Login
2021 Events

FI Computational Methods and Data Science Journal Club

→ America/New_York
IDA, 2nd Floor (Flatiron Institute)

IDA, 2nd Floor

Flatiron Institute
Description

 

 

FI Computational Methods and Data Science Journal Club

Bi-Weekly Speaker with Reception to follow

Flatiron Institute, 162 5th Avenue

  • Thursday, July 22nd -  2nd floor, IDA
  • Thursday, August 5th  -  5th floor, Classroom
  • Thursday, August 19th -  2nd floor, IDA

Speaker:  Kimberly Stachenfeld (Deepmind)
Title: Learned Simulators for Astrophysical Turbulence
Abstract: Recent machine learning advances in simulation invite the question: to what extent can learned simulators supplement or replace traditional simulators for scientific applications? In this talk, we address this question for astrophysical turbulence using four chaotic and turbulent domains: three from astrophysics involving decaying turbulence and radiative cooling mixing layers, as well as the classic Kuramoto-Sivashinsky equation. Simulating these complex, chaotic systems with traditional numerical solvers is computationally costly because fine grids are needed to accurately resolve dynamics. We implement a variety of convolutional neural network-based simulators, including a novel Dilated ResNet model, and find that learned models can outperform traditional solvers with comparable resolution across various scientifically relevant metrics, most notably preserving high-frequency information. We find that tuning training noise and temporal downsampling can improve rollout stability, and see that while generalization beyond the training distribution is a challenge for learned models,  training noise, convolutional architecture, and added loss constraints can help. To our knowledge, models are the first learned simulators evaluated for astrophysical applications and the first to be trained on data from the \texttt{Athena++} engine. Broadly, we conclude that learned simulators are beginning to be competitive with traditional solvers run on coarser grids, and emphasize that careful design choices can offer robust generalization.