https://physicsbaseddeeplearning.org/intro.html
[ ]
Toggle navigation sidebar
[ ]
Toggle in-page Table of Contents
logo
Physics-based Deep Learning
[ ]
* Welcome ...
Introduction
* A Teaser Example
* Overview [ ]
+ Models and Equations
+ Simple Forward Simulation of Burgers Equation with phiflow
+ Navier-Stokes Forward Simulation
+ Optimization and Convergence
* Supervised Training [ ]
+ Supervised training for RANS flows around airfoils
+ Discussion of Supervised Approaches
Physical Losses
* Physical Loss Terms
* Burgers Optimization with a Physics-Informed NN
* Discussion of Physical Losses
Differentiable Physics
* Introduction to Differentiable Physics
* Burgers Optimization with a Differentiable Physics Gradient
* So Far so Good - a First Discussion
* Differentiable Fluid Simulations
Differentiable Physics with NNs
* Integrating DP into NN Training
* Reducing Numerical Errors with Deep Learning
* Solving Inverse Problems with NNs
* Discussion
Reinforcement Learning
* Introduction to Reinforcement Learning
* Controlling Burgers' Equation with Reinforcement Learning
Improved Gradients
* Scale-Invariance and Inversion
* Simple Example comparing Different Optimizers
* Scale Invariant Physics Training
* Learning to Invert Heat Conduction with Scale-invariant Updates
* Half-Inverse Gradients
* Coupled Oscillators with Half-Inverse Gradients
* Discussion of Improved Gradients
PBDL and Uncertainty
* Introduction to Posterior Inference
* RANS Airfoil Flows with Bayesian Neural Nets
Fast Forward Topics
* Additional Topics
* Model Reduction and Time Series
* Generative Adversarial Networks
* Unstructured Meshes and Meshless Methods
End Matter
* Outlook
* References
* Notation and Abbreviations
Powered by Jupyter Book
* repository
* open issue
* .md
* .pdf
Contents
* Coming up
* Comments and suggestions
* Thanks!
* Citation
Welcome ...
Contents
* Coming up
* Comments and suggestions
* Thanks!
* Citation
Welcome ...#
_images/logo-xl.jpg
Welcome to the Physics-based Deep Learning Book (v0.2)
TL;DR: This document contains a practical and comprehensive
introduction of everything related to deep learning in the context of
physical simulations. As much as possible, all topics come with
hands-on code examples in the form of Jupyter notebooks to quickly
get started. Beyond standard supervised learning from data, we'll
look at physical loss constraints, more tightly coupled learning
algorithms with differentiable simulations, training algorithms
tailored to physics problems, as well as reinforcement learning and
uncertainty modeling. We live in exciting times: these methods have a
huge potential to fundamentally change what computer simulations can
achieve.
Note
What's new in v0.2? For readers familiar with v0.1 of this text, the
extended section Integrating DP into NN Training and the brand new
chapter on improved learning methods for physics problems (starting
with Scale-Invariance and Inversion) are highly recommended starting
points.
---------------------------------------------------------------------
Coming up#
As a sneak preview, the next chapters will show:
* How to train networks to infer a fluid flow around shapes like
airfoils, and estimate the uncertainty of the prediction. This
gives a surrogate model that replaces a traditional numerical
simulation.
* How to use model equations as residuals to train networks that
represent solutions, and how to improve upon these residual
constraints by using differentiable simulations.
* How to more tightly interact with a full simulator for inverse
problems. E.g., we'll demonstrate how to circumvent the
convergence problems of standard reinforcement learning
techniques by leveraging simulators in the training loop.
* We'll also discuss the importance of inversion for the update
steps, and how higher-order information can be used to speed up
convergence, and obtain more accurate neural networks.
Throughout this text, we will introduce different approaches for
introducing physical models into deep learning, i.e., physics-based
deep learning (PBDL) approaches. These algorithmic variants will be
introduced in order of increasing tightness of the integration, and
the pros and cons of the different approaches will be discussed. It's
important to know in which scenarios each of the different techniques
is particularly useful.
Executable code, right here, right now
We focus on Jupyter notebooks, a key advantage of which is that all
code examples can be executed on the spot, from your browser. You can
modify things and immediately see what happens - give it a try by
[running this teaser example in your browser].
Plus, Jupyter notebooks are great because they're a form of literate
programming.
Comments and suggestions#
This book, where "book" stands for a collection of digital texts and
code examples, is maintained by the Physics-based Simulation Group at
TUM. Feel free to contact us if you have any comments, e.g., via old
fashioned email. If you find mistakes, please also let us know! We're
aware that this document is far from perfect, and we're eager to
improve it. Thanks in advance ! Btw., we also maintain a link
collection with recent research papers.
_images/divider-mult.jpg
Fig. 1 Some visual examples of numerically simulated time sequences.
In this book, we explain how to realize algorithms that use neural
networks alongside numerical solvers.#
Thanks!#
This project would not have been possible without the help of many
people who contributed. Thanks to everyone Here's an alphabetical
list:
* Philipp Holl
* Maximilian Mueller
* Patrick Schnell
* Felix Trost
* Nils Thuerey
* Kiwon Um
Additional thanks go to Georg Kohl for the nice divider images (cf. [
KUT20]), Li-Wei Chen for the airfoil data image, and to Chloe
Paillard for proofreading parts of the document.
Citation#
If you find this book useful, please cite it via:
@book{thuerey2021pbdl,
title={Physics-based Deep Learning},
author={Nils Thuerey and Philipp Holl and Maximilian Mueller and Patrick Schnell and Felix Trost and Kiwon Um},
url={https://physicsbaseddeeplearning.org},
year={2021},
publisher={WWW}
}
next
A Teaser Example
By N. Thuerey, P. Holl, M. Mueller, P. Schnell, F. Trost, K. Um
(c) Copyright 2021,2022.