1
|
Voss J. Machine learning for accuracy in density functional approximations. J Comput Chem 2024; 45:1829-1845. [PMID: 38668453 DOI: 10.1002/jcc.27366] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2023] [Revised: 02/16/2024] [Accepted: 03/25/2024] [Indexed: 07/21/2024]
Abstract
Machine learning techniques have found their way into computational chemistry as indispensable tools to accelerate atomistic simulations and materials design. In addition, machine learning approaches hold the potential to boost the predictive power of computationally efficient electronic structure methods, such as density functional theory, to chemical accuracy and to correct for fundamental errors in density functional approaches. Here, recent progress in applying machine learning to improve the accuracy of density functional and related approximations is reviewed. Promises and challenges in devising machine learning models transferable between different chemistries and materials classes are discussed with the help of examples applying promising models to systems far outside their training sets.
Collapse
Affiliation(s)
- Johannes Voss
- SUNCAT Center for Interface Science and Catalysis, SLAC National Accelerator Laboratory, Menlo Park, California, USA
| |
Collapse
|
2
|
Sahoo SJ, Xu Q, Lei X, Staros D, Iyer GR, Rubenstein B, Suryanarayana P, Medford AJ. Self-Consistent Convolutional Density Functional Approximations: Application to Adsorption at Metal Surfaces. Chemphyschem 2024; 25:e202300688. [PMID: 38421371 DOI: 10.1002/cphc.202300688] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2023] [Revised: 02/23/2024] [Accepted: 02/25/2024] [Indexed: 03/02/2024]
Abstract
The exchange-correlation (XC) functional in density functional theory is used to approximate multi-electron interactions. A plethora of different functionals are available, but nearly all are based on the hierarchy of inputs commonly referred to as "Jacob's ladder." This paper introduces an approach to construct XC functionals with inputs from convolutions of arbitrary kernels with the electron density, providing a route to move beyond Jacob's ladder. We derive the variational derivative of these functionals, showing consistency with the generalized gradient approximation (GGA), and provide equations for variational derivatives based on multipole features from convolutional kernels. A proof-of-concept functional, PBEq, which generalizes the PBE α ${\alpha }$ framework with α ${\alpha }$ being a spatially-resolved function of the monopole of the electron density, is presented and implemented. It allows a single functional to use different GGAs at different spatial points in a system, while obeying PBE constraints. Analysis of the results underlines the importance of error cancellation and the XC potential in data-driven functional design. After testing on small molecules, bulk metals, and surface catalysts, the results indicate that this approach is a promising route to simultaneously optimize multiple properties of interest.
Collapse
Affiliation(s)
| | - Qimen Xu
- Georgia Institute of Technology, Atlanta, GA
- National Supercomputing Center, Shenzhen, People's Republic of China
| | | | - Daniel Staros
- Department of Chemistry, Brown University, Providence, RI
| | - Gopal R Iyer
- Department of Chemistry, Brown University, Providence, RI
| | | | | | | |
Collapse
|
3
|
Chen Z, Yang W. Development of a machine learning finite-range nonlocal density functional. J Chem Phys 2024; 160:014105. [PMID: 38180254 DOI: 10.1063/5.0179149] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Accepted: 12/12/2023] [Indexed: 01/06/2024] Open
Abstract
Kohn-Sham density functional theory has been the most popular method in electronic structure calculations. To fulfill the increasing accuracy requirements, new approximate functionals are needed to address key issues in existing approximations. It is well known that nonlocal components are crucial. Current nonlocal functionals mostly require orbital dependence such as in Hartree-Fock exchange and many-body perturbation correlation energy, which, however, leads to higher computational costs. Deviating from this pathway, we describe functional nonlocality in a new approach. By partitioning the total density to atom-centered local densities, a many-body expansion is proposed. This many-body expansion can be truncated at one-body contributions, if a base functional is used and an energy correction is approximated. The contribution from each atom-centered local density is a single finite-range nonlocal functional that is universal for all atoms. We then use machine learning to develop this universal atom-centered functional. Parameters in this functional are determined by fitting to data that are produced by high-level theories. Extensive tests on several different test sets, which include reaction energies, reaction barrier heights, and non-covalent interaction energies, show that the new functional, with only the density as the basic variable, can produce results comparable to the best-performing double-hybrid functionals, (for example, for the thermochemistry test set selected from the GMTKN55 database, BLYP based machine learning functional gives a weighted total mean absolute deviations of 3.33 kcal/mol, while DSD-BLYP-D3(BJ) gives 3.28 kcal/mol) with a lower computational cost. This opens a new pathway to nonlocal functional development and applications.
Collapse
Affiliation(s)
- Zehua Chen
- Department of Chemistry, Duke University, Durham, North Carolina 27708, USA
| | - Weitao Yang
- Department of Chemistry and Department of Physics, Duke University, Durham, North Carolina 27708, USA
| |
Collapse
|
4
|
Riemelmoser S, Verdi C, Kaltak M, Kresse G. Machine Learning Density Functionals from the Random-Phase Approximation. J Chem Theory Comput 2023; 19:7287-7299. [PMID: 37800677 PMCID: PMC10601474 DOI: 10.1021/acs.jctc.3c00848] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2023] [Indexed: 10/07/2023]
Abstract
Kohn-Sham density functional theory (DFT) is the standard method for first-principles calculations in computational chemistry and materials science. More accurate theories such as the random-phase approximation (RPA) are limited in application due to their large computational cost. Here, we use machine learning to map the RPA to a pure Kohn-Sham density functional. The machine learned RPA model (ML-RPA) is a nonlocal extension of the standard gradient approximation. The density descriptors used as ingredients for the enhancement factor are nonlocal counterparts of the local density and its gradient. Rather than fitting only RPA exchange-correlation energies, we also include derivative information in the form of RPA optimized effective potentials. We train a single ML-RPA functional for diamond, its surfaces, and liquid water. The accuracy of ML-RPA for the formation energies of 28 diamond surfaces reaches that of state-of-the-art van der Waals functionals. For liquid water, however, ML-RPA cannot yet improve upon the standard gradient approximation. Overall, our work demonstrates how machine learning can extend the applicability of the RPA to larger system sizes, time scales, and chemical spaces.
Collapse
Affiliation(s)
- Stefan Riemelmoser
- Faculty
of Physics and Center for Computational Materials Science, University of Vienna, Kolingasse 14-16, A-1090 Vienna, Austria
- Vienna
Doctoral School in Physics, University of
Vienna, Boltzmanngasse
5, A-1090 Vienna, Austria
| | - Carla Verdi
- Faculty
of Physics and Center for Computational Materials Science, University of Vienna, Kolingasse 14-16, A-1090 Vienna, Austria
- School
of Physics, The University of Sydney, Sydney, New South Wales 2006, Australia
- School
of Mathematics and Physics, The University
of Queensland, Brisbane, Queensland 4072, Australia
| | - Merzuk Kaltak
- VASP
Software GmbH, Sensengasse
8/12, A-1090 Vienna, Austria
| | - Georg Kresse
- Faculty
of Physics and Center for Computational Materials Science, University of Vienna, Kolingasse 14-16, A-1090 Vienna, Austria
- VASP
Software GmbH, Sensengasse
8/12, A-1090 Vienna, Austria
| |
Collapse
|
5
|
Remme R, Kaczun T, Scheurer M, Dreuw A, Hamprecht FA. KineticNet: Deep learning a transferable kinetic energy functional for orbital-free density functional theory. J Chem Phys 2023; 159:144113. [PMID: 37830452 DOI: 10.1063/5.0158275] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2023] [Accepted: 09/14/2023] [Indexed: 10/14/2023] Open
Abstract
Orbital-free density functional theory (OF-DFT) holds promise to compute ground state molecular properties at minimal cost. However, it has been held back by our inability to compute the kinetic energy as a functional of electron density alone. Here, we set out to learn the kinetic energy functional from ground truth provided by the more expensive Kohn-Sham density functional theory. Such learning is confronted with two key challenges: Giving the model sufficient expressivity and spatial context while limiting the memory footprint to afford computations on a GPU and creating a sufficiently broad distribution of training data to enable iterative density optimization even when starting from a poor initial guess. In response, we introduce KineticNet, an equivariant deep neural network architecture based on point convolutions adapted to the prediction of quantities on molecular quadrature grids. Important contributions include convolution filters with sufficient spatial resolution in the vicinity of nuclear cusp, an atom-centric sparse but expressive architecture that relays information across multiple bond lengths, and a new strategy to generate varied training data by finding ground state densities in the face of perturbations by a random external potential. KineticNet achieves, for the first time, chemical accuracy of the learned functionals across input densities and geometries of tiny molecules. For two-electron systems, we additionally demonstrate OF-DFT density optimization with chemical accuracy.
Collapse
Affiliation(s)
- R Remme
- IWR, Heidelberg University Im Neuenheimer Feld 205, 69120 Heidelberg Baden-Württemberg, Germany
| | - T Kaczun
- IWR, Heidelberg University Im Neuenheimer Feld 205, 69120 Heidelberg Baden-Württemberg, Germany
| | - M Scheurer
- IWR, Heidelberg University Im Neuenheimer Feld 205, 69120 Heidelberg Baden-Württemberg, Germany
| | - A Dreuw
- IWR, Heidelberg University Im Neuenheimer Feld 205, 69120 Heidelberg Baden-Württemberg, Germany
| | - F A Hamprecht
- IWR, Heidelberg University Im Neuenheimer Feld 205, 69120 Heidelberg Baden-Württemberg, Germany
| |
Collapse
|
6
|
Vuckovic S, Bahmann H. Nonlocal Functionals Inspired by the Strongly Interacting Limit of DFT: Exact Constraints and Implementation. J Chem Theory Comput 2023; 19:6172-6184. [PMID: 37611177 DOI: 10.1021/acs.jctc.3c00437] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/25/2023]
Abstract
Capturing strong correlation effects remains a key challenge for the development of improved exchange-correlation (XC) functionals in density functional theory. The recently proposed multiple radii functional (MRF) [J. Phys. Chem. Lett. 2017, 8, 2799; J. Chem. Theory Comput. 2019, 15, 3580] was designed to capture strong correlation effects seamlessly, as its mathematical structure draws from that of the exact XC functional in the limit of infinite correlations. The MRF functional provides a framework for building approximations along the density-fixed adiabatic connection, delivers accurate XC energy densities in the standard DFT gauge (same as that of the exact exchange energy density), and is free of one-electron self-interaction errors. To facilitate the development of XC functionals based on the MRF, we examine the behavior of the MRF functional when applied to uniform and scaled densities and consider how it can be made exact for the uniform electron gas. These theoretical insights are then used to build improved forms for the fluctuation function, an object that defines XC energy densities within the MRF framework. We also show how the MRF fluctuation function for physical correlation can be easily readjusted to accurately capture the XC functional in the limit of infinite correlations, demonstrating the versatility of MRF for building approximations for different correlation regimes. We describe the implementation of MRF using densities expanded on Gaussian basis sets, which improves the efficiency of previous grid-based MRF implementations.
Collapse
Affiliation(s)
- Stefan Vuckovic
- Department of Chemistry, University of Fribourg, 1700 Fribourg, Switzerland
| | - Hilke Bahmann
- Physical and Theoretical Chemistry, University of Wuppertal, Gaußstr. 20, 42119 Wuppertal, Germany
| |
Collapse
|
7
|
Hagg A, Kirschner KN. Open-Source Machine Learning in Computational Chemistry. J Chem Inf Model 2023; 63:4505-4532. [PMID: 37466636 PMCID: PMC10430767 DOI: 10.1021/acs.jcim.3c00643] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2023] [Indexed: 07/20/2023]
Abstract
The field of computational chemistry has seen a significant increase in the integration of machine learning concepts and algorithms. In this Perspective, we surveyed 179 open-source software projects, with corresponding peer-reviewed papers published within the last 5 years, to better understand the topics within the field being investigated by machine learning approaches. For each project, we provide a short description, the link to the code, the accompanying license type, and whether the training data and resulting models are made publicly available. Based on those deposited in GitHub repositories, the most popular employed Python libraries are identified. We hope that this survey will serve as a resource to learn about machine learning or specific architectures thereof by identifying accessible codes with accompanying papers on a topic basis. To this end, we also include computational chemistry open-source software for generating training data and fundamental Python libraries for machine learning. Based on our observations and considering the three pillars of collaborative machine learning work, open data, open source (code), and open models, we provide some suggestions to the community.
Collapse
Affiliation(s)
- Alexander Hagg
- Institute
of Technology, Resource and Energy-Efficient Engineering (TREE), University of Applied Sciences Bonn-Rhein-Sieg, 53757 Sankt Augustin, Germany
- Department
of Electrical Engineering, Mechanical Engineering and Technical Journalism, University of Applied Sciences Bonn-Rhein-Sieg, 53757 Sankt Augustin, Germany
| | - Karl N. Kirschner
- Institute
of Technology, Resource and Energy-Efficient Engineering (TREE), University of Applied Sciences Bonn-Rhein-Sieg, 53757 Sankt Augustin, Germany
- Department
of Computer Science, University of Applied
Sciences Bonn-Rhein-Sieg, 53757 Sankt Augustin, Germany
| |
Collapse
|
8
|
Huang B, von Rudorff GF, von Lilienfeld OA. The central role of density functional theory in the AI age. Science 2023; 381:170-175. [PMID: 37440654 DOI: 10.1126/science.abn3445] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2023] [Accepted: 05/30/2023] [Indexed: 07/15/2023]
Abstract
Density functional theory (DFT) plays a pivotal role in chemical and materials science because of its relatively high predictive power, applicability, versatility, and computational efficiency. We review recent progress in machine learning (ML) model developments, which have relied heavily on DFT for synthetic data generation and for the design of model architectures. The general relevance of these developments is placed in a broader context for chemical and materials sciences. DFT-based ML models have reached high efficiency, accuracy, scalability, and transferability and pave the way to the routine use of successful experimental planning software within self-driving laboratories.
Collapse
Affiliation(s)
- Bing Huang
- University of Vienna, Faculty of Physics, AT1090 Wien, Austria
| | - Guido Falk von Rudorff
- University Kassel, Department of Chemistry, 34132 Kassel, Germany
- Center for Interdisciplinary Nanostructure Science and Technology (CINSaT), 34132 Kassel, Germany
| | - O Anatole von Lilienfeld
- Vector Institute for Artificial Intelligence, Toronto, Ontario M5S 1M1, Canada
- Department of Chemistry, University of Toronto, St. George Campus, Toronto, Ontario M5S 3H6, Canada
- Department of Materials Science and Engineering, University of Toronto, St. George Campus, Toronto, Ontario M5S 3E4, Canada
- Department of Physics, University of Toronto, St. George Campus, Toronto, Ontario M5S 1A7, Canada
- Machine Learning Group, Technische Universität Berlin and Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany
| |
Collapse
|
9
|
Cuierrier E, Roy PO, Wang R, Ernzerhof M. The fourth-order expansion of the exchange hole and neural networks to construct exchange–correlation functionals. J Chem Phys 2022; 157:171103. [DOI: 10.1063/5.0122761] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022] Open
Abstract
The curvature Q σ of spherically averaged exchange (X) holes ρX, σ(r, u) is one of the crucial variables for the construction of approximations to the exchange–correlation energy of Kohn–Sham theory, the most prominent example being the Becke–Roussel model [A. D. Becke and M. R. Roussel, Phys. Rev. A 39, 3761 (1989)]. Here, we consider the next higher nonzero derivative of the spherically averaged X hole, the fourth-order term T σ. This variable contains information about the nonlocality of the X hole and we employ it to approximate hybrid functionals, eliminating the sometimes demanding calculation of the exact X energy. The new functional is constructed using machine learning; having identified a physical correlation between T σ and the nonlocality of the X hole, we employ a neural network to express this relation. While we only modify the X functional of the Perdew–Burke–Ernzerhof functional [Perdew et al., Phys. Rev. Lett. 77, 3865 (1996)], a significant improvement over this method is achieved.
Collapse
Affiliation(s)
- Etienne Cuierrier
- Département de Chimie, Université de Montréal, C.P. 6128 Succursale A, Montréal, Québec H3C 3J7, Canada
| | - Pierre-Olivier Roy
- Département de Chimie, Université de Montréal, C.P. 6128 Succursale A, Montréal, Québec H3C 3J7, Canada
| | - Rodrigo Wang
- Good Chemistry Company, Vancouver, British Columbia V6E 4B1, Canada
| | - Matthias Ernzerhof
- Département de Chimie, Université de Montréal, C.P. 6128 Succursale A, Montréal, Québec H3C 3J7, Canada
| |
Collapse
|