Journal ArticleDOI
On-the-Fly Active Learning of Interatomic Potentials for Large-Scale Atomistic Simulations
Reads0
Chats0
TLDR
The on-the-fly generation of machine-learning force fields by active-learning schemes is demonstrated by presenting recent applications and overall, simulations are accelerated by several orders of magnitude while retaining almost first-principles accuracy.Abstract:
The on-the-fly generation of machine-learning force fields by active-learning schemes attracts a great deal of attention in the community of atomistic simulations. The algorithms allow the machine to self-learn an interatomic potential and construct machine-learned models on the fly during simulations. State-of-the-art query strategies allow the machine to judge whether new structures are out of the training data set or not. Only when the machine judges the necessity of updating the data set with the new structures are first-principles calculations carried out. Otherwise, the yet available machine-learned model is used to update the atomic positions. In this manner, most of the first-principles calculations are bypassed during training, and overall, simulations are accelerated by several orders of magnitude while retaining almost first-principles accuracy. In this Perspective, after describing essential components of the active-learning algorithms, we demonstrate the power of the schemes by presenting recent applications.read more
Citations
More filters
Journal ArticleDOI
Gaussian Process Regression for Materials and Molecules.
Volker L. Deringer,Albert P. Bartók,Noam Bernstein,David M. Wilkins,Michele Ceriotti,Gábor Csányi +5 more
TL;DR: In this paper, the authors provide an introduction to Gaussian process regression (GPR) machine learning methods in computational materials science and chemistry, focusing on the regression of atomistic properties: in particular, on the construction of interatomic potentials, or force fields, in the Gaussian approximation potential (GAP) framework.
Journal ArticleDOI
Quantum Machine Learning in Chemical Compound Space.
TL;DR: The case is made for quantum machine learning: An inductive molecular modeling approach which can be applied to quantum chemistry problems.
Journal ArticleDOI
Ab Initio Machine Learning in Chemical Compound Space.
TL;DR: In this article, the authors present a review of machine learning techniques for chemical compound space (CCS) based on synthetic data and model architectures inspired by quantum mechanics, including quantum mechanics based Machine Learning (QML) approaches.
Journal ArticleDOI
Machine learning for metallurgy III: A neural network potential for Al-Mg-Si
TL;DR: In this article, a neural network potential for the Al-Cu system is presented as a first example of a machine learning potential that can achieve near-first-principle accuracy for many different metallurgically important aspects of this alloy.
References
More filters
Journal ArticleDOI
CHARMM: A program for macromolecular energy, minimization, and dynamics calculations
Bernard R. Brooks,Robert E. Bruccoleri,Barry D. Olafson,David J. States,S. Swaminathan,Martin Karplus +5 more
TL;DR: The CHARMM (Chemistry at Harvard Macromolecular Mechanics) as discussed by the authors is a computer program that uses empirical energy functions to model macromolescular systems, and it can read or model build structures, energy minimize them by first- or second-derivative techniques, perform a normal mode or molecular dynamics simulation, and analyze the structural, equilibrium, and dynamic properties determined in these calculations.
Journal ArticleDOI
Efficient Hybrid Solar Cells Based on Meso-Superstructured Organometal Halide Perovskites
Michael M. Lee,Joël Teuscher,Tsutomu Miyasaka,Takurou N. Murakami,Takurou N. Murakami,Henry J. Snaith +5 more
TL;DR: A low-cost, solution-processable solar cell, based on a highly crystalline perovskite absorber with intense visible to near-infrared absorptivity, that has a power conversion efficiency of 10.9% in a single-junction device under simulated full sunlight is reported.
Journal ArticleDOI
Electron-hole diffusion lengths exceeding 1 micrometer in an organometal trihalide perovskite absorber.
Samuel D. Stranks,Giles E. Eperon,Giulia Grancini,Christopher Menelaou,Marcelo J. P. Alcocer,Tomas Leijtens,Laura M. Herz,Annamaria Petrozza,Henry J. Snaith +8 more
TL;DR: In this article, transient absorption and photoluminescence-quenching measurements were performed to determine the electron-hole diffusion lengths, diffusion constants, and lifetimes in mixed halide and triiodide perovskite absorbers.
Journal ArticleDOI
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
Anubhav Jain,Shyue Ping Ong,Geoffroy Hautier,Wei-Wei Chen,William D. Richards,Stephen Dacek,Shreyas Cholia,Dan Gunter,David Skinner,Gerbrand Ceder,Kristin A. Persson +10 more
TL;DR: The Materials Project (www.materialsproject.org) is a core program of the Materials Genome Initiative that uses high-throughput computing to uncover the properties of all known inorganic materials as discussed by the authors.
Journal Article
Electron-Hole Diffusion Lengths Exceeding 1 Micrometer in an Organometal Trihalide Perovskite Absorber
Samuel D. Stranks,Giles E. Eperon,Giulia Grancini,Christopher Menelaou,Marcelo J. P. Alcocer,Tomas Leijtens,Laura M. Herz,Annamaria Petrozza,Henry J. Snaith +8 more
TL;DR: In this paper, transient absorption and photoluminescence-quenching measurements were performed to determine the electron-hole diffusion lengths, diffusion constants, and lifetimes in mixed halide and triiodide perovskite absorbers.
Related Papers (5)
Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons.
Generalized neural-network representation of high-dimensional potential-energy surfaces.
Jörg Behler,Michele Parrinello +1 more