DeePMD-kit v2: A software package for deep potential models

The Journal of Chemical Physics, Год журнала: 2023, Номер 159(5)

Опубликована: Авг. 1, 2023

DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials known as Deep Potential (DP) models. This package, which was released in 2017, has been widely used the fields of physics, chemistry, biology, and material science for studying atomistic systems. The current version offers numerous advanced features, such DeepPot-SE, attention-based hybrid descriptors, ability to fit tensile properties, type embedding, model deviation, DP-range correction, DP long range, graphics processing unit support customized operators, compression, non-von Neumann dynamics, improved usability, including documentation, compiled binary packages, graphical user interfaces, application programming interfaces. article presents an overview major highlighting its features technical details. Additionally, this comprehensive procedure conducting representative application, benchmarks accuracy efficiency different models, discusses ongoing developments.

Язык: Английский

---

How to validate machine-learned interatomic potentials

The Journal of Chemical Physics, Год журнала: 2023, Номер 158(12)

Опубликована: Март 2, 2023

Machine learning (ML) approaches enable large-scale atomistic simulations with near-quantum-mechanical accuracy. With the growing availability of these methods, there arises a need for careful validation, particularly physically agnostic models-that is, potentials that extract nature atomic interactions from reference data. Here, we review basic principles behind ML and their validation atomic-scale material modeling. We discuss best practice in defining error metrics based on numerical performance, as well guided validation. give specific recommendations hope will be useful wider community, including those researchers who intend to use materials "off shelf."

Язык: Английский

---

Atomistic modeling of the mechanical properties: the rise of machine learning interatomic potentials

Materials Horizons, Год журнала: 2023, Номер 10(6), С. 1956 - 1968

Опубликована: Янв. 1, 2023

This minireview highlights the superiority of machine learning interatomic potentials over conventional empirical and density functional theory calculations for analysis mechanical failure responses.

Язык: Английский

---

A “short blanket” dilemma for a state-of-the-art neural network potential for water: Reproducing experimental properties or the physics of the underlying many-body interactions?

The Journal of Chemical Physics, Год журнала: 2023, Номер 158(8)

Опубликована: Фев. 2, 2023

Deep neural network (DNN) potentials have recently gained popularity in computer simulations of a wide range molecular systems, from liquids to materials. In this study, we explore the possibility combining computational efficiency DeePMD framework and demonstrated accuracy MB-pol data-driven, many-body potential train DNN for large-scale water across its phase diagram. We find that is able reliably reproduce results liquid water, but provides less accurate description vapor-liquid equilibrium properties. This shortcoming traced back inability correctly represent interactions. An attempt explicitly include information about effects new exhibits opposite performance, being properties, losing These suggest DeePMD-based are not "learn" and, consequently, interactions, which implies may limited ability predict properties state points included training process. The can still be exploited on data-driven potentials, thus enable large-scale, "chemically accurate" various with caveat target must been adequately sampled by reference order guarantee faithful representation associated

Язык: Английский

---

Machine learning interatomic potential: Bridge the gap between small-scale models and realistic device-scale simulations

iScience, Год журнала: 2024, Номер 27(5), С. 109673 - 109673

Опубликована: Апрель 4, 2024

Machine learning interatomic potential (MLIP) overcomes the challenges of high computational costs in density-functional theory and relatively low accuracy classical large-scale molecular dynamics, facilitating more efficient precise simulations materials research design. In this review, current state four essential stages MLIP is discussed, including data generation methods, material structure descriptors, six unique machine algorithms, available software. Furthermore, applications various fields are investigated, notably phase-change memory materials, searching, properties predicting, pre-trained universal models. Eventually, future perspectives, consisting standard datasets, transferability, generalization, trade-off between complexity MLIPs, reported.

Язык: Английский

---

Recent Advances in Machine Learning‐Assisted Multiscale Design of Energy Materials

Advanced Energy Materials, Год журнала: 2024, Номер unknown

Опубликована: Дек. 10, 2024

Abstract This review highlights recent advances in machine learning (ML)‐assisted design of energy materials. Initially, ML algorithms were successfully applied to screen materials databases by establishing complex relationships between atomic structures and their resulting properties, thus accelerating the identification candidates with desirable properties. Recently, development highly accurate interatomic potentials generative models has not only improved robust prediction physical but also significantly accelerated discovery In past couple years, methods have enabled high‐precision first‐principles predictions electronic optical properties for large systems, providing unprecedented opportunities science. Furthermore, ML‐assisted microstructure reconstruction physics‐informed solutions partial differential equations facilitated understanding microstructure–property relationships. Most recently, seamless integration various platforms led emergence autonomous laboratories that combine quantum mechanical calculations, language models, experimental validations, fundamentally transforming traditional approach novel synthesis. While highlighting aforementioned advances, existing challenges are discussed. Ultimately, is expected fully integrate atomic‐scale simulations, reverse engineering, process optimization, device fabrication, empowering system design. will drive transformative innovations conversion, storage, harvesting technologies.

Язык: Английский

---

MLatom 3: A Platform for Machine Learning-Enhanced Computational Chemistry Simulations and Workflows

Journal of Chemical Theory and Computation, Год журнала: 2024, Номер 20(3), С. 1193 - 1213

Опубликована: Янв. 25, 2024

Machine learning (ML) is increasingly becoming a common tool in computational chemistry. At the same time, rapid development of ML methods requires flexible software framework for designing custom workflows. MLatom 3 program package designed to leverage power enhance typical chemistry simulations and create complex This open-source provides plenty choice users who can run with command-line options, input files, or scripts using as Python package, both on their computers online XACS cloud computing service at XACScloud.com. Computational chemists calculate energies thermochemical properties, optimize geometries, molecular quantum dynamics, simulate (ro)vibrational, one-photon UV/vis absorption, two-photon absorption spectra ML, mechanical, combined models. The choose from an extensive library containing pretrained models mechanical approximations such AIQM1 approaching coupled-cluster accuracy. developers build own various algorithms. great flexibility largely due use interfaces many state-of-the-art packages libraries.

Язык: Английский

---

DeePMD-GNN: A DeePMD-kit Plugin for External Graph Neural Network Potentials

Journal of Chemical Information and Modeling, Год журнала: 2025, Номер unknown

Опубликована: Март 27, 2025

Machine learning potentials (MLPs) have revolutionized molecular simulation by providing efficient and accurate models for predicting atomic interactions. MLPs continue to advance had profound impact in applications that include drug discovery, enzyme catalysis, materials design. The current landscape of MLP software presents challenges due the limited interoperability between packages, which can lead inconsistent benchmarking practices necessitates separate interfaces with dynamics (MD) software. To address these issues, we present DeePMD-GNN, a plugin DeePMD-kit framework extends its capabilities support external graph neural network (GNN) potentials.DeePMD-GNN enables seamless integration popular GNN-based models, such as NequIP MACE, within ecosystem. Furthermore, new infrastructure allows GNN be used combined quantum mechanical/molecular mechanical (QM/MM) using range corrected ΔMLP formalism.We demonstrate application DeePMD-GNN performing benchmark calculations NequIP, DPA-2 developed under consistent training conditions ensure fair comparison.

Язык: Английский

---

Newton-X Platform: New Software Developments for Surface Hopping and Nuclear Ensembles

Journal of Chemical Theory and Computation, Год журнала: 2022, Номер 18(11), С. 6851 - 6865

Опубликована: Окт. 4, 2022

Newton-X is an open-source computational platform to perform nonadiabatic molecular dynamics based on surface hopping and spectrum simulations using the nuclear ensemble approach. Both are among most common methodologies in chemistry for photophysical photochemical investigations. This paper describes main features of these methods how they implemented Newton-X. It emphasizes newest developments, including zero-point-energy leakage correction, complex-valued potential energy surfaces, induced by incoherent light, machine-learning potentials, exciton multiple chromophores, supervised unsupervised machine learning techniques. interfaced with several third-party quantum-chemistry programs, spanning a broad electronic structure methods.

Язык: Английский

---

Δ-Machine Learned Potential Energy Surfaces and Force Fields

Journal of Chemical Theory and Computation, Год журнала: 2022, Номер 19(1), С. 1 - 17

Опубликована: Дек. 17, 2022

There has been great progress in developing machine-learned potential energy surfaces (PESs) for molecules and clusters with more than 10 atoms. Unfortunately, this number of atoms generally limits the level electronic structure theory to less "gold standard" CCSD(T) level. Indeed, well-known MD17 dataset 9-20 atoms, all energies forces were obtained DFT calculations (PBE). This Perspective is focused on a Δ-machine learning method that we recently proposed applied bring DFT-based PESs close accuracy. demonstrated hydronium, N-methylacetamide, acetyl acetone, ethanol. For 15-atom tropolone, it appears special approaches (e.g., molecular tailoring, local CCSD(T)) are needed obtain energies. A new aspect approach extension force fields. The based many-body corrections polarizable field potentials. examined detail using TTM2.1 water potential. make use our recent datasets 2-b, 3-b, 4-b interactions water. These used develop fully ab initio water, termed q-AQUA.

Язык: Английский

---