Exceptional piezoelectricity, high thermal conductivity and stiffness and promising photocatalysis in two-dimensional MoSi2N4 family confirmed by first-principles

Nano Energy, Journal Year: 2020, Volume and Issue: 82, P. 105716 - 105716

Published: Dec. 29, 2020

Language: Английский

---

Physics-Inspired Structural Representations for Molecules and Materials

Chemical Reviews, Journal Year: 2021, Volume and Issue: 121(16), P. 9759 - 9815

Published: July 26, 2021

The first step in the construction of a regression model or data-driven analysis, aiming to predict elucidate relationship between atomic-scale structure matter and its properties, involves transforming Cartesian coordinates atoms into suitable representation. development representations has played, continues play, central role success machine-learning methods for chemistry materials science. This review summarizes current understanding nature characteristics most commonly used structural chemical descriptions atomistic structures, highlighting deep underlying connections different frameworks ideas that lead computationally efficient universally applicable models. It emphasizes link their physical chemistry, mathematical description, provides examples recent applications diverse set science problems, outlines open questions promising research directions field.

Language: Английский

---

First‐Principles Multiscale Modeling of Mechanical Properties in Graphene/Borophene Heterostructures Empowered by Machine‐Learning Interatomic Potentials

Advanced Materials, Journal Year: 2021, Volume and Issue: 33(35)

Published: July 23, 2021

Abstract Density functional theory calculations are robust tools to explore the mechanical properties of pristine structures at their ground state but become exceedingly expensive for large systems finite temperatures. Classical molecular dynamics (CMD) simulations offer possibility study larger elevated temperatures, they require accurate interatomic potentials. Herein authors propose concept first‐principles multiscale modeling properties, where ab initio level accuracy is hierarchically bridged mechanical/failure response macroscopic systems. It demonstrated that machine‐learning potentials (MLIPs) fitted datasets play a pivotal role in achieving this goal. To practically illustrate novel possibility, graphene/borophene coplanar heterostructures examined. shown MLIPs conveniently outperform popular CMD models graphene and borophene can evaluate heterostructure phases room temperature. Based on information provided by MLIP‐based CMD, continuum using element method be constructed. The highlights were missing block conducting modeling, employment empowers straightforward route bridge flexibility nanostructures scale.

Language: Английский

---

Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport

Physical review. B./Physical review. B, Journal Year: 2021, Volume and Issue: 104(10)

Published: Sept. 20, 2021

We develop a neuroevolution-potential (NEP) framework for generating neural network-based machine-learning potentials. They are trained using an evolutionary strategy performing large-scale molecular dynamics (MD) simulations. A descriptor of the atomic environment is constructed based on Chebyshev and Legendre polynomials. The method implemented in graphic processing units within open-source gpumd package, which can attain computational speed over ${10}^{7}$ atom-step per second one Nvidia Tesla V100. Furthermore, per-atom heat current available NEP, paves way efficient accurate MD simulations transport materials with strong phonon anharmonicity or spatial disorder, usually cannot be accurately treated either traditional empirical potentials perturbative methods.

Language: Английский

---

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

The Journal of Chemical Physics, Journal Year: 2023, Volume and Issue: 159(5)

Published: Aug. 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.

Language: Английский

---

Machine-learning interatomic potentials for materials science

Acta Materialia, Journal Year: 2021, Volume and Issue: 214, P. 116980 - 116980

Published: May 19, 2021

Language: Английский

---

GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations

The Journal of Chemical Physics, Journal Year: 2022, Volume and Issue: 157(11)

Published: Aug. 24, 2022

We present our latest advancements of machine-learned potentials (MLPs) based on the neuroevolution potential (NEP) framework introduced in [Fan et al., Phys. Rev. B 104, 104309 (2021)] and their implementation open-source package GPUMD. increase accuracy NEP models both by improving radial functions atomic-environment descriptor using a linear combination Chebyshev basis extending angular with some four-body five-body contributions as atomic cluster expansion approach. also detail efficient approach graphics processing units well workflow for construction models, we demonstrate application large-scale atomistic simulations. By comparing to state-of-the-art MLPs, show that not only achieves above-average but is far more computationally efficient. These results GPUMD promising tool solving challenging problems requiring highly accurate, To enable MLPs minimal training set, propose an active-learning scheme latent space pre-trained model. Finally, introduce three separate Python packages, GPYUMD, CALORINE, PYNEP, which integration into workflows.

Language: Английский

---

Intelligent Computing: The Latest Advances, Challenges, and Future

Intelligent Computing, Journal Year: 2023, Volume and Issue: 2

Published: Jan. 1, 2023

Computing is a critical driving force in the development of human civilization. In recent years, we have witnessed emergence intelligent computing, new computing paradigm that reshaping traditional and promoting digital revolution era big data, artificial intelligence, internet things with theories, architectures, methods, systems, applications. Intelligent has greatly broadened scope extending it from on data to increasingly diverse paradigms such as perceptual cognitive autonomous human–computer fusion intelligence. Intelligence undergone paths different evolution for long time but become intertwined years: not only intelligence oriented also driven. Such cross-fertilization prompted rapid advancement computing. still its infancy, an abundance innovations applications expected occur soon. We present first comprehensive survey literature covering theory fundamentals, technological important applications, challenges, future perspectives. believe this highly timely will provide reference cast valuable insights into academic industrial researchers practitioners.

Language: Английский

---

Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning

npj Computational Materials, Journal Year: 2022, Volume and Issue: 8(1)

Published: March 16, 2022

Computational study of molecules and materials from first principles is a cornerstone physics, chemistry, science, but limited by the cost accurate precise simulations. In settings involving many simulations, machine learning can reduce these costs, often orders magnitude, interpolating between reference This requires representations that describe any molecule or material support interpolation. We comprehensively review discuss current relations them, using unified mathematical framework based on many-body functions, group averaging, tensor products. For selected state-of-the-art representations, we compare energy predictions for organic molecules, binary alloys, Al-Ga-In sesquioxides in numerical experiments controlled data distribution, regression method, hyper-parameter optimization.

Language: Английский

---

Multi-Label Active Learning-Based Machine Learning Model for Heart Disease Prediction

Sensors, Journal Year: 2022, Volume and Issue: 22(3), P. 1184 - 1184

Published: Feb. 4, 2022

The rapid growth and adaptation of medical information to identify significant health trends help with timely preventive care have been recent hallmarks the modern healthcare data system. Heart disease is deadliest condition in developed world. Cardiovascular its complications, including dementia, can be averted early detection. Further research this area needed prevent strokes heart attacks. An optimal machine learning model achieve goal a wealth on disease. predicted diagnosed using machine-learning-based systems. Active (AL) methods improve classification quality by incorporating user-expert feedback sparsely labelled data. In paper, five (MMC, Random, Adaptive, QUIRE, AUDI) selection strategies for multi-label active were applied used reducing labelling costs iteratively selecting most relevant query their labels. label ranking classifier hyperparameters optimized grid search implement predictive modelling each scenario dataset. Experimental evaluation includes accuracy F-score with/without hyperparameter optimization. Results show that generalization beyond existing uses method versus others due accuracy. However, was highlighted regards settings.

Language: Английский

---