Machine Learning Potentials in Molecular Dynamics Simulations articles from across Nature Portfolio

Latest Research and News

• A hybrid quantum mechanics machine learning forcefield framework for accurate solute-dislocation interaction simulations

  Solute–dislocation interactions play a central role in controlling microstructural evolution and mechanical behaviour of structural materials, yet conventional atomistic modelling approaches struggle to combine the chemical accuracy with...

  • Junting Zhang
  • Colleen Reynolds
  • Mark R. Wenman

  Article Open access 13 October 2026 npj Computational Materials
• 

  HIP: Hessian Interatomic Potentials without derivatives

  Molecular Hessians, the second derivatives of the potential energy, are fundamental to many workflows in computational chemistry. Usually, accurate Hessians are computationally expensive to calculate and scale poorly with system size, whether...

  • Andreas Burger
  • Luca Thiede
  • Alán Aspuru-Guzik

  Article Open access 13 October 2026 Nature Computational Science
• 

  Targeted fine-tuning of machine-learning interatomic potentials for phonons and phase transitions

  Machine-learning interatomic potentials are widely used as computationally efficient surrogates for density functional theory in atomistic simulations, enabling large-scale and long-time modeling of materials systems. Here, we investigate how...

  • Jonas Grandel
  • Philipp Benner
  • Janine George

  Article Open access 07 October 2026 npj Computational Materials

• OMC-bench and AtomBit-OMC: task-aligned benchmarks and robust, interpretable machine-learned interatomic potentials for organic molecular crystals

  Organic molecular crystals (OMCs) underpin key applications in pharmaceuticals and functional materials, but accurate atomistic simulation remains difficult because OMC stability depends on subtle noncovalent interactions, conformational...

  • Muyu Lu
  • Chengxi Zhao
  • Linjiang Chen

  Article Open access 21 September 2026 npj Computational Materials

• Correlating atomic structure with carrier transport in defective MoS₂ with grain boundary via machine-learned potentials

  Accurate modelling of defects in materials requires quantum-level fidelity, computational efficiency, and validation against application-relevant physical observables. Density functional theory (DFT) is reliable but prohibitively expensive for large...

  • Saurabh Kharwar
  • Andrey Vyatskikh
  • Farzan Gity

  Article Open access 15 September 2026 Communications Materials

• Accelerated stable structure prediction of Li-intercalated bilayer graphene using a data-efficient deep learning framework

  Replacing bulk graphite with few-layer graphene is a promising route toward improving both the storage capacity and rate capability of fast-charging Li-ion batteries. As the simplest layered graphene system, bilayer graphene (BLG) provides an ideal...

  • Haoran Li
  • Bilin Gui
  • Hao-Sen Chen

  Article Open access 04 September 2026 npj Computational Materials

• Field-aware and charge-informed machine learning for predicting molecular and condensed-phase responses and vibrational spectra

  External electric fields play a crucial role in chemistry, materials, and biology. However, accurately capturing external field effects remains a challenge for machine learning interatomic potentials (MLIPs). By revealing the limitations of...

  • Ke Chen
  • Sandra Luber

  Article Open access 04 September 2026 npj Computational Materials
• 

  Atomistic machine learning with irreducible Cartesian natural tensors

  Atomistic machine learning is a powerful tool for accurate and efficient investigation of material behavior at the atomic scale. While attempts have been made to construct models directly within Cartesian space, they face challenges in providing a...

  • Qun Chen
  • A. S. L. Subrahmanyam Pattamatta
  • Mingjian Wen

  Article Open access 27 August 2026 Nature Communications

• Biomolecular Multiscale Simulation (BMS25) Dataset to Train Neural Network Potentials for QM/MM Settings with Electrostatic Embedding

  Neural network potentials (NNPs) can provide insight into biological processes at atomic resolution. Training these NNPs requires large and diverse datasets of molecules, conformations, and configurations. However, so far little attention has been...

  • Moritz Thürlemann
  • Felix Pultar
  • Sereina Riniker

  Article Open access 26 August 2026 Scientific Data
• 

  Vibrational power spectra as a tool to benchmark universal machine-learning interatomic potentials for molecular systems: the OMOL-1k-MD data set

  We present OMOL-1k-MD, a new dataset for the benchmark and training of universal machine-learning interatomic potentials (uMLIPs). It contains three independent ab initio molecular dynamics (AIMD) trajectories of 10 ps each for 1000 arbitrarily...

  • Maximilian A. Bechtel
  • Julien Steffen

  Article Open access 15 August 2026 npj Computational Materials
• 

  Trajectory forecasting lifts the femtosecond ceiling in molecular simulation

  • Seyed Mohamad Moosavi

  Article 05 August 2026 Nature Machine Intelligence

• Bayesian equivariant interatomic potential with iterative restratification of many-body message passing

  Machine learning potentials (MLPs) have become essential for large-scale atomistic simulations, enabling ab initio-level accuracy with computational efficiency. However, current MLPs struggle with uncertainty quantification, limiting their...

  • Soohaeng Yoo Willow
  • Tae Hyeon Park
  • Chang Woo Myung

  Article Open access 03 August 2026 npj Computational Materials
• 

  Accurate, transferable, and verifiable machine-learned interatomic potentials for layered materials

  Twisted layered van der Waals materials often exhibit unique electronic and optical properties absent in their non-twisted counterparts. Unfortunately, predicting such properties is hindered by the difficulty in determining the atomic structure in...

  • Johnathan D. Georgaras
  • Akash Ramdas
  • Felipe H. da Jornada

  Article Open access 31 July 2026 Nature Communications

• Coarse-grained graph architectures for all-atom force predictions

  We introduce a coarse-grained all-atom force field (CGAA-FF) that integrates coarse-grained message passing into all-atom force fields using equivariant graph models. By embedding atomistic coordinates into grain-level nodes, CGAA-FF predicts...

  • Sungwoo Kang
  • Jinwoong Chae

  Article Open access 29 July 2026 npj Computational Materials
• 

  Benchmarking universal machine learning interatomic potentials on elemental systems

  The rapid emergence of universal machine learning interatomic potentials (uMLIPs) has transformed materials modeling. Nevertheless, a comprehensive understanding of their generalization behavior across configurational space remains an open...

  • Hossein Tahmasbi
  • Andreas Knüpfer
  • Hossein Mirhosseini

  Article Open access 28 July 2026 npj Computational Materials

• Phonon density of states prediction from the phonon transformer

  The phonon density of states (PhDOS) governs the lattice vibrational and thermodynamic properties of numerous crystalline materials. Traditional approaches to obtaining the PhDOS, including experimental measurements and density functional theory...

  • Shang Xu
  • Tongyi Zhang
  • Wei Ren

  Article Open access 21 July 2026 npj Computational Materials

• Budget-constrained augmentation of universal interatomic potentials for reliable multicomponent molecular dynamics

  Universal machine-learning interatomic potentials (uMLIPs) enable near-DFT molecular dynamics (MD) at greatly reduced cost, yet reliability degrades in out-of-distribution (OOD) domains defined by data-sparse chemistries and nonequilibrium...

  • Hyeon-Jong Lee
  • You-Yeob Song
  • Dong-Hwa Seo

  Article Open access 21 July 2026 npj Computational Materials

• Predicting interface structure using the minima hopping method with a machine learning interatomic potential

  Predicting atomic-scale interfacial structures remains a central challenge in materials science due to their structural complexity and the difficulty of direct comparison between computational and experimental results. In this study, we present an...

  • Chang-Ti Chou
  • Menghang Wang
  • Christopher M. Wolverton

  Article Open access 15 July 2026 npj Computational Materials

• Ion-modulated structure, proton transfer, and capacitance in the Pt-water electric double layer

  The electric double layer (EDL) governs electrocatalysis, energy conversion, and storage, yet its atomic structure, capacitance, and reactivity remain elusive. Here we introduce a machine learning interatomic potential framework that incorporates...

  • Xiaoyu Wang
  • Junmin Chen
  • Bingqing Cheng

  Article Open access 14 July 2026 npj Computational Materials

• Machine learning Hamiltonian enables scalable and accurate defect calculations: the case of oxygen vacancies in amorphous SiO₂

  Point defects critically influence the properties of materials and devices, yet density functional theory (DFT) remains computationally demanding for defect supercell calculations. Machine learning interatomic potentials (MLIPs) offer high...

  • Zhenxing Dai
  • Yang Zhong
  • Shiyou Chen

  Article Open access 12 July 2026 npj Computational Materials