initial checkin

_config.yml

@@ -0,0 +1,28 @@
+# Book settings
+# Learn more at https://jupyterbook.org/customize/config.html
+
+title: Physics-based Deep Learning
+author: TUM-I15
+logo: resources/logo.png
+
+# Force re-execution of notebooks on each build.
+# See https://jupyterbook.org/content/execute.html
+execute:
+  execute_notebooks: force
+
+# Define the name of the latex output file for PDF builds
+latex:
+  latex_documents:
+    targetname: book.tex
+
+# Information about where the book exists on the web
+repository:
+  url: https://github.com/executablebooks/jupyter-book-TODO  # Online location of your book
+  path_to_book: docs  # Optional path to your book, relative to the repository root
+  branch: master  # Which branch of the repository should be used when creating links (optional)
+
+# Add GitHub buttons to your book
+# See https://jupyterbook.org/customize/config.html#add-a-link-to-your-repository
+html:
+  use_issues_button: true
+  use_repository_button: true

_toc.yml

@@ -0,0 +1,15 @@
+# Table of content
+# Learn more at https://jupyterbook.org/customize/toc.html
+#
+- file: intro
+- file: overview
+- file: supervised
+- file: physicalloss
+  sections:
+    - file: physicalloss-code
+- file: diffphys
+- file: jupyter-book-reference
+  sections:
+    - file: markdown
+    - file: notebooks
+- file: references

diffphys.md

@@ -0,0 +1,6 @@
+Differentiable Simulations
+=======================
+
+... are much more powerful ...
+
+

intro.md

@@ -0,0 +1,92 @@
+Welcome ... 
+============================
+
+Welcome to the Physics-based Deep Learning Book 👋
+
+**TL;DR**: This document targets 
+a veriety of combinations of physical simulations with deep learning.
+As much as possible, the algorithms will come with hands-on code examples to quickly get started.
+Beyond standard _supervised_ learning from data, we'll look at loss constraints, and 
+more tightly coupled learning algorithms with differentiable simulations.
+
+As a _sneak preview_, in the next chapters we'll show:
+
+- How to train networks to infer fluid flow solutions around shapes like airfoils in one go, i.e., without needing a simulator.
+
+- We'll show how to use model equations as residual to train networks that represent solutions, and how to improve upon this behavior by using differentiable simulations.
+
+- Even more tightly coupling a full _rough_ simulator for control problems is another topic. E.g., we'll demonstrate how to circumvent the convergence problems of standard reinforcement learning techniques by leveraging simulators in the training loop.
+
+This _book_, where book stands for a collection of text, equations, images and code examples,
+is maintained by the
+[TUM Physics-based Simulation Group](https://ge.in.tum.de). Feel free to contact us via
+[old fashioned email](mailto:i15ge@cs.tum.edu) if you have any comments. 
+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!
+
+TODO, add teaser pic
+
+## Thanks!
+
+The contents of the following files would not have been possible without the help of many people. Here's an alphabetical list. Big kudos to everyone 🙏
+
+- Mr. X
+- Ms. y
+- ...
+
+
+
+% ----------------
+
+
+===
+
+## Planned content, loose collection of notes and TODOs:
+
+General physics & dl , intro & textual overview
+    more general intro: https://github.com/thunil/Physics-Based-Deep-Learning
+
+Supervised? Airfoils? Liwei, simple example? app: optimization, shape opt w surrogates
+
+-    AIAA supervised learning , idp_weissenov/201019-upd-arxiv-v2/  {cite}`thuerey2020deepFlowPred`
+    skepticism? , started colab -> https://colab.research.google.com/drive/11KUe5Ybuprd7_qmNTe1nvQVUz3W6gRUo
+    torch version 1.7 [upd from Liwei?]
+
+vs. PINNs [alt.: neural ODEs , PDE net?] , all using GD (optional, PINNs could use BFGS)
+    [PINNs], phiflow example -> convert to colab
+
+-    PINNs -> are unsupervised a la tompson; all DL NNs are "supervised" during learning, unsup just means not precomputed and goes through function
+
+-    add image | NN | <> | Loss | , backprop; (bring back every section, add variants for other methods?)
+
+-    discuss CG solver, tompson as basic ''unsupervisedd'' example?
+
+Diff phys, start with overview of idea: gradients via autodiff, then run GD
+        (TODO include squared func Patrick?)
+
+-    Differentiable Physics (w/o network) , {cite}`holl2019pdecontrol` 
+        -> phiflow colab notebook good start, but needs updates (see above Jan2)
+    illustrate and discuss gradients -> mult. for chain rule; (later: more general PG chain w func composition)
+
+-    SOL_201019-finals_Solver-in-the-Loop-Main-final.pdf , {cite}`um2020sol` 
+        numerical errors, how to include in jupyter / colab?
+
+-    ICLR_190925-ICLR-final_1d8cf33bb3c8825e798f087d6cd35f2c7c062fd4.pdf alias
+        PDE control, control focused
+        https://github.com/holl-/PDE-Control    -> update to new version?
+
+beyond GD: re-cap newton & co
+
+Phys grad (PGs) as fundamental improvement, PNAS case; add more complex one?
+        PG update of poisson eq? see PNAS-template-main.tex.bak01-poissonUpdate , explicitly lists GD and PG updates
+
+PGa 2020 Sept, content: ML & opt
+    Gradients.pdf, -> overleaf-physgrad/ 
+
+PGb 201002-beforeVac, content: v1,v2,old - more PG focused
+    -> general intro versions
+
+[MISSING, time series, sequence prediction?] {cite}`wiewel2019lss,bkim2019deep,wiewel2020lsssubdiv`
+[BAYES , prob?]
+[unstruct / lagrangian] {cite}`prantl2019tranquil,ummenhofer2019contconv`
+Outlook

jupyter-book-reference.md

@@ -0,0 +1,5 @@
+Jupyter Book Reference Stuff
+=======================
+
+There are many ways to write content in Jupyter Book. This short section
+covers a few tips for how to do so.

markdown.md

@@ -0,0 +1,125 @@
+# Markdown Files
+
+Whether you write your book's content in Jupyter Notebooks (`.ipynb`) or
+in regular markdown files (`.md`), you'll write in the same flavor of markdown
+called **MyST Markdown**.
+
+## What is MyST?
+
+MyST stands for "Markedly Structured Text". It
+is a slight variation on a flavor of markdown called "CommonMark" markdown,
+with small syntax extensions to allow you to write **roles** and **directives**
+in the Sphinx ecosystem.
+
+## What are roles and directives?
+
+Roles and directives are two of the most powerful tools in Jupyter Book. They
+are kind of like functions, but written in a markup language. They both
+serve a similar purpose, but **roles are written in one line**, whereas
+**directives span many lines**. They both accept different kinds of inputs,
+and what they do with those inputs depends on the specific role or directive
+that is being called.
+
+### Using a directive
+
+At its simplest, you can insert a directive into your book's content like so:
+
+````
+```{mydirectivename}
+My directive content
+```
+````
+
+This will only work if a directive with name `mydirectivename` already exists
+(which it doesn't). There are many pre-defined directives associated with
+Jupyter Book. For example, to insert a note box into your content, you can
+use the following directive:
+
+````
+```{note}
+Here is a note
+```
+````
+
+This results in:
+
+```{note}
+Here is a note
+```
+
+In your built book.
+
+For more information on writing directives, see the
+[MyST documentation](https://myst-parser.readthedocs.io/).
+
+
+### Using a role
+
+Roles are very similar to directives, but they are less-complex and written
+entirely on one line. You can insert a role into your book's content with
+this pattern:
+
+```
+Some content {rolename}`and here is my role's content!`
+```
+
+Again, roles will only work if `rolename` is a valid role's name. For example,
+the `doc` role can be used to refer to another page in your book. You can
+refer directly to another page by its relative path. For example, the
+role syntax `` {doc}`intro` `` will result in: {doc}`intro`.
+
+For more information on writing roles, see the
+[MyST documentation](https://myst-parser.readthedocs.io/).
+
+
+% ### Adding a citation
+% 
+% You can also cite references that are stored in a `bibtex` file. For example,
+% the following syntax: `` {cite}`holdgraf_evidence_2014` `` will render like
+% this: {cite}`holdgraf_evidence_2014`.
+% 
+% Moreoever, you can insert a bibliography into your page with this syntax:
+% The `{bibliography}` directive must be used for all the `{cite}` roles to
+% render properly.
+% For example, if the references for your book are stored in `references.bib`,
+% then the bibliography is inserted with:
+% 
+% ````
+% ```{bib liography} referenc es.bib
+% ```
+% ````
+% 
+% Resulting in a rendered bibliography that looks like:
+% 
+% ```{bib liography} refere nces.bib
+% ```
+
+
+### Executing code in your markdown files
+
+If you'd like to include computational content inside these markdown files,
+you can use MyST Markdown to define cells that will be executed when your
+book is built. Jupyter Book uses *jupytext* to do this.
+
+First, add Jupytext metadata to the file. For example, to add Jupytext metadata
+to this markdown page, run this command:
+
+```
+jupyter-book myst init markdown.md
+```
+
+Once a markdown file has Jupytext metadata in it, you can add the following
+directive to run the code at build time:
+
+````
+```{code-cell}
+print("Here is some code to execute")
+```
+````
+
+When your book is built, the contents of any `{code-cell}` blocks will be
+executed with your default Jupyter kernel, and their outputs will be displayed
+in-line with the rest of your content.
+
+For more information about executing computational content with Jupyter Book,
+see [The MyST-NB documentation](https://myst-nb.readthedocs.io/).

notebooks.ipynb

@@ -0,0 +1,122 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Content with notebooks\n",
+    "\n",
+    "You can also create content with Jupyter Notebooks. This means that you can include\n",
+    "code blocks and their outputs in your book.\n",
+    "\n",
+    "## Markdown + notebooks\n",
+    "\n",
+    "As it is markdown, you can embed images, HTML, etc into your posts!\n",
+    "\n",
+    "![](https://myst-parser.readthedocs.io/en/latest/_static/logo.png)\n",
+    "\n",
+    "You an also $add_{math}$ and\n",
+    "\n",
+    "$$\n",
+    "math^{blocks}\n",
+    "$$\n",
+    "\n",
+    "or\n",
+    "\n",
+    "$$\n",
+    "\\begin{aligned}\n",
+    "\\mbox{mean} la_{tex} \\\\ \\\\\n",
+    "math blocks\n",
+    "\\end{aligned}\n",
+    "$$\n",
+    "\n",
+    "But make sure you \\$Escape \\$your \\$dollar signs \\$you want to keep!\n",
+    "\n",
+    "## MyST markdown\n",
+    "\n",
+    "MyST markdown works in Jupyter Notebooks as well. For more information about MyST markdown, check\n",
+    "out [the MyST guide in Jupyter Book](https://jupyterbook.org/content/myst.html),\n",
+    "or see [the MyST markdown documentation](https://myst-parser.readthedocs.io/en/latest/).\n",
+    "\n",
+    "## Code blocks and outputs\n",
+    "\n",
+    "Jupyter Book will also embed your code blocks and output in your book.\n",
+    "For example, here's some sample Matplotlib code:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from matplotlib import rcParams, cycler\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "plt.ion()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Fixing random state for reproducibility\n",
+    "np.random.seed(19680801)\n",
+    "\n",
+    "N = 10\n",
+    "data = [np.logspace(0, 1, 100) + np.random.randn(100) + ii for ii in range(N)]\n",
+    "data = np.array(data).T\n",
+    "cmap = plt.cm.coolwarm\n",
+    "rcParams['axes.prop_cycle'] = cycler(color=cmap(np.linspace(0, 1, N)))\n",
+    "\n",
+    "\n",
+    "from matplotlib.lines import Line2D\n",
+    "custom_lines = [Line2D([0], [0], color=cmap(0.), lw=4),\n",
+    "                Line2D([0], [0], color=cmap(.5), lw=4),\n",
+    "                Line2D([0], [0], color=cmap(1.), lw=4)]\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(10, 5))\n",
+    "lines = ax.plot(data)\n",
+    "ax.legend(custom_lines, ['Cold', 'Medium', 'Hot']);"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "There is a lot more that you can do with outputs (such as including interactive outputs)\n",
+    "with your book. For more information about this, see [the Jupyter Book documentation](https://jupyterbook.org)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.0"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version_major": 2,
+    "version_minor": 0
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

overview.md

@@ -0,0 +1,69 @@
+Overview
+============================
+
+The following "book" of targets _"Physics-Based Deep Learning"_ techniques
+(PBDL), i.e., the field of methods with combinations of physical modeling and
+deep learning (DL) techniques. Here, DL will typically refer to methods based
+on artificial neural networks. The general direction of PBDL represents a very
+active, quickly growing and exciting field of research. As such, this collection 
+of materials is a living document, and will grow and change over time. Feel free
+to contribute 😀
+
+[TUM Physics-based Simulation Group](https://ge.in.tum.de).
+
+[Link collection](https://github.com/thunil/Physics-Based-Deep-Learning)
+
+## Motivation
+
+....
+
+## Categorization
+
+Within the area of _physics-based deep learning_, 
+we can distinguish a variety of different 
+approaches, from targeting designs, constraints, combined methods, and
+optimizations to applications. More specifically, all approaches either target
+_forward_ simulations (predicting state or temporal evolution) or _inverse_
+problems (e.g., obtaining a parametrization for a physical system from
+observations).
+
+![An overview of categories of physics-based deep learning methods](resources/physics-based-deep-learning-overview.jpg)
+
+No matter whether we're considering forward or inverse problem, 
+the most crucial differentiation for the following topics lies in the 
+nature of the integration  between DL techniques
+and the domain knowledge, typically in the form of model euqations.
+Looking ahead, we will particularly aim for a very tight intgration
+of the two, that goes beyond soft-constraints in loss functions.
+Taking a global perspective, the following three categories can be
+identified to categorize _physics-based deep learning_ (PBDL)
+techniques:
+
+- _Data-driven_: the data is produced by a physical system (real or simulated),
+  but no further interaction exists.
+
+- _Loss-terms_: the physical dynamics (or parts thereof) are encoded in the
+  loss function, typically in the form of differentiable operations. The
+  learning process can repeatedly evaluate the loss, and usually receives
+  gradients from a PDE-based formulation.
+
+- _Interleaved_: the full physical simulation is interleaved and combined with
+  an output from a deep neural network; this requires a fully differentiable
+  simulator and represents the tightest coupling between the physical system and
+  the learning process. Interleaved approaches are especially important for
+  temporal evolutions, where they can yield an estimate of future behavior of the
+  dynamics.
+
+Thus, methods can be roughly categorized in terms of forward versus inverse
+solve, and how tightly the physical model is integrated into the
+optimization loop that trains the deep neural network. Here, especially approaches
+that leverage _differentiable physics_ allow for very tight integration
+of deep learning and numerical simulation methods.
+
+The goal of this document is to introduce the different PBDL techniques,
+ordered in terms of growing tightness of the integration, give practical 
+starting points with code examples, and illustrate pros and cons of the 
+different approaches. In particular, it's important to know in which scenarios 
+each of the different techniques is particularly useful.
+
+

physicalloss.md

@@ -0,0 +1,7 @@
+Physical Loss Terms
+=======================
+
+Using the equations now, but no numerical methods!
+
+Still interesting, leverages analytic derivatives of NNs, but lots of problems
+

references.bib

@@ -0,0 +1,764 @@
+
+% Publications by Nils Thuerey
+
+@STRING{ACM_TOG        = "{ACM} Trans. Graph."}
+@STRING{CVPR           = "Proc. Comp. Vision and Pattern Rec."}
+@STRING{EG             = "{E}urographics"}
+@STRING{EG_CGF         = "Comp. Grap. Forum"}
+@STRING{EGSR           = "{E}urographics Symposium on Rendering"}
+@STRING{EGWR           = "{E}urographics Workshop on Rendering"}
+@STRING{SCA            = "{S}ymposium on Computer Animation"}
+@STRING{ICLR           = "International Conference on Learning Representations"}
+@STRING{ICML           = "International Conference on Machine Learning"}
+@STRING{NeurIPS        = "Advances in Neural Information Processing Systems"}
+
+
+
+@article{um2020sol,
+	  title={Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers},
+	  author={Um, Kiwon and Brand, Robert and Holl, Philipp and Fei, Raymond Thuerey, Nils},
+	  journal=NeurIPS,
+	  year={2020}
+}
+
+@article{kohl2020lsim,
+	  title={Learning Similarity Metrics for Numerical Simulations},
+	  author={Kohl, Georg and Um, Kiwon and Thuerey, Nils},
+	  journal=ICML,
+	  year={2020}
+}
+
+@article{wiewel2020lsssubdiv,
+	  title={Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow},
+	  author={Wiewel, Steffen and Kim, Byungsoo and Azevedo, Vinicius C and Solenthaler, Barbara and Thuerey, Nils},
+	  journal=SCA,
+	  year={2020}
+}
+
+@article{chu2020tecogan,
+	  title={Learning temporal coherence via self-supervision for GAN-based video generation},
+	  author={Chu, Mengyu and Xie, You and Mayer, Jonas and Leal-Taix{\'e}, Laura and Thuerey, Nils},
+	  journal=ACM_TOG,
+	  volume={39},
+	  number={4},
+	  pages={75--1},
+	  year={2020},
+	  publisher={ACM New York, NY, USA}
+}
+
+
+@inproceedings{weiss2020ssc,
+	  title={Correspondence-Free Material Reconstruction using Sparse Surface Constraints},
+		  author={Weiss, Sebastian and Maier, Robert and Cremers, Daniel and Westermann, Rudiger and Thuerey, Nils},
+		  booktitle=CVPR,
+		  pages={4686--4695},
+	  year={2020}
+}
+
+@inproceedings{holl2019pdecontrol,
+	  title={Learning to Control PDEs with Differentiable Physics},
+	  author={Holl, Philipp and Thuerey, Nils and Koltun, Vladlen},
+	  booktitle=ICLR,
+	  year={2019}
+}
+
+@article{prantl2019tranquil,
+	  title={Tranquil clouds: Neural networks for learning temporally coherent features in point clouds},
+	  author={Prantl, Lukas and Chentanez, Nuttapong and Jeschke, Stefan and Thuerey, Nils},
+	  journal=ICLR,
+	  year={2019}
+}
+
+@inproceedings{ummenhofer2019contconv,
+	  title={Lagrangian fluid simulation with continuous convolutions},
+	  author={Ummenhofer, Benjamin and Prantl, Lukas and Thuerey, Nils and Koltun, Vladlen},
+	  booktitle=ICLR,
+	  year={2019}
+}
+
+@article{eckert2019scalarflow,
+	  title={ScalarFlow: a large-scale volumetric data set of real-world scalar transport flows for computer animation and machine learning},
+	  author={Eckert, Marie-Lena and Um, Kiwon and Thuerey, Nils},
+	  journal=ACM_TOG,
+	  volume={38},
+	  number={6},
+	  pages={1--16},
+	  year={2019},
+	  publisher={ACM New York, NY, USA}
+}
+
+
+@article{thuerey2020deepFlowPred,
+	  title={Deep learning methods for Reynolds-averaged Navier--Stokes simulations of airfoil flows},
+	  author={Thuerey, Nils and Weissenow, Konstantin and Prantl, Lukas and Hu, Xiangyu},
+	  journal={AIAA Journal}, year={2020},
+	  volume={58}, number={1}, pages={25--36},
+	  publisher={American Institute of Aeronautics and Astronautics}
+}
+
+@article{prantl2019rtliq,
+	  title  ={{Generating Liquid Simulations with Deformation-Aware Neural Networks}},
+	  author={Lukas Prantl and Boris Bonev and Nils Thuerey},
+	  journal=ICLR,
+	  year={2019},
+  	pages={20}
+}
+
+
+@article{wiewel2019lss,
+	  title  ={{Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flow}},
+	  author={Steffen Wiewel and Moritz Becher and Nils Thuerey},
+	  journal=EG_CGF,
+	  year={2019},
+	  volume={38},
+	  number={2},
+	  pages={12},
+}
+
+@article{bkim2019deep,
+	  title  ={{Deep Fluids: A Generative Network for Parameterized Fluid Simulations}},
+	  author={Kim, Byungsoo and Azevedo, Vinicius C and Thuerey, Nils and Kim, Theodore and Gross, Markus and Solenthaler, Barbara},
+	  journal=EG_CGF,
+	  year={2019},
+	  volume={38},
+	  number={2},
+	  pages={12},
+}
+
+@article{xie2018tempoGan,
+	 author = {Xie, You and Franz, Erik and Chu, Mengyu and Thuerey, Nils},
+	 title  ={{tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow}},
+	 journal = ACM_TOG,
+	 volume = {37(4)},
+	 year = {2018},
+	 publisher = {ACM}
+} 
+
+@article{hikaru2018simulating,
+	  title  ={{Simulating Liquids on Dynamically Warping Grids}},
+	  author={Hikaru, Ibayashi and Wojtan, Chris and Thuerey, Nils and Igarashi, Takeo and Ando, Ryoichi},
+	  journal={IEEE Transactions on Visualization and Computer Graphics},
+	  year={2018},
+	  publisher={IEEE}
+}
+
+@article{ren2018visual,
+	  title  ={{Visual Simulation of Multiple Fluids in Computer Graphics: A State-of-the-Art Report}},
+	  author={Ren, Bo and Yang, Xu-Yun and Lin, Ming C and Thuerey, Nils and Teschner, Matthias and Li, Chenfeng},
+	  journal={Journal of Computer Science and Technology},
+	  volume={33},
+	  number={3},
+	  pages={431--451},
+	  year={2018},
+	  publisher={Springer}
+	}
+
+
+@article{um2018mlflip,
+	  title  ={{Splash Modeling with Neural Networks}},
+	  author={Kiwon Um and Xiangyu Hu and Nils Thuerey},
+	  journal=EG_CGF,
+	  volume={37(8)},
+	  year={2018}
+	}
+
+@article{eckert2018oiof,
+	  title  ={{Coupled Fluid Density and Motion from Single Views}},
+	  author={Marie-Lena Eckert and Wolfgang Heidrich and Nils Thuerey},
+	  journal=EG_CGF,
+	  volume={37(8)},
+	  year={2018}
+	}
+
+
+@article{sato2018,
+		journal = EG_CGF,
+		title ={{Extended Narrow Band FLIP for Liquid Simulations}},
+		author = {Sato, Takahiro and Wojtan, Chris and Thuerey, Nils and Igarashi, Takeo and Ando, Ryoichi},
+		year = {2018},
+		publisher = {Eurographics Association},
+		ISSN = {1467-8659},
+		DOI = {10.1111/cgf.13351}
+	}
+
+@inproceedings{inglis2017primal,
+	  title  ={{Primal-Dual Optimization for Fluids}},
+	  author={Inglis, Tiffany and Eckert, M-L and Gregson, James and Thuerey, Nils},
+	  booktitle =EG_CGF,
+	  volume={36(8)},
+	  pages={354--368},
+	  year={2017},
+	  organization={Wiley Online Library}
+}
+
+@inproceedings{eberhardt2017hierarchical,
+	  title  ={{Hierarchical vorticity skeletons}},
+	  author={Eberhardt, Sebastian and Weissmann, Steffen and Pinkall, Ulrich and Thuerey, Nils},
+	  booktitle =SCA,
+	  pages={6},
+	  year={2017},
+	  organization={ACM}
+}
+
+@article{um2017perceptual,
+	  title  ={{Perceptual evaluation of liquid simulation methods}},
+	  author={Um, Kiwon and Hu, Xiangyu and Thuerey, Nils},
+	  journal=ACM_TOG,
+	  volume={36},
+	  number={4},
+	  pages={143},
+	  year={2017},
+	  publisher={ACM}
+}
+
+@article{koschier2017xfem,
+	  title  ={{Robust eXtended finite elements for complex cutting of deformables}},
+	  author={Koschier, Dan and Bender, Jan and Thuerey, Nils},
+	  journal=ACM_TOG,
+	  volume={36},
+	  number={4},
+	  pages={55},
+	  year={2017},
+	  publisher={ACM}
+}
+
+@article{chu2017data,
+	  title  ={{Data-driven synthesis of smoke flows with CNN-based feature descriptors}},
+	  author={Chu, Mengyu and Thuerey, Nils},
+	  journal=ACM_TOG,
+	  volume={36},
+	  number={4},
+	  pages={69},
+	  year={2017},
+	  publisher={ACM}
+}
+
+@article{thuerey2017interpolations,
+  title  ={{Interpolations of Smoke and Liquid Simulations}},
+  author={Thuerey, Nils},
+  journal=ACM_TOG,
+  volume={36},
+  number={1},
+  pages={3},
+  year={2017},
+  publisher={ACM}
+}
+
+@article{canabal2016dispersion,
+  title  ={{Dispersion kernels for water wave simulation}},
+  author={Canabal, Jos{\'e} A and Miraut, David and Thuerey, Nils and Kim, Theodore and Portilla, Javier and Otaduy, Miguel A},
+  journal=ACM_TOG,
+  volume={35},
+  number={6},
+  pages={202},
+  year={2016},
+  publisher={ACM}
+}
+
+@article{jones2016example,
+  title  ={{Example-based plastic deformation of rigid bodies}},
+  author={Jones, Ben and Thuerey, Nils and Shinar, Tamar and Bargteil, Adam W},
+  journal=ACM_TOG,
+  volume={35},
+  number={4},
+  pages={34},
+  year={2016},
+  publisher={ACM}
+}
+
+@inproceedings{ferstl2016narrow,
+  title  ={{Narrow band FLIP for liquid simulations}},
+  author={Ferstl, Florian and Ando, Ryoichi and Wojtan, Chris and Westermann, R{\"u}diger and Thuerey, Nils},
+  booktitle =EG_CGF,
+  volume={35(2)},
+  pages={225--232},
+  year={2016},
+  organization={Wiley Online Library}
+}
+
+@article{monszpart2016smash,
+  title  ={{SMASH: physics-guided reconstruction of collisions from videos}},
+  author={Monszpart, Aron and Thuerey, Nils and Mitra, Niloy J},
+  journal=ACM_TOG,
+  volume={35},
+  number={6},
+  pages={199},
+  year={2016},
+  publisher={ACM}
+}
+
+@article{mercier2015surface,
+  title  ={{Surface turbulence for particle-based liquid simulations}},
+  author={Mercier, Olivier and Beauchemin, Cynthia and Thuerey, Nils and Kim, Theodore and Nowrouzezahrai, Derek},
+  journal=ACM_TOG,
+  volume={34},
+  number={6},
+  pages={202},
+  year={2015},
+  publisher={ACM}
+}
+
+@ARTICLE{ Ando:2015:streamfunc,
+	AUTHOR = {R. Ando and  N. Thuerey and  C. Wojtan},
+	TITLE = {{A Stream Function Solver for Liquid Simulations}},
+	YEAR = {2015},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {34 (4)},
+	PAGES = {8}
+}
+
+
+@ARTICLE{ Ando:2015:coarsegrid,
+	AUTHOR = {R. Ando and  N. Thuerey and  C. Wojtan},
+	TITLE = {{A Dimension-reduced Pressure Solver for Liquid Simulations}},
+	YEAR = {2015},
+	JOURNAL = EG_CGF,
+	PUBLISHER = {Eurographics Association},
+	VOLUME = {34 (2)},
+	PAGES = {10}
+}
+
+
+@ARTICLE{ Raveendran:2014:blendingLiquids,
+	AUTHOR = {K. Raveendran and  N. Thuerey and  C. Wojtan and  G. Turk},
+	TITLE = {{Blending Liquids}},
+	YEAR = {2014},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {33 (4)},
+	PAGES = {10}
+}
+
+
+@ARTICLE{ Gregson:2014:divFreeof,
+	AUTHOR = {J. Gregson and  N. Thuerey and  I. Ihrke and  W. Heidrich},
+	TITLE = {{From Capture to Simulation - Connecting Forward and Inverse Problems in Fluids}},
+	YEAR = {2014},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {33 (4)},
+	PAGES = {10}
+}
+
+
+@ARTICLE{ Ando:2013:tetFlip,
+	AUTHOR = {R. Ando and  N. Thuerey and  C. Wojtan},
+	TITLE = {{Highly Adaptive Liquid Simulations on Tetrahedral Meshes}},
+	YEAR = {2013},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {32 (4)},
+	PAGES = {10}
+}
+
+
+@ARTICLE{ TedKim:2012:closestPointTurb,
+	AUTHOR = {T. Kim and  J. Tessendorf and  N. Thuerey},
+	TITLE = {{Closest-Point Turbulence for Liquid Surfaces}},
+	YEAR = {2013},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {32 (2)},
+	PAGES = {10}
+}
+
+
+@ARTICLE{ Pfaff:2012:vortexSheets,
+	AUTHOR = {T. Pfaff and  N. Thuerey and  M. Gross},
+	TITLE = {{Lagrangian Vortex Sheets for Animating Fluids}},
+	YEAR = {2012},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {31 (4)},
+	PAGES = {8}
+}
+
+
+@ARTICLE{ Raveendran:2012:meshControl,
+	AUTHOR = {K. Raveendran and  N. Thuerey and  C. Wojtan and  G. Turk},
+	TITLE = {{Controlling Fluids using Meshes}},
+	YEAR = {2012},
+	JOURNAL = SCA,
+	PUBLISHER = {Eurographics Association},
+	PAGES = {1-8}
+}
+
+
+@ARTICLE{ Ando:2011:adaptiveThinSheets,
+	AUTHOR = {R. Ando and  N. Thuerey and  R. Tsuruno},
+	TITLE = {{Preserving Fluid Sheets with Adaptively Sampled Anisotropic Particles}},
+	YEAR = {2011},
+	JOURNAL = {IEEE Transactions on Visualization and Computer Graphics},
+	PUBLISHER = {IEEE},
+	VOLUME = {18 (8)},
+	PAGES = {1202-1214}
+}
+
+
+@ARTICLE{ Pfaff:2010:anisopart,
+	AUTHOR = {T. Pfaff and  N. Thuerey and  J. Cohen and  S. Tariq and  M. Gross},
+	TITLE = {{Scalable Fluid Simulation using Anisotropic Turbulence Particles}},
+	YEAR = {2010},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {29 (5)},
+	PAGES = {8}
+}
+
+
+@ARTICLE{ Thuerey:2010:surfacetens,
+	AUTHOR = {N. Thuerey and  C. Wojtan and  M. Gross and  G. Turk},
+	TITLE = {{A Multiscale Approach to Mesh-based Surface Tension Flows}},
+	YEAR = {2010},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {29 (4)},
+	PAGES = {10}
+}
+
+
+@ARTICLE{ Wojtan:2010:thinsheets,
+	AUTHOR = {C. Wojtan and  N. Thuerey and  M. Gross and  G. Turk},
+	TITLE = {{Physics-Inspired Topology Changes for Thin Fluid Features}},
+	YEAR = {2010},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {29 (4)},
+	PAGES = {8}
+}
+
+
+@ARTICLE{ Pfaff:2009:wallturb,
+	AUTHOR = {T. Pfaff and  N. Thuerey and  A. Selle and  M. Gross},
+	TITLE = {{Synthetic Turbulence using Artificial Boundary Layers}},
+	YEAR = {2009},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {28 (5)},
+	PAGES = {10}
+}
+
+
+@ARTICLE{ Wojtan:2009:topogoop,
+	AUTHOR = {C. Wojtan and  N. Thuerey and  M. Gross and G. Turk},
+	TITLE = {{Deforming Meshes that Split and Merge}},
+	YEAR = {2009},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {28 (3)},
+	PAGES = {9}
+}
+
+
+@ARTICLE{ Oskam:2009:camcontrol,
+	AUTHOR = {T. Oskam and  R. W. Sumner and  N. Thuerey and  M. Gross},
+	TITLE = {{Visibility Transition Planning for Real-Time Camera Control}},
+	YEAR = {2009},
+	JOURNAL = SCA,
+	PUBLISHER = {Eurographics Association},
+	PAGES = {55-65}
+}
+
+
+@ARTICLE{ Thuerey:2009:dpfcGraphMod,
+	AUTHOR = {N. Thuerey and  R. Keiser and  U. Ruede and  M. Pauly},
+	TITLE = {{Detail-Preserving Fluid Control}},
+	YEAR = {2009},
+	JOURNAL = {Graphical Models},
+	PUBLISHER = {Elsevier},
+	VOLUME = {71,6},
+	PAGES = {221-228}
+}
+
+
+@ARTICLE{ TedKim:2008:waveletTurbulence,
+	AUTHOR = {T. Kim and  N. Thuerey and  D. James and  M. Gross},
+	TITLE = {{Wavelet Turbulence for Fluid Simulation}},
+	YEAR = {2008},
+	JOURNAL = ACM_TOG,
+	PUBLISHER = {ACM Press},
+	VOLUME = {27 (3)},
+	PAGES = {6}
+}
+
+
+@ARTICLE{ Angst:2008:fluidchar,
+	AUTHOR = {R. Angst and  N. Thuerey and  M. Botsch and  M. Gross},
+	TITLE = {{Robust and Efficient Wave Simulations on Deforming Meshes}},
+	YEAR = {2008},
+	JOURNAL = EG_CGF,
+	PUBLISHER = {Blackwell Publishing},
+	VOLUME = {27 (7)},
+	PAGES = {1895-1900}
+}
+
+
+@ARTICLE{ Thuerey:2008:adapLbm,
+	AUTHOR = {N. Thuerey and  U. Ruede},
+	TITLE = {{Stable free surface flows with the lattice Boltzmann method on adaptively coarsened grids}},
+	YEAR = {2009},
+	JOURNAL = {Computing and Visualization in Science},
+	PUBLISHER = {Springer},
+	VOLUME = {12 (5)}
+}
+
+
+@ARTICLE{ Sumner:2008:ethgpl,
+	AUTHOR = {R. Sumner and  N. Thuerey and M. Gross},
+	TITLE = {{The ETH Game Programming Laboratory: A Capstone for Computer Science and Visual Computing}},
+	YEAR = {2008},
+	JOURNAL = {Game Development in Computer Science Education},
+	PUBLISHER = {ACM}
+}
+
+
+@ARTICLE{ Thuerey:2007:paraLbm,
+	AUTHOR = {N. Thuerey and  T. Pohl and U. Ruede},
+	TITLE = {{Hybrid Parallelization Techniques for Lattice Boltzmann Free Surface Flows}},
+	YEAR = {2007},
+	JOURNAL = {Proceedings of Parallel CFD 2007},
+	PUBLISHER = {-},
+	PAGES = {1-8}
+}
+
+
+@ARTICLE{ Iglberger:2008:movPartLbm,
+	AUTHOR = {K. Iglberger and  N. Thuerey and U. Ruede},
+	TITLE = {{Simulation of moving particles in 3D with the Lattice Boltzmann method}},
+	YEAR = {2008},
+	JOURNAL = {Computers and Mathematics with Applications, Mesoscopic Methods in Engineering and Science},
+	PUBLISHER = {Elsevier},
+	VOLUME = {55 (7)},
+	PAGES = {1461-1468},
+	EDITORS = {L.-S. Luo, M. Krafczyk and Y. Liu}
+}
+
+
+@ARTICLE{ Thuerey:2007:rtWaves,
+	AUTHOR = {N. Thuerey and  M. Mueller-Fischer and  S. Schirm and  M. Gross},
+	TITLE = {{Real-time Breaking Waves for Shallow Water Simulations}},
+	YEAR = {2007},
+	JOURNAL = {Proc. Pacific Conference on Computer Graphics and Applications},
+	PUBLISHER = {IEEE Computer Society},
+	PAGES = {39-46}
+}
+
+
+@ARTICLE{ Thuerey:2007:swsBubbles,
+	AUTHOR = {N. Thuerey and  F. Sadlo and  S. Schirm and  M. Mueller-Fischer and M. Gross},
+	TITLE = {{Real-time simulations of bubbles and foam within a shallow water framework}},
+	YEAR = {2007},
+	JOURNAL = SCA,
+	PUBLISHER = {Eurographics Association},
+	PAGES = {191-198}
+}
+
+
+@ARTICLE{ Thuerey:2006:SCA06dpfc,
+	AUTHOR = {N. Thuerey and  R. Keiser and  U. Ruede and M. Pauly},
+	TITLE = {{Detail-Preserving Fluid Control}},
+	YEAR = {2006},
+	JOURNAL = SCA,
+	PUBLISHER = {Eurographics Association},
+	PAGES = {7-12}
+}
+
+
+@ARTICLE{ Thuerey:2006:SCA06sws,
+	AUTHOR = {N. Thuerey and  U. Ruede and M. Stamminger},
+	TITLE = {{Animation of Open water Phenomena with coupled Shallow Water and Free Surface Simulation}},
+	YEAR = {2006},
+	JOURNAL = SCA,
+	PUBLISHER = {Eurographics Association},
+	PAGES = {157-166}
+}
+
+
+@ARTICLE{ Thuerey:2006:VMV06,
+	AUTHOR = {N. Thuerey and  K. Iglberger and U. Ruede},
+	TITLE = {{Free Surface Flows with Moving and Deforming Objects for LBM}},
+	YEAR = {2006},
+	JOURNAL = {Proceedings of Vision, Modeling and Visualization 2006},
+	PUBLISHER = {IOS Press},
+	PAGES = {193-200}
+}
+
+
+@ARTICLE{ Zheng:2006:VMV06,
+	AUTHOR = {Y. Zheng and  H. Koestler and  N. Thuerey and U. Ruede},
+	TITLE = {{Enhanced Motion Blur Calculation with Optical Flow}},
+	YEAR = {2006},
+	JOURNAL = {Proceedings of Vision, Modeling and Visualization 2006},
+	PUBLISHER = {IOS Press},
+	PAGES = {253-260}
+}
+
+
+@ARTICLE{ Binder:2006:jcollif,
+	AUTHOR = {C. Binder and  C. Feichtinger and  H.-J. Schmid and  N. Thuerey and  W. Peukert and U. Ruede},
+	TITLE = {{Simulation of the Hydrodynamic Drag of Aggregated Particles}},
+	YEAR = {2006},
+	JOURNAL = {Journal of Colloid and Interface Science},
+	PUBLISHER = {Elsevier},
+	VOLUME = {301},
+	PAGES = {155-167}
+}
+
+
+@ARTICLE{ Koerner:2006:PLBM,
+	AUTHOR = {C. Koerner and  T. Pohl and  U. Ruede and  N. Thuerey and T. Zeiser},
+	TITLE = {{Parallel Lattice Boltzmann Methods for CFD Applications}},
+	YEAR = {2006},
+	JOURNAL = {Numerical Solution of Partial Differential Equations on Parallel Computers},
+	PUBLISHER = {Springer},
+	VOLUME = {ISBN 3-540-29076-1},
+	PAGES = {439-465}
+}
+
+
+@ARTICLE{ Thuerey:2006:adapParam,
+	AUTHOR = {N. Thuerey and  T. Pohl and  U. Ruede and  M. Oechsner and C. Koerner},
+	TITLE = {{Optimization and Stabilization of LBM Free Surface Flow Simulations using Adaptive Parameterization}},
+	YEAR = {2006},
+	JOURNAL = {Computers and Fluids},
+	PUBLISHER = {Elsevier},
+	VOLUME = {35 [8-9]},
+	PAGES = {934-939}
+}
+
+
+@ARTICLE{ Koerner:2005:lbmFoaming,
+	AUTHOR = {C. Koerner and  M. Thies and  T. Hofmann and  N. Thuerey and U. Ruede},
+	TITLE = {{Lattice Boltzmann Model for Free Surface Flow for Modeling Foaming}},
+	YEAR = {2005},
+	JOURNAL = {Journal of Statistical Physics},
+	PUBLISHER = {Springer},
+	VOLUME = {121 [1-2]},
+	PAGES = {179--196}
+}
+
+
+@ARTICLE{ Thuerey:2004:fsLevelsetLbm,
+	AUTHOR = {N. Thuerey and U. Ruede},
+	TITLE = {{Free Surface Lattice-Boltzmann fluid simulations with and without level sets}},
+	YEAR = {2004},
+	JOURNAL = {Proc. of Vision, Modelling, and Visualization VMV},
+	PUBLISHER = {IOS Press},
+	PAGES = {199-207}
+}
+
+
+@ARTICLE{ Pohl:2004:paraLbmSc,
+	AUTHOR = {T. Pohl and  Frank Deserno and  N. Thuerey and  U. Ruede and  P. Lammers and  G. Wellein and T. Zeiser},
+	TITLE = {{Performance Evaluation of Parallel Large-Scale Lattice Boltzmann Applications on Three Supercomputing Architectures}},
+	YEAR = {2004},
+	JOURNAL = {SC '04: Proceedings of the 2004 ACM/IEEE conference on Supercomputing},
+	PUBLISHER = {IEEE Computer Society},
+	PAGES = {21}
+}
+
+
+@ARTICLE{ Thuerey:2002:perfOpt3dMg,
+	AUTHOR = {M. Kowarschik and  U. Ruede and  N. Thuerey and C. Weiss},
+	TITLE = {{Performance Optimization of 3D Multigrid on Hierarchical Memory Architectures}},
+	YEAR = {2002},
+	JOURNAL = {Proceedings of PARA'02},
+	PUBLISHER = {Springer, Lecture Notes in Computer Science},
+	PAGES = {307-318}
+}
+
+
+@ARTICLE{ Gross:2011:gameDesignChapter,
+	AUTHOR = {M. Gross and  R. Sumner and  N. Thuerey},
+	TITLE = {{The Design and Development of Computer Games}},
+	YEAR = {2011},
+	JOURNAL = {The Design of Material, Organism, and Minds (Editors: S. Lang, M. Hampe)},
+	PUBLISHER = {Springer},
+	VOLUME = {ISBN 978-3-549-68995-9},
+	PAGES = {14}
+}
+
+
+@ARTICLE{ Thuerey:2007b:phd,
+	AUTHOR = {N. Thuerey},
+	TITLE = {{Physically based Animation of Free Surface Flows with the Lattice Boltzmann Method}},
+	YEAR = {2007},
+	JOURNAL = {PhD thesis},
+	PUBLISHER = {Dept. of Computer Science 10, University of Erlangen-Nuremberg},
+	VOLUME = {ISBN 978-3-89963-519-5}
+}
+
+
+@ARTICLE{ Thuerey:2006:drdobbs,
+	AUTHOR = {N. Thuerey},
+	TITLE = {{Fluid Simulation with Blender}},
+	YEAR = {2006},
+	JOURNAL = {Dr. Dobbs Journal},
+	PUBLISHER = {CMP Media}
+}
+
+
+@ARTICLE{ Iglberger:2005:movNanoPart,
+	AUTHOR = {Iglberger and  N. Thuerey and  U. Ruede and  H. Schmid and W. Peukert},
+	TITLE = {{Simulation of moving Nano-Particles with the Lattice Boltzmann Method in 3D}},
+	YEAR = {2005},
+	JOURNAL = {Proceedings of ASIM '05},
+	PUBLISHER = {SCS Publishing House}
+}
+
+
+@ARTICLE{ Feichtinger:2005:dragForcesLbm,
+	AUTHOR = {C. Feichtinger and  N. Thuerey and  U. Ruede and  C. Binder and  H. Schmid and  W. Peukert},
+	TITLE = {{Drag Force Simulations of Particle Agglomerates with the Lattice-Boltzmann Method}},
+	YEAR = {2005},
+	JOURNAL = {Proceedings of ASIM '05},
+	PUBLISHER = {SCS Publishing House}
+}
+
+
+@ARTICLE{ Thuerey:2005:adapGridsLbm,
+	AUTHOR = {N. Thuerey and U. Ruede},
+	TITLE = {{Optimized Free Surface Fluids on Adaptive Grids with the Lattice Boltzmann Method}},
+	YEAR = {2005},
+	JOURNAL = {Poster},
+	PUBLISHER = {SIGGRAPH '05}
+}
+
+
+@ARTICLE{ Thuerey:2005:interactiveLbmFluids,
+	AUTHOR = {N. Thuerey and  C. Koerner and U. Ruede},
+	TITLE = {{Interactive Free Surface Fluids with the Lattice Boltzmann Method}},
+	YEAR = {2005},
+	JOURNAL = {Technical Report 05-4},
+	PUBLISHER = {Department of Computer Science 10 System Simulation}
+}
+
+
+@ARTICLE{ Thuerey:2003:lbmMetallschaum,
+	AUTHOR = {N. Thuerey and  U. Ruede and C. Koerner},
+	TITLE = {{Simulation von Metallschaum mittels der Lattice-Boltzmann Methode}},
+	YEAR = {2003},
+	JOURNAL = {Konwihr Quartl},
+	PUBLISHER = {KONWIHR},
+	VOLUME = {35}
+}
+
+
+@ARTICLE{ Thuerey:2003:singlePhaseFsLbm,
+	AUTHOR = {N. Thuerey},
+	TITLE = {{A Lattice Boltzmann method for single-phase free surface flows in 3D}},
+	YEAR = {2003},
+	JOURNAL = {Master thesis},
+	PUBLISHER = {Dept. of Computer Science 10, University of Erlangen-Nuremberg}
+}
+
+
+@ARTICLE{ Thuerey:2002:cacheOptMg,
+	AUTHOR = {N. Thuerey},
+	TITLE = {{Cache Optimizations for Multigrid in 3D}},
+	YEAR = {2002},
+	JOURNAL = {Semester thesis},
+	PUBLISHER = {Dept. of Computer Science 10, University of Erlangen-Nuremberg}
+}
+

references.md

@@ -0,0 +1,9 @@
+References
+============================
+
+% in new section?
+
+```{bibliography} references.bib
+```
+
+

supervised.md

@@ -0,0 +1,5 @@
+Supervised Learning
+=======================
+
+Doing things the old fashioned way...
+