2 (18:45):
Yeah, So a conventional physics based weather model, it takes
the initial state of the atmosphere and then runs a
bunch of fluid dynamics on it to simulate what's going
to happen to all of these different fluids.
Speaker 1 (19:01):
There's a sort of kind of classic sort of feels
like kind of nineteenth century deterministic. Give me the initial
condition and I'll tell you what's going to happen in
the future. It's that right, it's sort of rules based.
Speaker 2 (19:13):
Exactly exactly, and that is nice because you can see
the exact physics that is being used, but you need
compute clusters. They cost hundreds of millions of dollars in
order to run this because the atmosphere is so big.
(19:34):
And by contrast, a AI based weather model can run
on just a gaming laptop.
Speaker 1 (19:42):
Huh.
Speaker 2 (19:43):
And what it does, by contrast, is effectively picking out statistics.
Speaker 1 (19:49):
I mean, it's just it's machine learning. I presume it's
pattern matching exactly.
Speaker 2 (19:53):
It's our model is a transformer based architecture, the same
thing that powers chat GPT.
Speaker 1 (19:59):
Our A models in general better at this point than
the physics based traditional models.
Speaker 2 (20:04):
It depends on the use case. But if you're talking
about hurricanes, yeah, we ran a case study on Hurricane
Ian and our model would have predicted landfall by two
hundred kilometers closer.
Speaker 1 (20:21):
I mean, that's another one where like I'm intrigued by
what you said, but I'm very eager for I'm not
eager for this hurricane season to come, but like it
will resonate more with me when you do that prospectively, right,
of course, I mean, will you this year be predicting
where hurricanes are going to make landfall?
Speaker 2 (20:41):
We will be predicting that for public safety reasons. We
aren't going to be you won't tell me.
Speaker 1 (20:48):
Yeah you will, but you won't tell me we.
Speaker 2 (20:49):
Will know a hurricane. Okay, but fair, you of course
don't want to say, hey, don't listen to Noah about
these evacuation orders.
Speaker 1 (21:01):
No, no, fair that that is very responsible. So basically,
you're selling data. You are likely soon to be selling forecasts.
That's sort of the business. On the technical side, what
is the frontier? What are you trying to figure out
that you haven't figured out yet?
Speaker 2 (21:19):
Yeah, well, one of the big areas for innovation is
on the AI modeling side. We were kind of surprised
that our models did as well as they did because
there are a lot of quite frankly obvious things that
we haven't done, things like just increasing the amount of
(21:40):
compute we're using to train these models. We use something
like a fifteenth as much as Google did. So what
happens when you train it for longer?
Speaker 1 (21:51):
I mean, I'll say, on the AI side, it's not
obvious that it's optimal for you to be doing the
AI as well. Right, there's a universe where you are
optimizing the balloons and the data, and then someone else
like Google, who has all the computers and all the
AI knows what to do with doing the AI side.
Speaker 2 (22:12):
Of it, right, Yes, and no, I think that where
that falls apart is coupling our data with the models
much more closely. In that there's so much to be
done in terms of figuring out how to better take
advantage of our data into particular and also things like saying,
(22:34):
based on this weather model, where should we be flying
our balloons to improve the forecast? And we're already using
our own AI weather forecasts to do that flight plan
optimization to figure out where our balloons are going to fly.
So it's really this beneficial effect where the better our
weather forecast, the better we can fly our balloons. And
(22:56):
we can then target our balloons to fly to the
places that will most improve the weather forecast.
Speaker 1 (23:03):
That's a good feedback loop.
Speaker 2 (23:04):
There's also a lot to do on the balloon side
of things. I wish I could tell you about our
project that will increase flight time by another factor.
Speaker 1 (23:16):
Of ten, another factor of ten.
Speaker 2 (23:19):
Yeah, so what what are you at now?
Speaker 1 (23:21):
What's the like median flight time?
Speaker 2 (23:23):
Medium flight time is seven to ten days depending on
how we're targeting it.
Speaker 1 (23:30):
And so you think you're going to get to ninety days. Yep,
we around the world in eighty days. Yeah, you say
you wish you could tell me like you feel like
you're about to do it. Yeah, tell me, tell me
without telling me what you can't tell me.
Speaker 2 (23:44):
Okay, I'll do my best. So we have had some
very successful flight tests where we have demonstrated the ability
to fly without using any finite resources.
Speaker 1 (24:03):
So what what is the key finite resource? The the
lift gas, the what is it helium or hydrogen?
Speaker 2 (24:08):
What you used to keep Our balloons are compatible with
both helium and hydrogen, So which we use is dependent
on the country.
Speaker 1 (24:17):
When you say flying without any finite resource, that's what
I think of, yep.
Speaker 2 (24:22):
Okay, yeah, that and ballast.
Speaker 1 (24:25):
Oh right, So so you want to you can? I should?
I guess.
Speaker 2 (24:31):
I mean, there's heat there, leave it there and just say.
Speaker 1 (24:37):
If you get that, could you fly forever?
Speaker 2 (24:40):
That the dream someday, someday we're we're definitely ninety.
Speaker 1 (24:45):
Days for a weather balloon is sort of forever, right.
Speaker 2 (24:47):
It really is. And so, yeah, we've had some very
successful flight tests.
Speaker 1 (24:53):
What's the longest flight you've had to this point?
Speaker 2 (24:55):
Forty days?
Speaker 1 (24:57):
Forty days? Okay?
Speaker 2 (24:58):
Long?
Speaker 1 (24:58):
Yeah?
Speaker 2 (24:59):
Long? And that was without using this technology, was that
like a fluke. It was definitely on the side of
the bell curve. But we've had multiple month long flights.
Speaker 1 (25:11):
What why do your balloons usually what do you say fall?
Crash sounds a little extreme crash fall.
Speaker 2 (25:19):
Yeah, it's that they run out of ballast and lifting gas,
and so these finite resources have been used up. You
don't have a more ballast to drop, you don't have
a more gas event, and so you can no longer
control your altitude.
Speaker 1 (25:37):
What happens when it falls crashes comes down.
Speaker 2 (25:41):
So by the time it falls, it has used up
all of the ballast. So instead of weighing four pounds,
it weighs about two hundred grams.
Speaker 1 (25:56):
Two hundred grams is what half a pound?
Speaker 2 (25:58):
Ish? Yes, I'd looked it up. Zero point four to
four pounds.
Speaker 1 (26:04):
Okay. By the way, when you're getting rid of ballast,
is it just like sand or something? You just like
sprinkle sand out exactly? Okay, So it's half a pound,
so it wouldn't hurt if it hit me on the head?
Is that is that part of the reason half a
pound is important? Would it if it hit me on that?
Speaker 2 (26:21):
Is it? Anybody on that it's never hit anybody. We
do landing simulations and control where it lands to direct
it towards unpopulated areas. But remember it also has this
envelope attached to it, which acts like a parachute, so
it actually falls very slowly. It's very light and not
(26:45):
an issue.
Speaker 1 (26:46):
And then what happens. Then you have this big deflated
balloon sitting on the ground or floating in the ocean,
and is it just what happens to you?
Speaker 2 (26:54):
Yeah? So I love that question because it's a chance
to talk about how our balloons can reduce the amount
of waste going out into the world compared to the
half a million that are launched every year, of which
only a fifth are covered.
Speaker 1 (27:10):
Just get answer directly. I appreciate that you want to
contextualize it, but like, first, let's talk about what happens
with your balloons and then feel free to provide the bigger.
Speaker 2 (27:18):
Cart sounds good, sounds good? Yeah, yeah, So our balloons
are out in the world, and we recover as many
of them as we can. In the long term, we're
aiming to recover essentially all of them because we'll direct
them to specific landing sites.
Speaker 1 (27:36):
I mean, the ocean has got to be tough to write.
I presume when they fall in the ocean, for the
most part, you don't recover them.
Speaker 2 (27:42):
Is that right, exactly? And that's one of the reasons
why improving endurance is so exciting, because if you circumnavigate
multiple times, well, on the last leg, you bring it
down in a field, have somebody drive around and collect
all of them. They are about half million weather balloons
launched each year, and only a fifth of those are recovered.
(28:04):
So when each balloon flies for only two hours, well,
you have to launch a lot more balloons to collect
the same amount of data. So we really see this
as an opportunity to reduce the amount of stuff that's
going out there in the first place.
Speaker 1 (28:20):
Right, So there will actually be fewer balloons going into
the world if you succeed.
Speaker 2 (28:26):
Exactly.
Speaker 1 (28:28):
So, you're at this point where you've learned a lot.
You sort of feels like you're kind of on the
precipice of a lot more. And I want to talk
about sort of two futures. Right. One is a future
where where your company doesn't succeed for any number of
reasons with which you're truly more familiar than I. And
then the other is if you do succeed. Right, So,
(28:48):
in the sort of sad version where you don't succeed,
what are some reasons it might not work out?
Speaker 2 (28:52):
Yeah, I think that probably the biggest reason is that
scaling up hardware is hard. We need to increase manufacturing
by a factor of one hundred effectively, and.
Speaker 1 (29:06):
So it's scaling up that final assembly by a factor
of one hundred is complicated and hard and just kind
of classic hard building. A business gets more capital intensive exactly,
and the money before you can get the money exactly. Okay,
So that's an easy to imagine sad outcome. Let's talk
(29:26):
about the happy outcome. Like it works. You scale up
your balloons, stay up for months at a time. What's
the world look like? What are you doing in that scenario.
Speaker 2 (29:38):
We want everybody to see twice as far into the
future when it comes to weather. So making the ten
day forecast is accurate is the current five day forecast.
Making the twenty day forecast as accurate as the ten
day forecast, so we want people to see twice as
far into the future. We want to pinpoint where hurricanes
are going to make landfall a week in advance, and
(30:02):
we want day to day weather that businesses rely on
to be really accurate, things like never having to cancel
a flight last minute because a bomb cyclone popped up,
saving fuel with all of your shipping because you know
(30:24):
where there will be headwinds. We want to accelerate the
transition to renewables, and we want weather to go from
this crazy, unpredictable source of uncertainty to something that humans
just know about.
Speaker 1 (30:42):
We'll be back in a minute with the lightning round. Okay,
let's do the lightning round. Would you rather have it
be too hot or too cold?
Speaker 2 (31:03):
Too cold any day?
Speaker 1 (31:06):
Okay? The next one is multiple choice. What is your
favorite movie prominently featuring balloons? Wizard of Oz around the
World in eighty days, up the Red Balloon, or none
of the above.
Speaker 2 (31:20):
It's got to be up brilliant.
Speaker 1 (31:21):
Movie, Blimps, overrated or underrated?
Speaker 2 (31:27):
Ooh, so here, I've got to make a distinction between
blimps and Zeppelins because I actually used to work at
a zeppelin company.
Speaker 1 (31:37):
Is that the Larry Page Zeppelin company? It sure is
perhaps the only zeppelin company. Yeah, and so is the
distinction that a zeppelin has a rigid frame?
Speaker 2 (31:49):
Got it in? Won?
Speaker 1 (31:51):
Okay? So how about this. Let me reformulate it to
see if I get it this time. Airships overrated or underrated?
Speaker 2 (31:59):
Underrated? I thought that zeppelins are so cool. I don't
have a great mission driven answer here other than you know,
I think it's amazing. I read too many books growing
up which prominently featured airships.
Speaker 1 (32:18):
Isn't the isn't the Larry Page airship company dreams some
kind of cargo, like the idea that, for like really
heavy things, giant airships would be an efficient way to
move cargo.
Speaker 2 (32:29):
Full disclosure, It's been a long time since I worked there,
so I can't speak to that company in particular. But yeah,
faster deliveries than a ship, more efficient deliveries than a plane.
Speaker 1 (32:43):
Aha, It's like a niche an Until what's something besides
the weather that AI will be really good at predicting?
Speaker 2 (32:53):
Oh? Great question, let's see. Uh. I don't have a
good answer off the top of my head. I think
that it will be really interesting for economics in terms
of taking short term data, various real time indicators, and
(33:18):
making predictions about what the final readings are going to be.
Speaker 1 (33:24):
I'm sure a lot of very smart people are working
on that and they may in fact already have good
models and they're not telling us.
Speaker 2 (33:31):
I think that's likely.
Speaker 1 (33:32):
Is there anything else you want to say?
Speaker 2 (33:35):
I think that covers it. Yeah, great to be on
the show.
Speaker 1 (33:39):
Thanks for your time. It was lovely to talk with you.
Good luck.
Speaker 2 (33:41):
Thanks and if you ever are in Paloelto, you're welcome
to come see a balloon launch.
Speaker 1 (33:48):
Great. So do you still you launch from where you launch?
From that Air Force base or like or just from.
Speaker 2 (33:56):
From our part part?
Speaker 1 (33:57):
Are they easy? Yeah? From the parking lot, that's cool.
Speaker 2 (33:59):
Yeah.
Speaker 1 (34:00):
How much space do you need to launch a weather balloon?
Speaker 2 (34:03):
Not that much? About fifty by fifty feet. It's really
just a matter of making sure there's nothing that the
balloon will blow into right after releasing it.
Speaker 1 (34:13):
Uh huh. Seems like it'll be fun to see. Yeah,
I like a balloon. Kai Marshland is the co founder
and chief product officer of Windborne Systems. Today's show was
produced by Gabriel Hunter Chang and edited by Lydia Jean Kott,
who was engineered by Sarah Buguer. You can email us
(34:34):
at problem at Pushkin dot FM. I'm Jacob Goldstein and
we'll be back next week with another episode of What's
Your Problem,
Popular Podcasts
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations.
The Nikki Glaser Podcast
Every week comedian and infamous roaster Nikki Glaser provides a fun, fast-paced, and brutally honest look into current pop-culture and her own personal life.
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.