no code implementations • 29 May 2024 • Xiang Fu, Andrew Rosen, Kyle Bystrom, Rui Wang, Albert Musaelian, Boris Kozinsky, Tess Smidt, Tommi Jaakkola
In density functional theory, charge density is the core attribute of atomic systems from which all chemical properties can be derived.
no code implementations • 10 Jan 2024 • Jonathan Vandermause, Anders Johansson, Yucong Miao, Joost J. Vlassak, Boris Kozinsky
Here, we train four machine-learned force fields for equiatomic NiTi based on the LDA, PBE, PBEsol, and SCAN DFT functionals.
no code implementations • 20 Oct 2023 • Xiang Fu, Albert Musaelian, Anders Johansson, Tommi Jaakkola, Boris Kozinsky
When running MD, the MTS integrator then evaluates the smaller model for every time step and the larger model less frequently, accelerating simulation.
no code implementations • 24 Apr 2023 • Mgcini Keith Phuthi, Archie Mingze Yao, Simon Batzner, Albert Musaelian, Boris Kozinsky, Ekin Dogus Cubuk, Venkatasubramanian Viswanathan
The properties of lithium metal are key parameters in the design of lithium ion and lithium metal batteries.
1 code implementation • 20 Apr 2023 • Albert Musaelian, Anders Johansson, Simon Batzner, Boris Kozinsky
This work brings the leading accuracy, sample efficiency, and robustness of deep equivariant neural networks to the extreme computational scale.
1 code implementation • 17 Nov 2022 • Albert Zhu, Simon Batzner, Albert Musaelian, Boris Kozinsky
This incurs a large computational overhead in both training and prediction that often results in order-of-magnitude more expensive predictions.
3 code implementations • 13 May 2022 • Ilyes Batatia, Simon Batzner, Dávid Péter Kovács, Albert Musaelian, Gregor N. C. Simm, Ralf Drautz, Christoph Ortner, Boris Kozinsky, Gábor Csányi
The rapid progress of machine learning interatomic potentials over the past couple of years produced a number of new architectures.
3 code implementations • 11 Apr 2022 • Albert Musaelian, Simon Batzner, Anders Johansson, Lixin Sun, Cameron J. Owen, Mordechai Kornbluth, Boris Kozinsky
This work introduces Allegro, a strictly local equivariant deep learning interatomic potential that simultaneously exhibits excellent accuracy and scalability of parallel computation.
no code implementations • 11 Mar 2021 • Natalya S. Fedorova, Andrea Cepellotti, Boris Kozinsky
The Seebeck coefficient and electrical conductivity are two critical quantities to optimize simultaneously in designing thermoelectric materials, and they are determined by the dynamics of carrier scattering.
Materials Science
2 code implementations • 8 Jan 2021 • Simon Batzner, Albert Musaelian, Lixin Sun, Mario Geiger, Jonathan P. Mailoa, Mordechai Kornbluth, Nicola Molinari, Tess E. Smidt, Boris Kozinsky
This work presents Neural Equivariant Interatomic Potentials (NequIP), an E(3)-equivariant neural network approach for learning interatomic potentials from ab-initio calculations for molecular dynamics simulations.
no code implementations • 7 Dec 2020 • Lixin Sun, Jonathan Vandermause, Simon Batzner, Yu Xie, David Clark, Wei Chen, Boris Kozinsky
Computing accurate reaction rates is a central challenge in computational chemistry and biology because of the high cost of free energy estimation with unbiased molecular dynamics.
3 code implementations • 26 Aug 2020 • Yu Xie, Jonathan Vandermause, Lixin Sun, Andrea Cepellotti, Boris Kozinsky
We present a way to dramatically accelerate Gaussian process models for interatomic force fields based on many-body kernels by mapping both forces and uncertainties onto functions of low-dimensional features.
1 code implementation • 5 Nov 2019 • Kayahan Saritas, Eric R. Fadel, Boris Kozinsky, Jeffrey C. Grossman
Electronic structure of layered LiNiO2 has been controversial despite numerous theoretical and experimental reports regarding its nature.
Materials Science
no code implementations • 7 May 2019 • Jonathan P. Mailoa, Mordechai Kornbluth, Simon L. Batzner, Georgy Samsonidze, Stephen T. Lam, Chris Ablitt, Nicola Molinari, Boris Kozinsky
Neural network force field (NNFF) is a method for performing regression on atomic structure-force relationships, bypassing expensive quantum mechanics calculation which prevents the execution of long ab-initio quality molecular dynamics simulations.
1 code implementation • 3 Apr 2019 • Jonathan Vandermause, Steven B. Torrisi, Simon Batzner, Alexie M. Kolpak, Boris Kozinsky
Machine learning based interatomic potentials currently require manual construction of training sets consisting of thousands of first principles calculations and are often restricted to single-component and nonreactive systems.
Computational Physics Materials Science
1 code implementation • 25 Nov 2015 • Georgy Samsonidze, Boris Kozinsky
Recent discovery of new materials for thermoelectric energy conversion is enabled by efficient prediction of materials' performance from first-principles, without empirically fitted parameters.
Materials Science