MedeA Machine Learning Potential Generator (MLPG)

MedeA Machine Learning Potential Generator (MLPG)

This training session provides an overview on MedeA's new machine-learned potential capabilities. 


A demonstration of MedeA LAMMPS with machine-learned potentials (MLPs), as provided by MedeA, will be followed by an introduction to the new machine-learned potential generator (MLPG) of MedeA.  MLPG allows the user to independently create their own MLP.   


We'll discuss guidelines for constructing a training set, performing DFT calculations for all structures included in the training set, and efficient storage of relevant data for use with the MLPG. 


This training session will enable users to perform LAMMPS calculations with MLPs as well as to create and apply their own MLPs. 

David Reith
Application & Research Scientist

David has an academic background and expertise rooted on the development and application of ab initio based simulations techniques for materials science