MDSI Workshop: Computational Material Design powered by Machine Learning

Date: 24. February, 2022


Computational science has been of paramount importance in providing physical understanding as well as technological advancement for material and device development. Recently, the field has been propelled by the fusion of computational and machine learning (ML) techniques. Several approaches were proposed ranging from directly modeling atomistic structure-property relations, using ML as a surrogate model, to incorporating directly ML models within simulations. Although different spatial scales in materials (quantum, atomistic, continuum) face different obstacles, many challenges are common to all scales such as the need for sufficiently broad datasets that are simultaneously as small as possible. Knowledge transfer between computational science subfields can therefore boost advances in both method development and application.

The workshop aims at bringing together leading world and local TUM experts in the field to foster collaborations, initiate discussion, and stimulate new ideas to tackle the pressing challenges in computational material design. 



09:00 - 09:15

Welcome by Organizers

Minisymposium 1 (moderator: Alessio Gagliardi)
09:15 - 09:50

Keynote lecture - Michele Ceriotti (EPFL)
Machine learning for atomistic materials modeling

09:50 - 10:00


10:00 - 10:20

Short Talk - Stelios Koutsourelakis
Data-driven inversion of the process-structure-property chain for the design of random material microstructures

10:20 - 10:40

Short Talk - Stephan Günnemann
Directional Graph Neural Networks for Molecules

10:40 - 11:00

Short Talk - Julija Zavadlav
Machine learning-based molecular modeling consistent with experimental data

11:00 - 13:00

Lunch Break

Minisymposium 2 (moderator: Stephan Günnemann)
13:00 - 13:35

Keynote lecture - Frank Noe (FU Berlin)
Deep Learning for Molecular Physics

13:35 - 13:40


13:40 - 14:00

Short Talk - Harald Oberhofer
Computational Design of Small Molecule Organic Semiconductors

14:00 - 14:20

Short Talk - David Egger
Raman Spectra of Materials with Kernel-Based Machine Learning

14:20 - 14:40 Short Talk - Alessio Gagliardi

Multiscale simulations & Machine learning: charge transport in organic semiconductors

14:40 - 15:00


Minisymposium 3 (moderator: Julija Zavadlav)
15:00 - 15:20 Short Talk - Nils Thuerey
Deep Learning Algorithms for Fluid Simulations
15:20 - 15:40 Short Talk - Nikolaus Adams

Multi-fidelity prediction of crystallization as basis of Bayesian optimization

15:40 - 16:00

Short Talk - Axel Zimmermann
What have we learned about combustion dynamics?

16:00 - 16:05 Break
16:05 - 16:40

Keynote lecture - Petros Koumoutsakos (Harvard)

AI and Computational Science: Computational Intelligence vs Artificial Science

16:40 - 16:50

Closing words

17:15 - 18:15

Closed session at MDSI



Please register your participation via the following link:

After registering, you will receive a confirmation email containing information about joining the meeting. Registration is open until 20. February, 2022.