DeepVel & DeepVelU Neural Networks for Flow Inversions

Using supervised learning to infer the instantaneous depth-dependent transverse velocity vector of the plasma motions from observations of the Sun.

Contents

1. Introduction
2. Publications & Communications
3. Walkthrough

---

Introduction

• Work in progress.

Publications & Communications

• Paper(s) published in peer-reviewed journals:

  • Benoit Tremblay & Raphaël Attié, 2020. "Inferring Plasma Flows at Granular and Supergranular Scales with a New Architecture for the DeepVel Neural Network". Frontiers in Astronomy and Space Sciences, Volume 7, id.25. DOI.
  • Benoit Tremblay, Thierry Roudier, Michel Rieutord & Alain Vincent, 2018. "Reconstruction of Horizontal Plasma Motions at the Photosphere from Intensitygrams: A Comparison Between DeepVel, LCT, FLCT, and CST". Solar Physics, Volume 293, 57. DOI.

• Blog(s):

  • Nicole Castro, Raphaël Attié, Michael Kirk & Benoit Tremblay, 2020. "Rise and Sunshine: NASA Uses Deep Learning to Map Flows on Sun’s Surface, Predict Solar Flares". NVIDIA Blog.

• Poster(s) & Talk(s):

  • (e-poster) Benoit Tremblay, Maria Kazachenko & Raphaël Attié, 2020. "Inferring Depth-dependent Plasma Motions from Surface Observations using Deep Learning". AAS Solar Physics Division meeting #51.

Walkthrough

• Work in progress.