A Deep Learning Parameterization of Gravity Wave Drag Coupled to an Atmospheric Global Climate Model - Aditi Sheshadri

A Deep Learning Parameterization of Gravity Wave Drag Coupled to an Atmospheric Global Climate Model - Aditi Sheshadri

Kavli Institute for Theoretical Physics via YouTube Direct link

Intro

1 of 17

1 of 17

Intro

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

A Deep Learning Parameterization of Gravity Wave Drag Coupled to an Atmospheric Global Climate Model - Aditi Sheshadri

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Gravity waves are ubiquitous..
  3. 3 Big source of uncertainty in climate prediction
  4. 4 Data Wave
  5. 5 Proof of concept.. Idealized model test
  6. 6 Model architecture - WaveNet
  7. 7 WaveNet does pretty well!
  8. 8 Predicting the QBO
  9. 9 Learning' one year is sufficient
  10. 10 Stable for 100 y times when run online
  11. 11 Increased CO2-WaveNet generalizes
  12. 12 QBO period, amplitude decrease
  13. 13 Future directions
  14. 14 Project Loon
  15. 15 Loon provides unprecedented coverage
  16. 16 Localize and analyze packets of gravity waves in time
  17. 17 Horizontal winds dominant predictors

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.