Name: Powered by TensorFlow: utilizing deep learning to better predict extreme weather
Uploaded: 2020-03-25T08:34:13.000Z
Duration: 2 min 43 s
Description: Thousands of YouTube videos with English-Chinese subtitles! Now you can learn to understand native speakers, expand your vocabulary, and improve your pronunciation...

KARTHIK KASHINATH: Extreme weather is changing.

There's more extreme rainfall, heavy flooding, forest fires.

There's the radio signature, [INAUDIBLE]..

Being able to predict these extreme events more accurately

is kind of the big challenge that we're facing right now.

There's 100 terabytes of climate data every day

from satellites, from observations, from models.

can sift through all of that data rapidly and accurately.

And deep learning is almost perfectly poised for problems

THORSTEN KURTH: A lot of NERSC users are using TensorFlow.

over the different models, different layer parameters.

for example, our satellite imagery segmentation tasks.

And then we use TensorFlow to enhance the models

until we found a set of models to perform well

But for the volume of the data, complexity of the data,

So if you want to do this on your workstation,

MIKE HOUSTON: To really tackle these problems requires

So systems like the Summit supercomputer,

It's a million times faster than your common laptop.

Just imagine what you do at your workstation,

but now imagine having 27,000 times that power.

THORSTEN KURTH: We were surprised how good it actually

anybody's ever run an AI application at this scale.

Instead of having the climate scientists figure out

could express things in a very natural way in Python,

in TensorFlow, and get all the high performance code

that most HPC people are used to within TensorFlow.

KARTHIK KASHINATH: We're now entering the space where

AI can actually contribute to the predictions

MIKE HOUSTON: When you combine traditional HPC with AI,

you can tackle things we never thought that we could tackle.

Fusion reactor research, understanding diseases

THORSTEN KURTH: We've shown that with the hyperactivity

framework such as TensorFlow, you can get to massive scale,

KARTHIK KASHINATH: Genetics, neuroscience, cosmology,

high energy physics, that is immensely exciting for me.

Subtitles ListPlay Video

Powered by TensorFlow: utilizing deep learning to better predict extreme weather

specific

incredible

massive

awesome