mlsanityData to 14 Oct 2026

Machine-learning-accelerated simulations to enable automatic surface reconstruction

arXiv 2305.07251 ↗First posted 12 May 2023cond-mat.mtrl-sci cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Understanding material surfaces and interfaces is vital in applications like catalysis or electronics. By combining energies from electronic structure with statistical mechanics, ab initio simulations can in principle predict the structure of material surfaces as a function of thermodynamic variables. However, accurate energy simulations are prohibitive when coupled to the vast phase space that must be statistically sampled. Here, we present a bi-faceted computational loop to predict surface phase diagrams of multi-component materials that accelerates both the energy scoring and statistical sampling methods. Fast, scalable, and data-efficient machine learning interatomic potentials are trained on high-throughput density-functional theory calculations through closed-loop active learning. Markov-chain Monte Carlo sampling in the semi-grand canonical ensemble is enabled by using virtual surface sites. The predicted surfaces for GaN(0001), Si(111), and SrTiO3(001) are in agreement with past work and suggest that the proposed strategy can model complex material surfaces and discover previously unreported surface terminations.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 9 of its 76 references that are in the map. First posted on arXiv 12 May 2023.

Builds on

9 of 76 references.

References · 9

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  3. 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 255
  4. 2020Machine Learning Force Fieldscited by 207
  5. 2022Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulationscited by 95
  6. 2023Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensemblescited by 30
  7. 2017Practical Bayesian optimization in the presence of outlierscited by 25
  8. 2021Differentiable sampling of molecular geometries with uncertainty-based adversarial attackscited by 25
  9. 2022Atomistic structure search using local surrogate modecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 2; 2026: 3.

8 papers.

  1. 2023Higher-Order Equivariant Neural Networks for Charge Density Prediction in Materialscited by 13
  2. 2025DistMLIP: A Distributed Inference Platform for Machine Learning Interatomic Potentialscited by 5
  3. 2026Scaling Autoregressive Models for Lattice Thermodynamicscited by 5
  4. 2024Active learning of Boltzmann samplers and potential energies with quantum mechanical accuracycited by 2
  5. 2026Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twincited by 2
  6. 2023Accelerating the prediction of inorganic surfaces with machine learning interatomic potentialscited by 1
  7. 2025Accelerating and enhancing thermodynamic simulations of electrochemical interfacescited by 1
  8. 2026Universal Thermodynamic Interatomic Potentials for Crystalline Materialscited by 0