Difference between revisions of "Data Driven Modelling Special Interest Group"

From OpenFOAM Wiki
Jump to navigation Jump to search
Line 25: Line 25:
 
We aim to have short virtual meetings (max. 1h) every '''two''' months and meet in person, if possible, at the OpenFOAM conference and workshop. The bi-monthly meetings update all members about the recent progress and coordinate upcoming efforts. Everybody is welcome to join our meetings. Past and upcoming meetings are listed below:
 
We aim to have short virtual meetings (max. 1h) every '''two''' months and meet in person, if possible, at the OpenFOAM conference and workshop. The bi-monthly meetings update all members about the recent progress and coordinate upcoming efforts. Everybody is welcome to join our meetings. Past and upcoming meetings are listed below:
  
* next virtual meeting: May/June 2023
+
* next virtual meeting: September/October 2023
 +
* next in-person meeting at the OpenFOAM workshop, Genoa
 +
* Jun 27 2023, online
 
* Mar 24 2023, online, [https://andreweiner.github.io/reveal.js/ofml_tc_6.html#/ slides]
 
* Mar 24 2023, online, [https://andreweiner.github.io/reveal.js/ofml_tc_6.html#/ slides]
 
* Jan 30 2023, online, [https://andreweiner.github.io/reveal.js/ofml_tc_5.html#/ slides]
 
* Jan 30 2023, online, [https://andreweiner.github.io/reveal.js/ofml_tc_5.html#/ slides]
Line 37: Line 39:
 
The following OpenFOAM+ML [https://github.com/OFDataCommittee/OFMLHackathon hackathons] have been organized by the special interest group:
 
The following OpenFOAM+ML [https://github.com/OFDataCommittee/OFMLHackathon hackathons] have been organized by the special interest group:
  
* next hackathon: June/July 2023
+
* next hackathon: July 2023
 
* Jan 23-25, 2023, virtual
 
* Jan 23-25, 2023, virtual
 
* July 23-25, 2022, virtual
 
* July 23-25, 2022, virtual

Revision as of 13:52, 29 June 2023

Scope

For us, data-driven modeling comprises a variety of different topics, some of which are listed below:

  • machine learning (ML): combining CFD and ML, e.g., using ML models in CFD or deriving ML models from CFD data
  • data science: analyzing CFD data to guide modeling and decision making
  • data engineering: aggregating, storing, and processing CFD data

The following list briefly summarizes our current objectives:

  • short term objectives
    • reduce the technical barrier to get started with data-driven modeling in OpenFOAM to enable more people to include data-driven workflows in their applications or research
    • promote data-driven techniques that are already available in OpenFOAM, e.g., dynamic mode decomposition (DMD)
    • promote third-party libraries for data-driven modeling that are based on or built for OpenFOAM
  • long term objectives
    • aid the understanding of when and how to use data-driven modeling in the CFD workflow
    • accelerate developments and applications of data-driven approaches around OpenFOAM
    • establish tested data-driven techniques as a natural element of CFD simulations to improve accuracy and/or speed

Work process

A detailed roadmap and a collection of resources are available on Github. The GitHub repository is also an excellent means to get in touch (e.g., via GitHub issues). Besides the repository, feel free to contact the SIG's chairs, Andre Weiner and Tomislav Marić, or any other member of the SIG.

Meetings

We aim to have short virtual meetings (max. 1h) every two months and meet in person, if possible, at the OpenFOAM conference and workshop. The bi-monthly meetings update all members about the recent progress and coordinate upcoming efforts. Everybody is welcome to join our meetings. Past and upcoming meetings are listed below:

  • next virtual meeting: September/October 2023
  • next in-person meeting at the OpenFOAM workshop, Genoa
  • Jun 27 2023, online
  • Mar 24 2023, online, slides
  • Jan 30 2023, online, slides
  • Oct 11 2022, online, slides
  • July 21 2022, OpenFOAM-v2206 release webinar, slides
  • July 11 2022, in person, 17th OpenFOAM Workshop, Cambridge
  • Jun 9 2022, online, slides
  • Apr 5 2022, online, slides
  • Feb 8 2022, online, slides

The following OpenFOAM+ML hackathons have been organized by the special interest group:

  • next hackathon: July 2023
  • Jan 23-25, 2023, virtual
  • July 23-25, 2022, virtual

Members

  • Andre Weiner, Technical University of Braunschweig, chair
  • Tomislav Marić, Technical University of Darmstadt, co-chair
  • Abhijeet Vishwasrao, Ecole Polytechnique Paris
  • Alex Skillen, The University of Manchester
  • Ajay Bangalore Harish, The University of Manchester
  • Chiara Pesci, ESI
  • Dirk Gründing, private contributer
  • François Mazen, Kitware
  • Holger Marschall, Technical University of Darmstadt
  • Karthik Kashinath, Nvidia
  • Kutalmis Bercin, ESI-OpenCFD
  • Nausheen Basha, Imperial College London
  • Neil Ashton, Amazon Web Services
  • Rahul Sundar, Indian Insitute of Technology, Madras
  • Reza Lotfi Navaei, Tarbiat Modares University, Tehran
  • Saeed Salehi, Chalmers University of Technology

If you would like to participate actively in this SIG, please get in touch.