27 min

Advanced Weather Predictions Radio Cade

    • Technology

The weather; everyone talks about it, so the old joke goes, no one does anything about it. Dr. Leela Watson, founder and CEO of InitWeather, says that by using advanced algorithms and machine learning, we can make faster and more reliable predictions about the weather that can help a wide range of industries, including agriculture, energy, and aerospace.  "When I started this,"  said Dr. Watson, "it was, oh , let's just do this. And then when you dive into it, you realize why not so many people have been using machine learning within weather, because it is such a big problem. And just sorting through all the different ways that it can be done is a challenge."  
 
TRANSCRIPT:
Intro: 0:01
Inventors and their inventions. Welcome to Radio Cade, a podcast from the Cade Museum for Creativity and Invention in Gainesville, Florida. The museum is named after James Robert Cade, who invented Gatorade in 1965. My name is Richard Miles. We'll introduce you to inventors and the things that motivate them. We'll learn about their personal stories, how their inventions work, and how their ideas get from the laboratory to the marketplace,
Richard Miles: 0:40
The weather: everyone talks about it, but so the old joke goes, no one does anything about it. However, using advanced algorithms and machine learning, we can make faster and better predictions about the weather that can help a wide range of industries. Welcome to Radio Cade . I'm your host, Richard Miles. Today I'm very pleased to welcome Dr. Leela Watson, a former NASA meteorologist, and the co-founder and CEO of InitWeather. Welcome to Radio Cade, Leela.
Dr. Leela Watson: 1:05
Thank you. Thanks for having me.
Richard Miles: 1:06
So Leela, I'm guessing that as a meteorologist, you have probably heard lots of jokes about the weather. Are there any good ones out there, because it's not exactly comedy gold, right?
Dr. Leela Watson: 1:15
No, it's definitely not. I mean, I've heard them all, so I'm waiting for that really great one. That real zinger, that--
Richard Miles: 1:20
That actually makes you laugh, right? Yeah. There are a lot of lame weather jokes, but none that I've heard that are really good. So that's a tragedy for your profession, but anyway, why don't we start out by explaining for the listener exactly what it is that InitWeather does. And as I understand it, you crunch a lot of existing data to come up with faster and more reliable forecast. Something that is very particularly useful for things like the agricultural industry. And of course, utility companies, as we saw in Texas a few weeks ago, actually. So, how does it weather differ from other weather forecasts?
Dr. Leela Watson: 1:51
So, at a really basic level, what we do is we use machine learning to create better weather forecasts. So, the way that we're different is that weather forecasts are generally made from computer weather models that are out there and forecasters take that information and make their weather forecast . So what we do in our product takes that weather data that's available. We run it through our machine learning algorithm, and then we do create better weather forecasts than what are currently out there now.
Richard Miles: 2:20
But you're taking obviously, from more than one data set, when you see a weather forecast on the TV or in the newspaper, are they all drawing from the same pool of data or do they all have different data sources that go into that forecast?

The weather; everyone talks about it, so the old joke goes, no one does anything about it. Dr. Leela Watson, founder and CEO of InitWeather, says that by using advanced algorithms and machine learning, we can make faster and more reliable predictions about the weather that can help a wide range of industries, including agriculture, energy, and aerospace.  "When I started this,"  said Dr. Watson, "it was, oh , let's just do this. And then when you dive into it, you realize why not so many people have been using machine learning within weather, because it is such a big problem. And just sorting through all the different ways that it can be done is a challenge."  
 
TRANSCRIPT:
Intro: 0:01
Inventors and their inventions. Welcome to Radio Cade, a podcast from the Cade Museum for Creativity and Invention in Gainesville, Florida. The museum is named after James Robert Cade, who invented Gatorade in 1965. My name is Richard Miles. We'll introduce you to inventors and the things that motivate them. We'll learn about their personal stories, how their inventions work, and how their ideas get from the laboratory to the marketplace,
Richard Miles: 0:40
The weather: everyone talks about it, but so the old joke goes, no one does anything about it. However, using advanced algorithms and machine learning, we can make faster and better predictions about the weather that can help a wide range of industries. Welcome to Radio Cade . I'm your host, Richard Miles. Today I'm very pleased to welcome Dr. Leela Watson, a former NASA meteorologist, and the co-founder and CEO of InitWeather. Welcome to Radio Cade, Leela.
Dr. Leela Watson: 1:05
Thank you. Thanks for having me.
Richard Miles: 1:06
So Leela, I'm guessing that as a meteorologist, you have probably heard lots of jokes about the weather. Are there any good ones out there, because it's not exactly comedy gold, right?
Dr. Leela Watson: 1:15
No, it's definitely not. I mean, I've heard them all, so I'm waiting for that really great one. That real zinger, that--
Richard Miles: 1:20
That actually makes you laugh, right? Yeah. There are a lot of lame weather jokes, but none that I've heard that are really good. So that's a tragedy for your profession, but anyway, why don't we start out by explaining for the listener exactly what it is that InitWeather does. And as I understand it, you crunch a lot of existing data to come up with faster and more reliable forecast. Something that is very particularly useful for things like the agricultural industry. And of course, utility companies, as we saw in Texas a few weeks ago, actually. So, how does it weather differ from other weather forecasts?
Dr. Leela Watson: 1:51
So, at a really basic level, what we do is we use machine learning to create better weather forecasts. So, the way that we're different is that weather forecasts are generally made from computer weather models that are out there and forecasters take that information and make their weather forecast . So what we do in our product takes that weather data that's available. We run it through our machine learning algorithm, and then we do create better weather forecasts than what are currently out there now.
Richard Miles: 2:20
But you're taking obviously, from more than one data set, when you see a weather forecast on the TV or in the newspaper, are they all drawing from the same pool of data or do they all have different data sources that go into that forecast?

27 min

Top Podcasts In Technology

Lex Fridman
Jason Calacanis
The New York Times
Ben Gilbert and David Rosenthal
NPR
Jack Rhysider