☆ 4.7 Article

A semilocal machine-learning correction to density functional approximations

JOURNAL OF CHEMICAL PHYSICS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Interdisciplinary Applications

Supervised learning of a chemistry functional with damped dispersion

Yiwei Liu et al.

Summary: In this study, we optimized a singly hybrid functional called CF22D, which outperforms most existing non-doubly hybrid functionals in terms of accuracy in chemistry. By using a flexible functional form that combines a global hybrid meta-nonseparable gradient approximation with a damped dispersion term, we trained CF22D using a large database and performance-triggered iterative supervised training. The use of a combined database demonstrated CF22D's good performance across various chemical properties and systems.

NATURE COMPUTATIONAL SCIENCE (2023)

添加到收藏夹

Article Chemistry, Physical

Improving Density Functional Prediction of Molecular Thermochemical Properties with a Machine-Learning-Corrected Generalized Gradient Approximation

JingChun Wang et al.

Summary: In the past decade, there has been a growing interest in designing sophisticated density functional approximations (DFAs) by integrating machine learning techniques. This study presents a machine learning correction to the widely used Perdew-Burke-Ernzerhof (PBE) functional, which improves heats of formation while maintaining accuracy for other properties. The research highlights the potential of combining data-driven machine learning methods with physics-inspired derivations for achieving chemical accuracy.

JOURNAL OF PHYSICAL CHEMISTRY A (2022)

添加到收藏夹

Article Chemistry, Physical

Exact constraints and appropriate norms in machine-learned exchange-correlation functionals

Kanun Pokharel et al.

Summary: This study designs a deep neural network using machine learning techniques to replicate strongly constrained and appropriately normed functional by only using electron density and local derivative information. The experimental results demonstrate that this machine learning approach shows good performance and transferability in molecular and periodic systems.

JOURNAL OF CHEMICAL PHYSICS (2022)

添加到收藏夹

Article Physics, Multidisciplinary

Machine-learning-based exchange correlation functional with physical asymptotic constraints

Ryo Nagai et al.

Summary: This paper introduces a neural network-based exchange-correlation functional that satisfies physical asymptotic constraints, improving the accuracy and generalization performance of machine learning-based functionals.

PHYSICAL REVIEW RESEARCH (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Machine learning the derivative discontinuity of density-functional theory

Johannes Gedeon et al.

Summary: This article presents a solution to the problems in density functional theory, namely the explicit dependency of the functionals on the particle number and the derivative discontinuity at integer particle numbers. They propose training a neural network as a universal functional that exhibits piece-wise linearity between integer particle numbers and reproduces the derivative discontinuity of the exchange-correlation energy.

MACHINE LEARNING-SCIENCE AND TECHNOLOGY (2022)

添加到收藏夹

Article Chemistry, Physical

DeePKS: A Comprehensive Data-Driven Approach toward Chemically Accurate Density Functional Theory

Yixiao Chen et al.

Summary: The study introduces a general machine learning-based framework for constructing accurate and widely applicable energy functionals within the framework of generalized Kohn-Sham density functional theory. By developing a method for training self-consistent models that can handle large datasets and improve prediction accuracy, it demonstrates chemically accurate predictions on various molecular properties. The functional can be continuously enhanced as more data becomes available.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2021)

添加到收藏夹

Article Physics, Multidisciplinary

Kohn-Sham Equations as Regularizer: Building Prior Knowledge into Machine-Learned Physics

Li Li et al.

Summary: Incorporating prior knowledge into machine learning models for physics is crucial for improving generalization performance. Solving the Kohn-Sham equations when training neural networks for the exchange-correlation functional provides implicit regularization, enhancing predictive capabilities effectively.

PHYSICAL REVIEW LETTERS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Pure non-local machine-learned density functional theory for electron correlation

Johannes T. Margraf et al.

Summary: Density-functional theory is a rigorous framework for describing the ground state properties of atoms, molecules and solids, while a new machine-learning based DFA called Kernel Density Functional Approximation has been developed, which is pure, non-local and transferable, showing remarkable possibilities for diverse interactions and system sizes.

NATURE COMMUNICATIONS (2021)

添加到收藏夹

Article Chemistry, Physical

Constructing and representing exchange-correlation holes through artificial neural networks

Etienne Cuierrier et al.

Summary: This study utilizes machine learning algorithms to partially automate the construction of X and XC holes, developing a tool called ExMachina for generating approximations. Unlike traditional machine learning that relies on patterns in datasets, the focus here is on physical insight, demonstrating how to go beyond existing approximations.

JOURNAL OF CHEMICAL PHYSICS (2021)

添加到收藏夹

Review Chemistry, Multidisciplinary

Learning to Approximate Density Functionals

Bhupalee Kalita et al.

Summary: Density functional theory (DFT) calculations are widely used in scientific research, with machine learning (ML) offering new possibilities for improving the accuracy and usefulness of these calculations. ML has the potential to propose or enhance approximations for DFT, but challenges such as generalization remain to be addressed for implementing ML-designed functionals in standard codes.

ACCOUNTS OF CHEMICAL RESEARCH (2021)

添加到收藏夹

Article Chemistry, Physical

Exploring the Limits of the XYG3-Type Doubly Hybrid Approximations for the Main-Group Chemistry: The xDH@B3LYP Model

Igor Ying Zhang et al.

Summary: This study investigates the limits of XYG3-type doubly hybrid approximations using the B3LYP reference orbitals, without resorting to any long-range correction scheme, for a balanced description of covalent and noncovalent interactions. The results demonstrate that the xDH@B3LYP model can achieve accuracy and robustness comparable to or even better than expensive composite methods in wave function theory, shedding new light on the development of DHAs.

JOURNAL OF PHYSICAL CHEMISTRY LETTERS (2021)

添加到收藏夹

Article Physics, Multidisciplinary

Highly accurate machine learning model for kinetic energy density functional

Mohammed Alghadeer et al.

Summary: A highly accurate predictive model was developed using Machine Learning to estimate one-dimensional kinetic energy density functionals, showing better accuracy than standard KEDF. The statistical training approach suggested the reliability of the model for large-scale orbital free density functional theory calculations.

PHYSICS LETTERS A (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Pushing the frontiers of density functionals by solving the fractional electron problem

James Kirkpatrick et al.

Summary: Density functional theory has long been plagued by systematic errors in approximations, but a new neural network-based functional, DM21, shows promise in accurately describing complex systems and outperforming traditional functionals in benchmarks. By relying on data and constraints, DM21 represents a viable pathway toward the exact universal functional.

SCIENCE (2021)

添加到收藏夹

Article Multidisciplinary Sciences

BSE49, a diverse, high-quality benchmark dataset of separation energies of chemical bonds

Viki Kumar Prasad et al.

Summary: The dataset consists of 4502 datapoints covering 49 unique X-Y type single bonds, classified into Existing and Hypothetical categories. The bond separation energies provided can be used as a high-quality reference dataset for assessing and developing computational chemistry methods.

SCIENTIFIC DATA (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Regularized machine learning on molecular graph model explains systematic error in DFT enthalpies

Himaghna Bhattacharjee et al.

Summary: This research aims to discover and correct errors in DFT calculated thermochemistry for gaseous species, achieving significant improvement by analyzing molecular features using graph theory and employing a regularized algorithm.

SCIENTIFIC REPORTS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Artificial intelligence-enhanced quantum chemical method with broad applicability

Peikun Zheng et al.

Summary: AIQM1 is a general-purpose and highly transferable artificial intelligence-quantum mechanical method that can accurately calculate ground-state energies and geometries of organic compounds, including challenging systems like fullerene C-60. It combines artificial intelligence with quantum mechanics to provide a new method for computational chemistry simulations with high accuracy, speed and transferability.

NATURE COMMUNICATIONS (2021)

添加到收藏夹

Article Chemistry, Multidisciplinary

Doubly Hybrid Functionals Close to Chemical Accuracy for Both Finite and Extended Systems: Implementation and Test of XYG3 and XYGJ-OS

Yizhen Wang et al.

Summary: The study demonstrates that the accuracy of doubly hybrid approximations for molecules can be transferred to semiconductors and insulators, and is applicable to different chemical environments with good performance in first- and second-order response properties. This finding strengthens the predictive power of DFT and will inspire future development of density functional approximations with high accuracy and efficiency.

JACS AU (2021)

添加到收藏夹

Article Chemistry, Physical

Recent developments in the general atomic and molecular electronic structure system

Giuseppe M. J. Barca et al.

JOURNAL OF CHEMICAL PHYSICS (2020)

添加到收藏夹

Article Chemistry, Physical

Bayesian Optimization for Calibrating and Selecting Hybrid-Density Functional Models

R. A. Vargas-Hernandez

JOURNAL OF PHYSICAL CHEMISTRY A (2020)

添加到收藏夹

Article Chemistry, Physical

Completing density functional theory by machine learning hidden messages from molecules

Ryo Nagai et al.

NPJ COMPUTATIONAL MATERIALS (2020)

添加到收藏夹

Article Chemistry, Physical

Orbital-free density functional theory calculation applying semi-local machine-learned kinetic energy density functional and kinetic potential

Mikito Fujinami et al.

CHEMICAL PHYSICS LETTERS (2020)

添加到收藏夹

Article Chemistry, Physical

Recent developments in the PySCF program package

Qiming Sun et al.

JOURNAL OF CHEMICAL PHYSICS (2020)

添加到收藏夹

Article Chemistry, Physical

Machine Learning Approaches toward Orbital-free Density Functional Theory: Simultaneous Training on the Kinetic Energy Density Functional and Its Functional Derivative

Ralf Meyer et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2020)

添加到收藏夹

Article Physics, Multidisciplinary

Deep Learning the Hohenberg-Kohn Maps of Density Functional Theory

Javier Robledo Moreno et al.

PHYSICAL REVIEW LETTERS (2020)

添加到收藏夹

Article Multidisciplinary Sciences

Machine learning accurate exchange and correlation functionals of the electronic density

Sebastian Dick et al.

NATURE COMMUNICATIONS (2020)

添加到收藏夹

Article Chemistry, Medicinal

PubChemQC PM6: Data Sets of 221 Million Molecules with Optimized Molecular Geometries and Electronic Properties

Maho Nakata et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2020)

添加到收藏夹

Article Physics, Multidisciplinary

Efficient learning of a one-dimensional density functional theory

M. Michael Denner et al.

PHYSICAL REVIEW RESEARCH (2020)

添加到收藏夹

Review Chemistry, Multidisciplinary

Status and Challenges of Density Functional Theory

Pragya Verma et al.

TRENDS IN CHEMISTRY (2020)

添加到收藏夹

Article Chemistry, Physical

Machine Learning the Physical Nonlocal Exchange-Correlation Functional of Density-Functional Theory

Jonathan Schmidt et al.

JOURNAL OF PHYSICAL CHEMISTRY LETTERS (2019)

添加到收藏夹

Article Chemistry, Physical

Toward the Exact Exchange-Correlation Potential: A Three-Dimensional Convolutional Neural Network Construct

Yi Zhou et al.

JOURNAL OF PHYSICAL CHEMISTRY LETTERS (2019)

添加到收藏夹

Article Physics, Multidisciplinary

A classical density functional from machine learning and a convolutional neural network

Shang-Chun Lin et al.

SCIPOST PHYSICS (2019)

添加到收藏夹

Article Chemistry, Multidisciplinary

PYSCF: the Python-based simulations of chemistry framework

Qiming Sun et al.

WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE (2018)

添加到收藏夹

Article Chemistry, Physical

Neural-network Kohn-Sham exchange-correlation potential and its out-of-training transferability

Ryo Nagai et al.

JOURNAL OF CHEMICAL PHYSICS (2018)

添加到收藏夹

Article Chemistry, Physical

Survival of the most transferable at the top of Jacob's ladder: Defining and testing the ωB97M(2) double hybrid density functional

Narbe Mardirossian et al.

JOURNAL OF CHEMICAL PHYSICS (2018)

添加到收藏夹

Article Chemistry, Physical

Semi-local machine-learned kinetic energy density functional with third-order gradients of electron density

Junji Seino et al.

JOURNAL OF CHEMICAL PHYSICS (2018)

添加到收藏夹

Article Multidisciplinary Sciences

Doubly hybrid density functionals that correctly describe both density and energy for atoms

Neil Qiang Su et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2018)

添加到收藏夹

Article Chemistry, Physical

A Density Functional Tight Binding Layer for Deep Learning of Chemical Hamiltonians

Haichen Li et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2018)

添加到收藏夹

Article Chemistry, Medicinal

PubChemQC Project: A Large-Scale First-Principles Electronic Structure Database for Data-Driven Chemistry

Maho Nakata et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2017)

添加到收藏夹

Review Chemistry, Physical

Thirty years of density functional theory in computational chemistry: an overview and extensive assessment of 200 density functionals

Narbe Mardirossian et al.

MOLECULAR PHYSICS (2017)

添加到收藏夹

Article Multidisciplinary Sciences

Bypassing the Kohn-Sham equations with machine learning

Felix Brockherde et al.

NATURE COMMUNICATIONS (2017)

添加到收藏夹

Article Chemistry, Physical

Improving the Performance of Long-Range-Corrected Exchange-Correlation Functional with an Embedded Neural Network

Qin Liu et al.

JOURNAL OF PHYSICAL CHEMISTRY A (2017)

添加到收藏夹

Review Chemistry, Physical

Understanding machine-learned density functionals

Li Li et al.

INTERNATIONAL JOURNAL OF QUANTUM CHEMISTRY (2016)

添加到收藏夹

Article Chemistry, Multidisciplinary

Improving B3LYP Heats of Formation with Three-Dimensional Molecular Descriptors

Yuwei Zhou et al.

JOURNAL OF COMPUTATIONAL CHEMISTRY (2016)

添加到收藏夹

Article Materials Science, Multidisciplinary

Pure density functional for strong correlation and the thermodynamic limit from machine learning

Li Li et al.

PHYSICAL REVIEW B (2016)

添加到收藏夹

Article Chemistry, Multidisciplinary

Libcint: An efficient general integral library for Gaussian basis functions

Qiming Sun

JOURNAL OF COMPUTATIONAL CHEMISTRY (2015)

添加到收藏夹

Article Physics, Multidisciplinary

Strongly Constrained and Appropriately Normed Semilocal Density Functional

Jianwei Sun et al.

PHYSICAL REVIEW LETTERS (2015)

添加到收藏夹

Review Multidisciplinary Sciences

Machine learning: Trends, perspectives, and prospects

M. I. Jordan et al.

SCIENCE (2015)

添加到收藏夹

Article Chemistry, Physical

Alternative Approach to Chemical Accuracy: A Neural Networks-Based First-Principles Method for Heat of Formation of Molecules Made of H, C, N, O F, S, and Cl

Jian Sun et al.

JOURNAL OF PHYSICAL CHEMISTRY A (2014)

添加到收藏夹

Review Multidisciplinary Sciences

Quest for a universal density functional: the accuracy of density functionals across a broad spectrum of databases in chemistry and physics

Roberto Peverati et al.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2014)

添加到收藏夹

Article Chemistry, Physical

Orbital-free bond breaking via machine learning

John C. Snyder et al.

JOURNAL OF CHEMICAL PHYSICS (2013)

添加到收藏夹

Review Chemistry, Multidisciplinary

Challenges for Density Functional Theory

Aron J. Cohen et al.

CHEMICAL REVIEWS (2012)

添加到收藏夹

Article Chemistry, Physical

New accurate reference energies for the G2/97 test set

Robin Haunschild et al.

JOURNAL OF CHEMICAL PHYSICS (2012)

添加到收藏夹

Article Chemistry, Physical

Performance of Gradient-Corrected and Hybrid Density Functional Theory: Role of the Underlying Local Density Approximation and the Gradient Correction

Bun Chan et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2012)

添加到收藏夹

Article Chemistry, Physical

The X1s Method for Accurate Bond Dissociation Energies

Jianming Wu et al.

CHEMPHYSCHEM (2010)

添加到收藏夹

Article Physics, Multidisciplinary

Correcting the systematic error of the density functional theory calculation: the alternate combination approach of genetic algorithm and neural network

Wang Ting-Ting et al.

Chinese Physics B (2010)

添加到收藏夹

Article Chemistry, Physical

Property-optimized Gaussian basis sets for molecular response calculations

Dmitrij Rappoport et al.

JOURNAL OF CHEMICAL PHYSICS (2010)

添加到收藏夹

Article Chemistry, Multidisciplinary

Revealing Noncovalent Interactions

Erin R. Johnson et al.

JOURNAL OF THE AMERICAN CHEMICAL SOCIETY (2010)

添加到收藏夹

Article Chemistry, Physical

Accurate computational thermochemistry from explicitly correlated coupled-cluster theory

Wim Klopper et al.

THEORETICAL CHEMISTRY ACCOUNTS (2010)

添加到收藏夹

Review Chemistry, Physical

Atomization energies from coupled-cluster calculations augmented with explicitly-correlated perturbation theory

Wim Klopper et al.

CHEMICAL PHYSICS (2009)

添加到收藏夹

Review Chemistry, Physical

The DBH24/08 Database and Its Use to Assess Electronic Structure Model Chemistries for Chemical Reaction Barrier Heights

Jingjing Zheng et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2009)

添加到收藏夹

Article Chemistry, Multidisciplinary

Accurate Prediction of Heats of Formation by a Combined Method of B3LYP and Neural Network Correction

Jianming Wu et al.

JOURNAL OF COMPUTATIONAL CHEMISTRY (2009)

添加到收藏夹

Article Chemistry, Physical

Improving the B3LYP bond energies by using the X1 method

Jianming Wu et al.

JOURNAL OF CHEMICAL PHYSICS (2008)

添加到收藏夹

Article Chemistry, Physical

The X1 method for accurate and efficient prediction of heats of formation

Jianming Wu et al.

JOURNAL OF CHEMICAL PHYSICS (2007)

添加到收藏夹

Article Chemistry, Physical

Improving the accuracy of density-functional theory calculation: The genetic algorithm and neural network approach

Hui Li et al.

JOURNAL OF CHEMICAL PHYSICS (2007)

添加到收藏夹

Review Chemistry, Physical

A new local density functional for main-group thermochemistry, transition metal bonding, thermochemical kinetics, and noncovalent interactions

Yan Zhao et al.

JOURNAL OF CHEMICAL PHYSICS (2006)

添加到收藏夹

Article Chemistry, Organic

Systematic errors in computed alkane energies using B3LYP and other popular DFT functionals

Matthew D. Wodrich et al.

ORGANIC LETTERS (2006)

添加到收藏夹

Review Chemistry, Physical

Design of density functionals by combining the method of constraint satisfaction with parametrization for thermochemistry, thermochemical kinetics, and noncovalent interactions

Y Zhao et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2006)

添加到收藏夹

Article Chemistry, Physical

Semiempirical hybrid density functional with perturbative second-order correlation

S Grimme

JOURNAL OF CHEMICAL PHYSICS (2006)

添加到收藏夹

Article Chemistry, Physical

Accurate Coulomb-fitting basis sets for H to Rn

F Weigend

PHYSICAL CHEMISTRY CHEMICAL PHYSICS (2006)

添加到收藏夹

Article Chemistry, Physical

Balanced basis sets of split valence, triple zeta valence and quadruple zeta valence quality for H to Rn: Design and assessment of accuracy

F Weigend et al.

PHYSICAL CHEMISTRY CHEMICAL PHYSICS (2005)

添加到收藏夹

Article Chemistry, Physical

Accurate prediction of heat of formation by combining Hartree-Fock/density functional theory calculation with linear regression correction approach

XM Duan et al.

JOURNAL OF CHEMICAL PHYSICS (2004)

添加到收藏夹

Article Chemistry, Physical

Improving the accuracy of density-functional theory calculation: The statistical correction approach

XJ Wang et al.

JOURNAL OF PHYSICAL CHEMISTRY A (2004)

添加到收藏夹

Article Chemistry, Physical

A generalized exchange-correlation functional: the Neural-Networks approach

X Zheng et al.

CHEMICAL PHYSICS LETTERS (2004)

添加到收藏夹

Article Chemistry, Physical

A combined first-principles calculation and neural networks correction approach for evaluating Gibbs energy of formation

XJ Wang et al.

MOLECULAR SIMULATION (2004)

添加到收藏夹

Article Chemistry, Physical

Combined first-principles calculation and neural-network correction approach for heat of formation

LH Hu et al.

JOURNAL OF CHEMICAL PHYSICS (2003)

添加到收藏夹

Article Chemistry, Physical

Assessment of Gaussian-3 and density functional theories for a larger experimental test set

LA Curtiss et al.

JOURNAL OF CHEMICAL PHYSICS (2000)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.