Agenda
The Materials Design User Group Meeting represents a unique opportunity to interact with colleagues and developers, present results, learn about developments in MedeA, and see the latest developments in computational material science and engineering.
The Plenary Sessions and Training Sessions will be open to all registrants in 2022. Sessions cover a broad range of research and modeling areas that will educate and inspire.
Speakers include:
-
Prof. Jörg Behler
-
Dr. Jozef Bicerano
-
Prof. Jeffrey Grossman
-
Prof. Georg Kresse
-
Dr. Carla Verdi
Register for the UGM.
Learn about our Plenary Speakers.
October 12, 2022
plenary
Atomistic Simulations with High-Dimensional Neural Network Potentials
Jörg Behler
October 12, 2022, 11:00 AM EDT / 8:00 AM PDT
In this talk, the evolution of MLPs will be illustrated using high-dimensional neural networks, an important and frequently used type of MLPs. Some examples concerning their applicability will be presented.
October 13, 2022
training
MedeA Training: Generating and Applying Machine-Learned Potentials with MedeA
David Reith
October 13, 2022, 8:00 AM PDT
This session introduces MedeA's Machine-Learned Potential Generator (MLPG), which allows to generate MLPs in a highly efficient manner for a given set of training structures.
October 18, 2022
plenary
Δ-Machine Learning Beyond DFT: from Phase Transitions to Quantum Paraelectricity and CO Adsorption
Georg Kresse
October 18, 2022, 10:00 AM EDT / 7:00 AM PDT
This talk will discuss the on-the-fly learning technique implemented in VASP, based on molecular dynamics and Bayesian
inference, and a Δ-machine learning approach.
October 27, 2022
training
MedeA Training: Multiscale Modeling of Polymers Using the MedeA Environment
Jörg-Rüdiger Hill
October 27, 2022, 8:00 AM PDT
We will demonstrate how to build both atomistic and coarse-grained models of polymers using the amorphous builder, and how to run simulations with the LAMMPS and Gibbs molecular dynamics and Monte Carlo codes.