Applications of machine learning in surfaces and interfaces DOI Open Access
Shaofeng Xu, Jing‐Yuan Wu, Ying Guo

et al.

Chemical Physics Reviews, Journal Year: 2025, Volume and Issue: 6(1)

Published: March 1, 2025

Surfaces and interfaces play key roles in chemical material science. Understanding physical processes at complex surfaces is a challenging task. Machine learning provides powerful tool to help analyze accelerate simulations. This comprehensive review affords an overview of the applications machine study systems materials. We categorize into following broad categories: solid–solid interface, solid–liquid liquid–liquid surface solid, liquid, three-phase interfaces. High-throughput screening, combined first-principles calculations, force field accelerated molecular dynamics simulations are used rational design such as all-solid-state batteries, solar cells, heterogeneous catalysis. detailed information on for

Language: Английский

Perspective: Atomistic simulations of water and aqueous systems with machine learning potentials DOI Creative Commons
Amir Omranpour, Pablo Montero de Hijes, Jörg Behler

et al.

The Journal of Chemical Physics, Journal Year: 2024, Volume and Issue: 160(17)

Published: May 1, 2024

As the most important solvent, water has been at center of interest since advent computer simulations. While early molecular dynamics and Monte Carlo simulations had to make use simple model potentials describe atomic interactions, accurate ab initio relying on first-principles calculation energies forces have opened way predictive aqueous systems. Still, these are very demanding, which prevents study complex systems their properties. Modern machine learning (MLPs) now reached a mature state, allowing us overcome limitations by combining high accuracy electronic structure calculations with efficiency empirical force fields. In this Perspective, we give concise overview about progress made in simulation employing MLPs, starting from work free molecules clusters via bulk liquid electrolyte solutions solid–liquid interfaces.

Language: Английский

Citations

20
Molecular dynamics simulations of heat transport using machine-learned potentials: A mini-review and tutorial on GPUMD with neuroevolution potentials DOI Creative Commons
Haikuan Dong,

Yongbo Shi,

Penghua Ying

et al.

Journal of Applied Physics, Journal Year: 2024, Volume and Issue: 135(16)

Published: April 24, 2024

Molecular dynamics (MD) simulations play an important role in understanding and engineering heat transport properties of complex materials. An essential requirement for reliably predicting is the use accurate efficient interatomic potentials. Recently, machine-learned potentials (MLPs) have shown great promise providing required accuracy a broad range In this mini-review tutorial, we delve into fundamentals transport, explore pertinent MD simulation methods, survey applications MLPs transport. Furthermore, provide step-by-step tutorial on developing highly predictive simulations, utilizing neuroevolution as implemented GPUMD package. Our aim with to empower researchers valuable insights cutting-edge methodologies that can significantly enhance efficiency studies.

Language: Английский

Citations

14
From the Automated Calculation of Potential Energy Surfaces to Accurate Infrared Spectra DOI Creative Commons
Benjamin Schröder, Guntram Rauhut

The Journal of Physical Chemistry Letters, Journal Year: 2024, Volume and Issue: 15(11), P. 3159 - 3169

Published: March 13, 2024

Advances in the development of quantum chemical methods and progress multicore architectures computer science made simulation infrared spectra isolated molecules competitive with respect to established experimental methods. Although it is mainly multidimensional potential energy surface that controls accuracy these calculations, subsequent vibrational structure calculations need be carefully converged order yield accurate results. As both aspects considered a balanced way, we focus on approaches for up 12–15 atoms parts, which have been automated some extent so they can employed routine applications. Alternatives machine learning will discussed, appear attractive, as long local regions are sufficient. The automatization still its infancy, generalization large amplitude motions or molecular clusters far from trivial, but many systems relevant astrophysical studies already reach.

Language: Английский

Citations

11
An overview about neural networks potentials in molecular dynamics simulation DOI
Raidel Martin‐Barrios, Edisel Navas‐Conyedo, Xuyi Zhang

et al.

International Journal of Quantum Chemistry, Journal Year: 2024, Volume and Issue: 124(11)

Published: May 21, 2024

Abstract Ab‐initio molecular dynamics (AIMD) is a key method for realistic simulation of complex atomistic systems and processes in nanoscale. In AIMD, finite‐temperature dynamical trajectories are generated by using forces computed from electronic structure calculations. with high numbers components typical AIMD run computationally demanding. On the other hand, machine learning (ML) subfield artificial intelligence that consist set algorithms show experience use input output data where capable analysing predicting future. At present, main application ML techniques atomic simulations development new interatomic potentials to correctly describe potential energy surfaces (PES). This technique constant progress since its inception around 30 years ago. The combine advantages classical methods, is, efficiency simple functional form accuracy first principles this article we review evolution four generations some their most notable applications. focuses on MLPs based neural networks. Also, present state art topic future trends. Finally, report results scientometric study (covering period 1995–2023) about impact applied simulations, distribution publications geographical regions hot topics investigated literature.

Language: Английский

Citations

11
The emergence of machine learning force fields in drug design DOI
Mingan Chen, Xinyu Jiang,

Lehan Zhang

et al.

Medicinal Research Reviews, Journal Year: 2024, Volume and Issue: 44(3), P. 1147 - 1182

Published: Jan. 3, 2024

In the field of molecular simulation for drug design, traditional mechanic force fields and quantum chemical theories have been instrumental but limited in terms scalability computational efficiency. To overcome these limitations, machine learning (MLFFs) emerged as a powerful tool capable balancing accuracy with MLFFs rely on relationship between structures potential energy, bypassing need preconceived notion interaction representations. Their depends models used, quality volume training data sets. With recent advances equivariant neural networks high-quality datasets, significantly improved their performance. This review explores MLFFs, emphasizing design. It elucidates MLFF principles, provides development validation guidelines, highlights successful implementations. also addresses challenges developing applying MLFFs. The concludes by illuminating path ahead outlining to be opportunities harnessed. inspires researchers embrace investigations new perform simulations

Language: Английский

Citations

9
New Algorithms to Generate Permutationally Invariant Polynomials and Fundamental Invariants for Potential Energy Surface Fitting DOI
Yiping Hao, Xiaoxiao Lu, Bina Fu

et al.

Journal of Chemical Theory and Computation, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 22, 2025

Symmetric functions, such as Permutationally Invariant Polynomials (PIPs) and Fundamental Invariants (FIs), are effective concise descriptors for incorporating permutation symmetry into neural network (NN) potential energy surface (PES) fitting. The traditional algorithm generating symmetric polynomials has a factorial time complexity of N!, where N is the number identical atoms, posing significant challenge to applying NN PESs larger systems, particularly with more than 10 atoms. Herein, we report new which only linear It can tremendously accelerate generation process molecular systems. proposed based on graph connectivity analysis following action set permutational group. For instance, in case calculating invariant 15-atom molecule, tropolone, our approximately 2 million times faster previous method. efficiency be further enhanced increasing size making FI-NN approach feasible systems over atoms high demands.

Language: Английский

Citations

1
AI in computational chemistry through the lens of a decade-long journey DOI Creative Commons
Pavlo O. Dral

Chemical Communications, Journal Year: 2024, Volume and Issue: 60(24), P. 3240 - 3258

Published: Jan. 1, 2024

This article gives a perspective on the progress of AI tools in computational chemistry through lens author's decade-long contributions put wider context trends this rapidly expanding field. over last decade is tremendous: while ago we had glimpse what was to come many proof-of-concept studies, now witness emergence AI-based that are mature enough make faster and more accurate simulations increasingly routine. Such turn allow us validate even revise experimental results, deepen our understanding physicochemical processes nature, design better materials, devices, drugs. The rapid introduction powerful rise unique challenges opportunities discussed too.

Language: Английский

Citations

7
ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials DOI Creative Commons
Rolf David, Miguel de la Puente, Axel Gomez

et al.

Digital Discovery, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

ArcaNN is a comprehensive framework that employs concurrent learning to generate training datasets for reactive MLIPs in the condensed phase.

Language: Английский

Citations

7
Physics-Informed Active Learning for Accelerating Quantum Chemical Simulations DOI

Yi-Fan Hou,

Lina Zhang, Quanhao Zhang

et al.

Journal of Chemical Theory and Computation, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 12, 2024

Quantum chemical simulations can be greatly accelerated by constructing machine learning potentials, which is often done using active (AL). The usefulness of the constructed potentials limited high effort required and their insufficient robustness in simulations. Here, we introduce end-to-end AL for robust data-efficient with affordable investment time resources minimum human interference. Our protocol based on physics-informed sampling training points, automatic selection initial data, uncertainty quantification, convergence monitoring. versatility this shown our implementation quasi-classical molecular dynamics simulating vibrational spectra, conformer search a key biochemical molecule, time-resolved mechanism Diels-Alder reaction. These investigations took us days instead weeks pure quantum calculations high-performance computing cluster.

Language: Английский

Citations

6
Ab initio dispersion potentials based on physics-based functional forms with machine learning DOI Creative Commons
Corentin Villot, Ka Un Lao

The Journal of Chemical Physics, Journal Year: 2024, Volume and Issue: 160(18)

Published: May 8, 2024

In this study, we introduce SAPT10K, a comprehensive dataset comprising 9982 noncovalent interaction energies and their binding energy components (electrostatics, exchange, induction, dispersion) for diverse intermolecular complexes of 944 unique dimers. These cover significant portions the potential surface were computed using higher-order symmetry-adapted perturbation theory, SAPT2+(3)(CCD), with large aug-cc-pVTZ basis set. The dispersion values in SAPT10K serve as crucial inputs refining ab initio potentials based on Grimme's D3 many-body (MBD) models. Additionally, Δ machine learning (ML) models newly developed features, which are derived from histograms distances element/substructure pairs to simultaneously account local environments well long-range correlations, also address deficiencies D3/MBD models, including inflexibility functional forms, absence MBD contributions D3, standard Hirshfeld partitioning scheme used MBD. can be applied involving wide range elements charged monomers, surpassing other popular ML limited systems only neutral monomers specific elements. efficient D3-ML model, Cartesian coordinates sole input, demonstrates promising results testing set 6714 dimers, outperforming another component-based machine-learned force field (CLIFF), by 1.5 times. refined D3/MBD-ML have capability replace time-consuming theory-based calculations promptly illustrate contribution supramolecular assembly chemical reactions.

Language: Английский

Citations

5