Interatomic Potential

Interatomic potentials are mathematical functions describing the energy of a system of atoms as a function of their positions, serving as the foundation for atomistic simulations. Current research heavily emphasizes machine learning approaches, particularly graph neural networks and other equivariant architectures, to create accurate and computationally efficient potentials, often focusing on improving data efficiency, handling long-range interactions, and ensuring robustness and generalizability across diverse materials. These advancements significantly accelerate materials discovery and design by enabling large-scale simulations previously intractable with traditional methods, impacting fields ranging from materials science to drug discovery.

Papers

February 12, 2024

Cartesian atomic cluster expansion for machine learning interatomic potentials
Bingqing Cheng
New Machine Interatomic Potential Atomistic Simulation Formal Logic Atomic Cluster Expansion

February 6, 2024

Enhanced sampling of robust molecular datasets with uncertainty-based collective variables
Aik Rui Tan, Johannes C. B. Dietschreit, Rafael Gomez-Bombarelli
Molecular Data Interatomic Potential Chemical Data Molecular System Potential Energy Surface Enhanced Sampling Collective Variable

December 18, 2023

Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials
Kyle Noordhoek, Christopher J. Bartel
Human Prediction New Machine Object Surface First Principle Interatomic Potential Phase Diagram Inorganic Material

October 30, 2023

Role of Structural and Conformational Diversity for Machine Learning Potentials
Nikhil Shenoy, Prudencio Tossou, Emmanuel Noutahi, Hadrien Mary, Dominique Beaini, Jiarui Ding
Integral Role Inner Structure Molecular Conformation Chemical Space Interatomic Potential Machine Learning Potential

October 20, 2023

Learning Interatomic Potentials at Multiple Scales
Xiang Fu, Albert Musaelian, Anders Johansson, Tommi Jaakkola, Boris Kozinsky
Interatomic Potential Electronic Structure Long Range Interaction

October 4, 2023

Spline-based neural network interatomic potentials: blending classical and machine learning models
Joshua A. Vita, Dallas R. Trinkle
Machine Learning Model First Principle Interatomic Potential Spline Based

September 27, 2023

C3Net: interatomic potential neural network for prediction of physicochemical properties in heterogenous systems
Sehan Lee, Jaechang Lim, Woo Youn Kim
Human Prediction Free Energy Interatomic Potential Atomic Resolution

August 17, 2023

Accurate machine learning force fields via experimental and simulation data fusion
Sebastien Röcken, Julija Zavadlav
Data Driven Multidimensional Local Precision Rate Force Field Interatomic Potential Density Functional Theory Molecular Modeling Machine Learning Potential

July 24, 2023

June 23, 2023

Accurate melting point prediction through autonomous physics-informed learning
Olga Klimanova, Timofei Miryashkin, Alexander Shapeev
Physic Informed Interatomic Potential Melting Point Phase Boundary

June 12, 2023

June 2, 2023

Transfer learning for atomistic simulations using GNNs and kernel mean embeddings
John Falk, Luigi Bonati, Pietro Novelli, Michele Parrinello, Massimiliano Pontil
Graph Neural Network Formality Transfer Interatomic Potential Atomistic Simulation Chemical Data Potential Energy Surface Kernel Mean Embeddings

May 19, 2023

PANNA 2.0: Efficient neural network interatomic potentials and new architectures
Franco Pellegrini, Ruggero Lot, Yusuf Shaidu, Emine Küçükbenli
Neural Architecture Interatomic Potential Efficient Neural Network Novel Architecture Long Range Interaction Charge Tuning

May 10, 2023

Graph Neural Network Interatomic Potential Ensembles with Calibrated Aleatoric and Epistemic Uncertainty on Energy and Forces
Jonas Busk, Mikkel N. Schmidt, Ole Winther, Tejs Vegge, Peter Bjørn Jørgensen
Epistemic Uncertainty Molecular Dynamic Aleatoric Uncertainty Energy Policy Research Uncertainty Calibration Interatomic Potential External Human Force Non Gaussian Aleatoric Uncertainty

May 2, 2023

Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles
Aik Rui Tan, Shingo Urata, Samuel Goldman, Johannes C. B. Dietschreit, Rafael Gómez-Bombarelli
Uncertainty Quantification Interatomic Potential Atomistic Simulation Model Ensemble Neural Network Potential Based NIDS

February 28, 2023

CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling
Bowen Deng, Peichen Zhong, KyuJung Jun, Janosh Riebesell, Kevin Han, Christopher J. Bartel, Gerbrand Ceder
Force Field Interatomic Potential Atomistic Simulation Neural Network Potential Crystal Graph

February 12, 2023

Data efficiency and extrapolation trends in neural network interatomic potentials
Joshua A. Vita, Daniel Schwalbe-Koda
Neural Network Interatomic Potential Trend Extrapolation Data Efficiency Extrapolation Performance Based NIDS

November 30, 2022

Capturing long-range interaction with reciprocal space neural network
Hongyu Yu, Liangliang Hong, Shiyou Chen, Xingao Gong, Hongjun Xiang
Neural Network Long Term Interatomic Potential Long Range Interaction

Interatomic Potential

Papers

Cartesian atomic cluster expansion for machine learning interatomic potentials

Enhanced sampling of robust molecular datasets with uncertainty-based collective variables

Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials

Role of Structural and Conformational Diversity for Machine Learning Potentials

Learning Interatomic Potentials at Multiple Scales

Spline-based neural network interatomic potentials: blending classical and machine learning models

C3Net: interatomic potential neural network for prediction of physicochemical properties in heterogenous systems

Accurate machine learning force fields via experimental and simulation data fusion

Interpretable Ensemble Learning for Materials Property Prediction with Classical Interatomic Potentials: Carbon as an Example

Synthetic pre-training for neural-network interatomic potentials

Accurate melting point prediction through autonomous physics-informed learning

Reliable machine learning potentials based on artificial neural network for graphene

Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction

Transfer learning for atomistic simulations using GNNs and kernel mean embeddings

PANNA 2.0: Efficient neural network interatomic potentials and new architectures

Graph Neural Network Interatomic Potential Ensembles with Calibrated Aleatoric and Epistemic Uncertainty on Energy and Forces

Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles

CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling

Data efficiency and extrapolation trends in neural network interatomic potentials

Capturing long-range interaction with reciprocal space neural network