Description

Back to top

Atomistic simulations such as molecular dynamics (MD) are a cornerstone of computational material science. MD is a powerful tool that can generate fully-resolved, (classically) dynamically correct trajectories based only on a description of the energetics of the interactions between atoms. A longstanding challenge in MD is the development of approximations to the exact quantum potential energy surface that are computationally affordable and scalable, therefore enabling simulations of much larger systems over much longer times than are possible using direct solutions to Schrödinger’s equation.

Until recently, the functional form of these so-called interatomic potentials was largely based on physical considerations. In the past years, machine learning approaches thoroughly reshaped the field through the introduction of numerical methods which require less prior knowledge, lead to lower regression errors, and better transferability. While machine learning has shown great promise, developments are often still guided by ad hoc heuristics, which slows down further progress. This calls for a rigorous study of the modeling and numerical errors involved in the representation of forces and energies obtained from quantum mechanics by models of classical mechanics, through both a priori or a posteriori error estimates, of uncertainty quantification for detecting which parameters influence most the results, of the influence of the training database or how it should be augmented to minimize prediction errors.

This workshop aims to explore mathematical challenges of this kind and to discuss how fundamental insights can be translated into practical improvements in the cost/accuracy tradeoff of the next generation of data-driven interatomic potentials, enabling robust large-scale simulations at unprecedented accuracies and spatio-temporal scales.

This workshop will include lightning talks for early career researchers (including graduate students). In order to propose a lightning session talk, you must first register for the workshop, and then submit a proposal using the form that will become available on this page after you register. The registration form should not be used to propose a lightning session talk.

The deadline for proposing is April 2, 2024. If your proposal is accepted, you should plan to attend the event in-person.

Organizers

Back to top
G D
Geneviève Dusson Centre National de la Recherche Scientifique
R K
Risi Kondor University of Chicago
C O
Christoph Ortner University of British Columbia
D P
Danny Perez Los Alamos National Laboratory

Speakers

Back to top
A A
Alice Allen Los Alamos National Laboratory
I B
Ilyes Batatia Cambridge University
A B
Anton Bochkarev Ruhr-Universität Bochum
M C
Michele Ceriotti EPFL
R C
Rose Cersonsky University of Wisconsin
B C
Bingqing Chen Institute of Science and Technology Austria
G C
Gábor Csany University of Cambridge
R D
Ralf Drautz ICAMS, Ruhr-Universität
E G
Elena Gelzinyte Cambridge University
J G
James Goff Sandia National Laboratory
T H
Teresa Head-Gordon University of California, Berkeley (UC Berkeley)
J J
Jan Janssen Max-Planck-Institut für Eisenforschung GmbH
J K
James Kermode University of Warwick
J L
Julien Lam CNRS-Lille
C M
Cosmin Marinica CEA
N N
Ngoc-Cuong Nguyen Massachusetts Institute of Technology (MIT)
J N
Jigyasa Nigam EPFL
C O
Cameron Owen Harvard University
A P A S
Aparna P. A. Subramanyam Los Alamos National Laboratory (LANL)
C v d O
Cas van der Oord Cambridge University
Y W
Yangshuai Wang University of British Columbia

Schedule

Back to top
Monday, April 8, 2024
9:00-9:45 CDT
Atomic cluster expansion for modeling local and semilocal atomic interactions

Speaker: Ralf Drautz (Ruhr-Universität Bochum)

9:45-10:00 CDT
Q&A
10:00-10:30 CDT
Coffee Break
10:30-11:00 CDT
TBA

Speaker: Alice Allen (Los Alamos National Laboratory)

11:00-11:10 CDT
Q&A
11:10-11:15 CDT
Tech Break
11:15-12:00 CDT
Physics-Inspired Machine Learning Methods: A Status Report on Predictive Chemistry

Speaker: Teresa Head-Gordon (University of California, Berkeley (UC Berkeley))

12:00-12:15 CDT
Q&A
12:15-13:15 CDT
Lunch Break
13:15-13:45 CDT
Matrix Function Networks for learning non local quantum effects.

Speaker: Ilyes Batatia (Cambridge University)

13:45-13:55 CDT
Q&A
13:55-14:00 CDT
Tech Break
14:00-14:30 CDT
Pyiron: workflows for the development and assessment of interatomic potentials

Speaker: Jan Janssen (Max-Planck-Institut für Eisenforschung GmbH)

14:30-14:40 CDT
Q&A
14:40-15:40 CDT
Social Hour
Tuesday, April 9, 2024
9:00-9:45 CDT
A MACE force field for all of materials chemistry

Speaker: Gabor Csanyi (University of Cambridge)

9:45-10:00 CDT
Q&A
10:00-10:30 CDT
Coffee Break
10:30-11:00 CDT
A Framework for Generalization Analysis of Machine-Learned Interatomic Potentials: A Case Study on Crystalline Defects

Speaker: Yangshuai Wang (University of British Columbia)

11:00-11:10 CDT
Q&A
11:10-11:15 CDT
Tech Break
11:15-12:00 CDT
Environment-adaptive machine learning potentials for atomistic simulations of materials under extreme conditions

Speaker: Ngoc-Cuong Nguyen (Massachusetts Institute of Technology (MIT))

12:00-12:15 CDT
Q&A
12:15-13:15 CDT
Lunch Break
13:15-13:45 CDT
Unpacking the ingredients of atomic representations: machine learning force fields and beyond

Speaker: Jigyasa Nigam (EPFL)

13:45-13:55 CDT
Q&A
13:55-14:00 CDT
Tech Break
14:00-14:30 CDT
TBA

Speaker: Aparna Subramanyam (Los Alamos National Laboratory (LANL))

14:30-14:40 CDT
Q&A
14:40-15:10 CDT
Coffee Break
15:10-16:10 CDT
Lightning Talks for Junior Participants
Wednesday, April 10, 2024
9:00-9:45 CDT
Machine-learning of long-range, non-bonded interactions

Speaker: Michele Ceriotti (EPFL)

9:45-10:00 CDT
Q&A
10:00-10:30 CDT
Coffee Break
10:30-11:00 CDT
Bayesian and Equivariant Force Fields for the Description of Metals in their Bulk, Surface, and Nano-Scale Forms

Speaker: Cameron Owen (Harvard University)

11:00-11:10 CDT
Q&A
11:10-11:15 CDT
Tech Break
11:15-12:00 CDT
Cartesian atomic cluster expansion for machine learning interatomic potentials

Speaker: Bingqing Cheng (UC Berkeley)

12:00-12:15 CDT
Q&A
12:15-13:15 CDT
Lunch
13:15-14:00 CDT
Collaborations, free discussions
14:00-14:30 CDT
TBA

Speaker: Cas van der Oord (University of Cambridge)

14:30-14:40 CDT
Q&A
14:40-15:10 CDT
Coffee Break
15:10-15:40 CDT
Exploiting linear models for transferability and long-range interactions

Speaker: Julien Lam

15:40-15:50 CDT
Q&A
Thursday, April 11, 2024
9:00-9:45 CDT
Multiscale and Data-driven Methods for the Simulation of Materials Failure

Speaker: James Kermode (University of Warwick)

9:45-10:00 CDT
Q&A
10:00-10:30 CDT
Coffee Break
10:30-11:00 CDT
Charge and other advances in the Ch.ACE for next generation interatomic potentials

Speaker: James Goff (Sandia National Laboratory)

11:00-11:10 CDT
Q&A
11:10-11:15 CDT
Tech Break
11:15-12:00 CDT
TBA

Speaker: Rose Ceronsky (University of Wisconsin)

12:00-12:15 CDT
Q&A
12:15-13:15 CDT
Lunch
13:15-14:00 CDT
Collaborations, free discussions
14:00-14:30 CDT
Machine Learning Interatomic Potentials to Predict Bond Dissociation Energies

Speaker: Elena Gelzinyte (Fritz Haber Institute of the Max Planck Society)

14:30-14:40 CDT
Q&A
14:40-15:10 CDT
Coffee Break
15:10-15:40 CDT
TBA

Speaker: TBA

15:40-15:50 CDT
Q&A
Friday, April 12, 2024
9:00-9:45 CDT
Sampling Complex Energy Landscapes in Material Science Using Data-Driven Force Fields

Speaker: Cosmin Marinica (CEA)

9:45-10:00 CDT
Q&A
10:00-10:30 CDT
Coffee Break
10:30-11:00 CDT
TBA

Speaker: Roman Zubatyuk (Carnegie Mellon)

11:00-11:10 CDT
Q&A
11:10-11:15 CDT
Tech Break
11:15-11:45 CDT
Ruhr-Universität Bochum

Speaker: Anton Bochkarev (Ruhr-Universität Bochum)

11:45-11:55 CDT
Q&A

Registration

Back to top

IMSI is committed to making all of our programs and events inclusive and accessible. Contact to request accommodations.

In order to register for this workshop, you must have an IMSI account and be logged in. Please use one of the buttons below to login or create an account.