Machine Learning of Molecules and Materials: Materials II

Presentations

• Exploring equivariant models for electronic properties

  ORAL · Invited

  March 7, 2024, 11:30 AM – March 7, 2024, 12:06 PM

  Presenters

  • Mihail Bogojeski

    • TU Berlin

  Authors

  • Klaus-Robert Muller

    • TU Berlin

  • Mihail Bogojeski

    • TU Berlin

  View abstract →

• Neural Network Backflow for ab initio quantum chemistry in second quantization

  ORAL

  March 7, 2024, 12:06 PM – March 7, 2024, 12:18 PM

  Presenters

  • An-Jun Liu

    • University of Illinois Urbana-Champaign

  Authors

  • An-Jun Liu

    • University of Illinois Urbana-Champaign

  • Bryan K Clark

    • University of Illinois at Urbana-Champaign

  View abstract →

• Avoiding a reproducibility crisis in deep learning for surrogate potentials: How massively parallel programming, millions of training steps, and numerics combine to create non-determinism in models and what this means for the simulated physics

  ORAL

  March 7, 2024, 12:18 PM – March 7, 2024, 12:30 PM

  Publication: Coletti M, Sedova A, Chahal R, Gibson L, Roy S, Bryantsev V. Multiobjective Hyperparameter Optimization for Deep Learning Interatomic Potential Training Using NSGA-II. In: Proceedings of the 52nd International Conference on Parallel Processing Workshops 2023 Aug 7 (pp. 172-179).
  Planned work: Understanding numerical reproducibility in training and application of deep learning surrogate potentials for physics

  Presenters

  • Ada Sedova

    • Oak Ridge National Laboratory

  Authors

  • Ada Sedova

    • Oak Ridge National Laboratory

  • Ganesh Sivaraman

    • Argonne National Laboratory

  • Mark Coletti

    • Oak Ridge National Laboratory

  • Wael Elwasif

    • Oak Ridge National Laboratory

  • Micholas D Smith

    • University of Tennessee, Knoxville

  • Oscar Hernandez

    • Oak Ridge National Laboratory

  View abstract →

• Free energy simulations with machine learning-based forcefields for prediction of thermodynamic properties of molten salts

  ORAL

  March 7, 2024, 12:30 PM – March 7, 2024, 12:42 PM

  Publication: Several papers are in preparations at this stage, 1-2 papers will be submitted by the time of presentation

  Presenters

  • Vyacheslav Bryantsev

    • Oak Ridge National Laboratory
    • Oak Ridge National Lab
    • OaK Ridge National Lab

  Authors

  • Vyacheslav Bryantsev

    • Oak Ridge National Laboratory
    • Oak Ridge National Lab
    • OaK Ridge National Lab

  • Luke D Gibson

    • Oak Ridge National Laboratory

  • Rajni Chahal

    • Oak Ridge National Laboratory

  • Santanu Roy

    • Oak Ridge National Laboratory
    • Oak Ridge National Lab

  View abstract →

• JARVIS-Leaderboard: Large Scale Benchmark of Materials Design Methods

  ORAL

  March 7, 2024, 12:42 PM – March 7, 2024, 12:54 PM

  Presenters

  • Kamal Choudhary

    • National Institute of Standards and Tech

  Authors

  • Kamal Choudhary

    • National Institute of Standards and Tech

  View abstract →

• First-principles study of THz dielectric properties of liquid molecules with a machine learning model for dipole moments

  ORAL

  March 7, 2024, 12:54 PM – March 7, 2024, 1:06 PM

  Publication: "34th IUPAP Conference on Computational Physics" Springer Proceedings in Physics, submitted.

  Presenters

  • Tomohito Amano

    • Univ of Tokyo

  Authors

  • Tomohito Amano

    • Univ of Tokyo

  • Yamazaki Tamio

    • JSR Corporation

  • Shinji Tsuneyuki

    • The university of Tokyo

  View abstract →

• Machine learning molecular conformational energies using semi-local density fingerprints

  ORAL

  March 7, 2024, 1:06 PM – March 7, 2024, 1:18 PM

  Presenters

  • Yang Yang

    • Cornell University

  Authors

  • Yang Yang

    • Cornell University

  • Zachary M Sparrow

    • Cornell University

  • Brian G Ernst

    • Cornell University

  • Trine K Quady

    • Cornell University

  • Zhuofan Shen

    • Cornell University

  • Richard Kang

    • Cornell University
    • University of California, Berkeley

  • Justin Lee

    • Cornell University

  • Yan Yang

    • Cornell University

  • Lijie Tu

    • Cornell University

  • Robert A Distasio

    • Cornell University

  View abstract →

• Spectroscopy of two-dimensional interacting lattice electrons using symmetry-awareneural backflow transformations

  ORAL

  March 7, 2024, 1:18 PM – March 7, 2024, 1:30 PM

  Publication: Soon to appear in arxiv:
  I. Romero, J. Nys, and G. Carleo , Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware
  neural backflow transformations
  
  Work based on :
  https://arxiv.org/pdf/2104.14869.pdf

  Presenters

  • Imelda Romero

    • École Polytechnique Fédérale de Lausanne

  Authors

  • Imelda Romero

    • École Polytechnique Fédérale de Lausanne

  • Jannes Nys

    • École Polytechnique Fédérale de Lausanne (EPFL)

  • Giuseppe Carleo

    • EPFL

  View abstract →

• Using Machine Learning to Predict the Adsorption Properties of Thiophene (C₄H₄S)

  ORAL

  March 7, 2024, 1:30 PM – March 7, 2024, 1:42 PM

  Presenters

  • Walter F Malone

    • Tuskegee University
    • Professor

  Authors

  • Walter F Malone

    • Tuskegee University
    • Professor

  • Soleil Chapman

    • Tuskegee University

  View abstract →

• Machine Learned Interatomic Potentials to Predict Solvatochromic and Stokes Shifts

  ORAL

  March 7, 2024, 1:42 PM – March 7, 2024, 1:54 PM

  Publication: -

  Presenters

  • Carlo Maino

    • Universty of Warwick

  Authors

  • Carlo Maino

    • Universty of Warwick

  • Nicholas D Hine

    • University of Warwick

  • Vasilios G Stavros

    • University of Warwick

  • Natércia Rodrigues

    • Instituto Superior Técnico

  View abstract →

• Electronic stopping power predictions from machine learning

  ORAL

  March 7, 2024, 1:54 PM – March 7, 2024, 2:06 PM

  Presenters

  • Cheng-Wei Lee

    • Colorado School of Mines

  Authors

  • Cheng-Wei Lee

    • Colorado School of Mines

  • Logan Ward

    • Argonne National Laboratory

  • Ben Blaiszik

    • University of Chicago

  • Ian Foster

    • Argonne National Laboratory

  • Andre Schleife

    • University of Illinois at Urbana-Champaign

  View abstract →

• Predicting Properties of van der Waals Magnets using Graph Neural Networks

  ORAL

  March 7, 2024, 2:06 PM – March 7, 2024, 2:18 PM

  Presenters

  • Peter Minch

    • Rensselaer Polytechnic Institute

  Authors

  • Peter Minch

    • Rensselaer Polytechnic Institute

  • Romakanta Bhattarai

    • Rensselaer Polytechnic Institute

  • Trevor David Rhone

    • Rensselaer Polytechnic Institute

  View abstract →

• Optimizing machine learning electronic structure methods based on the one-electron reduced density matrix

  ORAL

  March 7, 2024, 2:18 PM – March 7, 2024, 2:30 PM

  Publication: [1] Y. Bai, L. Vogt-Maranto, M. E. Tuckerman, and W. J. Glover. Machine learning the Hohenberg-Kohn map for molecular excited states. Nature communications, 13:7044, 2022.
  
  [2] F. Brockherde, L. Vogt, L. Li, M. E. Tuckerman, K. Burke, and K. R. Mu ̈ller. Bypassing the Kohn- Sham equations with machine learning. Nature communications, 8:872, 2017.
  
  [3] L. Fiedler, N. A. Modine, S. Schmerler, D. J. Vogel, G. A. Popoola, A. P. Thompson, S. Rajaman- ickam, and A. Cangi. Predicting electronic structures at any length scale with machine learning. npj Computational Materials, 9:115, 2023.
  
  [4] X. Shao, L. Paetow, M. E. Tuckerman, and M. Pavanello. Machine learning electronic structure methods based on the one-electron reduced density matrix. Nature Communications, 14:6281, 2023.

  Presenters

  • Nicolas J Viot

    • Rutgers University - Newark

  Authors

  • Nicolas J Viot

    • Rutgers University - Newark

  • Xuecheng Shao

    • Rutgers University - Newark

  • Michele Pavanello

    • Rutgers University - Newark

  View abstract →