English
Related papers

Related papers: Does Hessian Data Improve the Performance of Machi…

200 papers

Many materials properties depend on higher-order derivatives of the potential energy surface, yet machine learned interatomic potentials (MLIPs) trained with a standard loss on energy, force, and stress errors can exhibit error in…

Materials Science · Physics 2026-01-30 Teddy Koker , Abhijeet Gangan , Mit Kotak , Jaime Marian , Tess Smidt

An adaptive physics-inspired model design strategy for machine-learning interatomic potentials (MLIPs) is proposed. This strategy relies on iterative reconfigurations of composite models from single-term models, followed by a unified…

Materials Science · Physics 2026-02-27 Weishi Wang , Mark K. Transtrum , Vincenzo Lordi , Vasily V. Bulatov , Amit Samanta

Access to the potential energy Hessian enables determination of the Gibbs free energy, and certain approaches to transition state search and optimization. Here, we demonstrate that off-the-shelf pretrained Open Catalyst Project (OCP)…

Materials Science · Physics 2024-10-08 Brook Wander , Joseph Musielewicz , Raffaele Cheula , John R. Kitchin

We train an equivariant machine learning model to predict energies and forces for a real-world study of hydrogen combustion under conditions of finite temperature and pressure. This challenging case for reactive chemistry illustrates that…

Chemical Physics · Physics 2023-06-16 Xingyi Guan , Joseph Heindel , Taehee Ko , Chao Yang , Teresa Head-Gordon

Machine learning interatomic potentials (MLIPs) have massively changed the field of atomistic modeling. They enable the accuracy of density functional theory in large-scale simulations while being nearly as fast as classical interatomic…

Materials Science · Physics 2025-12-03 Niklas Leimeroth , Linus C. Erhard , Karsten Albe , Jochen Rohrer

Machine-learning interatomic potentials (MLIPs) have enabled molecular dynamics at near ab initio accuracy, yet remain limited to energies and forces by construction, leaving electronic observables such as dipole moments and…

A central pursuit in theoretical chemistry is the accurate simulation of photochemical reactions, which are governed by nonadiabatic transitions through conical intersections. Machine learning has emerged as a transformative tool for…

Machine-learning interatomic potentials (MLIPs) have greatly extended the reach of atomic-scale simulations, offering the accuracy of first-principles calculations at a fraction of the cost. Leveraging large quantum mechanical databases and…

Machine-learned interatomic potentials (MLIPs) are typically trained on datasets that encompass a restricted subset of possible input structures, which presents a potential challenge for their generalization to a broader range of systems…

Computational Physics · Physics 2023-11-06 Yangshuai Wang , Shashwat Patel , Christoph Ortner

Machine learning interatomic potentials (MLIPs) can predict energy, force, and stress of materials and enable a wide range of downstream discovery tasks. A key design choice in MLIPs involves the trade-off between invariant and equivariant…

The promise of machine learning interatomic potentials (MLIPs) has led to an abundance of public quantum mechanical (QM) training datasets. The quality of an MLIP is directly limited by the accuracy of the energies and atomic forces in the…

Accurate molecular property predictions require 3D geometries, which are typically obtained using expensive methods such as density functional theory (DFT). Here, we attempt to obtain molecular geometries by relying solely on machine…

Machine-Learning Interatomic Potentials (MLIPs) have surged in popularity due to their promise of expanding the spatiotemporal scales possible for simulating molecules with high fidelity. The accuracy of any MLIP is dependent on the data…

Soft Condensed Matter · Physics 2026-02-27 Natalie E. Hooven , Arthur Y. Lin , Charles H. Carroll , Rose K. Cersonsky

Foundational machine learning interatomic potentials (MLIPs) are being developed at a rapid pace, promising closer and closer approximation to ab initio accuracy. This unlocks the possibility to simulate much larger length and time scales.…

Materials Science · Physics 2026-05-27 Luuk H. E. Kempen , Raffaele Cheula , Mie Andersen

The use of machine learning interatomic potentials (MLIPs) in simulations of materials is a state-of-the-art approach, which allows achieving nearly \textit{ab initio} accuracy with orders of magnitude less computational cost.…

Materials Science · Physics 2021-10-28 R. E. Ryltsev , N. M. Chtchelkatchev

Fundamental tasks in computational chemistry, from transition state search to vibrational analysis, rely on molecular Hessians, which are the second derivatives of the potential energy. Yet, Hessians are computationally expensive to…

Machine learning interatomic potentials (MLIPs) based on a large dataset obtained by density functional theory (DFT) calculation have been developed recently. This study gives both conceptual and practical bases for the high accuracy of…

Materials Science · Physics 2017-11-08 Akira Takahashi , Atsuto Seko , Isao Tanaka

Machine-learning interatomic potentials (MLIPs) enable large-scale atomistic simulations at moderate computational cost while retaining ab initio accuracy. MLIPs trained on coupled-cluster data, particularly CCSD(T), have emerged as a…

Materials Science · Physics 2026-03-11 Yuji Ikeda , Axel Forslund , Pranav Kumar , Yongliang Ou , Jong Hyun Jung , Andreas Köhn , Blazej Grabowski

Machine learning interatomic potentials (MLIPs) are one of the main techniques in the materials science toolbox, able to bridge ab initio accuracy with the computational efficiency of classical force fields. This allows simulations ranging…

Materials Science · Physics 2025-03-20 Bruno Focassio , Luis Paulo Mezzina Freitas , Gabriel R. Schleder

Machine-learned interatomic potentials (MLIPs) are increasingly used to replace computationally demanding electronic-structure calculations to model matter at the atomic scale. The most commonly used model architectures are constrained to…

Chemical Physics · Physics 2026-03-30 Filippo Bigi , Paolo Pegolo , Arslan Mazitov , Jonathan Schmidt , Michele Ceriotti