Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Jonathan Vandermause"'
Publikováno v:
npj Computational Materials, Vol 10, Iss 1, Pp 1-12 (2024)
Abstract Coarse graining techniques play an essential role in accelerating molecular simulations of systems with large length and time scales. Theoretically grounded bottom-up models are appealing due to their thermodynamic consistency with the under
Externí odkaz:
https://doaj.org/article/b4722b8247ad48e2bc048925c759f47e
Autor:
Yu Xie, Jonathan Vandermause, Senja Ramakers, Nakib H. Protik, Anders Johansson, Boris Kozinsky
Publikováno v:
npj Computational Materials, Vol 9, Iss 1, Pp 1-8 (2023)
Abstract Machine learning interatomic force fields are promising for combining high computational efficiency and accuracy in modeling quantum interactions and simulating atomistic dynamics. Active learning methods have been recently developed to trai
Externí odkaz:
https://doaj.org/article/59458cb3a493432699e07912a032e97c
Publikováno v:
Nature Communications, Vol 13, Iss 1, Pp 1-12 (2022)
Uncertainty-aware machine learning models are used to automate the training of reactive force fields. The method is used here to simulate hydrogen turnover on a platinum surface with unprecedented accuracy.
Externí odkaz:
https://doaj.org/article/4fdade2ecf7f418689a47025b578bb55
Autor:
Cheol Woo Park, Mordechai Kornbluth, Jonathan Vandermause, Chris Wolverton, Boris Kozinsky, Jonathan P. Mailoa
Publikováno v:
npj Computational Materials, Vol 7, Iss 1, Pp 1-9 (2021)
Abstract Recently, machine learning (ML) has been used to address the computational cost that has been limiting ab initio molecular dynamics (AIMD). Here, we present GNNFF, a graph neural network framework to directly predict atomic forces from autom
Externí odkaz:
https://doaj.org/article/69d11dd21aef4871997919972e929e7b
Publikováno v:
npj Computational Materials, Vol 7, Iss 1, Pp 1-10 (2021)
Abstract 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. This allows for automated active
Externí odkaz:
https://doaj.org/article/f04a0cef3d874031836d2287821283f8
Coarse graining techniques play an essential role in accelerating molecular simulations of systems with large length and time scales. Theoretically grounded bottom-up models are appealing due to their thermodynamic consistency with the underlying all
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1968827d303f0b33f02da1e2d3315098
https://doi.org/10.21203/rs.3.rs-2214639/v1
https://doi.org/10.21203/rs.3.rs-2214639/v1
Machine learning interatomic force fields are promising for combining high computational efficiency and accuracy in modeling quantum interactions and simulating atomic level processes. Active learning methods have been recently developed to train for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b15f89eb37c058fa0cc0a5eddb148b8
https://doi.org/10.21203/rs.3.rs-1606203/v1
https://doi.org/10.21203/rs.3.rs-1606203/v1
Autor:
Lixin Sun, Jonathan Vandermause, Simon Batzner, Yu Xie, David Clark, Wei Chen, Boris Kozinsky
Publikováno v:
Journal of chemical theory and computation. 18(4)
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. In this work, a data-driven machine learning algorithm is devised to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::45d755cdf9192a9c2820e9df9fe87c04
https://pubmed.ncbi.nlm.nih.gov/35274958
https://pubmed.ncbi.nlm.nih.gov/35274958
Autor:
Yu Xie, Jonathan Vandermause, Senja Ramakers, Nakib H. Protik, Anders Johansson, Boris Kozinsky
Machine learning interatomic force fields are promising for combining high computational efficiency and accuracy in modeling quantum interactions and simulating atomistic dynamics. Active learning methods have been recently developed to train force f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe29903a8ebfc0dfbf391e55c3974b53
Atomistic modeling of chemically reactive systems has so far relied on either expensive ab initio methods or bond-order force fields requiring arduous parametrization. Here, we describe a Bayesian active learning framework for autonomous ``on-the-fly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e359ca7665948dbbecc5d42bce0b21a
https://doi.org/10.21203/rs.3.rs-1178160/v1
https://doi.org/10.21203/rs.3.rs-1178160/v1