The central role of density functional theory in the AI age

Density functional theory (DFT) plays a pivotal role for the chemical and materials science due to its relatively high predictive power, applicability, versatility and computational efficiency. We review recent progress in machine learning model developments which has relied heavily on density functional theory for synthetic data generation and for the design of model architectures. The general relevance of these developments is placed in some broader context for the chemical and materials sciences. Resulting in DFT based machine learning models with high efficiency, accuracy, scalability, and transferability (EAST), recent progress indicates probable ways for the routine use of successful experimental planning software within self-driving laboratories.

[1]  Byungchan Han,et al.  Closed-loop optimization of nanoparticle synthesis enabled by robotics and machine learning , 2023, Matter.

[2]  M. Tuckerman,et al.  Machine learning the Hohenberg-Kohn map for molecular excited states , 2022, Nature Communications.

[3]  O. A. von Lilienfeld,et al.  Toward DMC Accuracy Across Chemical Space with Scalable Δ-QML. , 2022, Journal of chemical theory and computation.

[4]  Gabriel dos Passos Gomes,et al.  On scientific understanding with artificial intelligence , 2022, Nature Reviews Physics.

[5]  H. Kulik,et al.  Machine learning models predict calculation outcomes with the transferability necessary for computational catalysis , 2022, Journal of chemical theory and computation.

[6]  M. Coote,et al.  Inclusion of More Physics Leads to Less Data: Learning the Interaction Energy as a Function of Electron Deformation Density with Limited Training Data. , 2022, Journal of chemical theory and computation.

[7]  Alexander L. Gaunt,et al.  Pushing the frontiers of density functionals by solving the fractional electron problem , 2021, Science.

[8]  A. Levitt,et al.  Practical error bounds for properties in plane-wave electronic structure calculations , 2021, SIAM J. Sci. Comput..

[9]  Pascal Friederich,et al.  Fast Generation of Machine Learning-Based Force Fields for Adsorption Energies. , 2021, Journal of chemical theory and computation.

[10]  J. Dambre,et al.  Modeling Electronic Response Properties with an Explicit-Electron Machine Learning Potential. , 2021, Journal of chemical theory and computation.

[11]  M. Reiher.  Molecule‐Specific Uncertainty Quantification in Quantum Chemical Studies , 2021, Israel Journal of Chemistry.

[12]  B. Kozinsky,et al.  CIDER: An Expressive, Nonlocal Feature Set for Machine Learning Density Functionals with Exact Constraints. , 2021, Journal of chemical theory and computation.

[13]  M. Ceriotti,et al.  Introduction: Machine Learning at the Atomic Scale. , 2021, Chemical reviews.

[14]  N. Marzari,et al.  Electronic-structure methods for materials design , 2021, Nature Materials.

[15]  Isaac Tamblyn,et al.  Toward Orbital-Free Density Functional Theory with Small Data Sets and Deep Learning. , 2021, Journal of chemical theory and computation.

[16]  Yong Xu,et al.  Deep-learning density functional theory Hamiltonian for efficient ab initio electronic-structure calculation , 2021, Nature Computational Science.

[17]  O. A. von Lilienfeld,et al.  Ab Initio Machine Learning in Chemical Compound Space , 2020, Chemical reviews.

[18]  Thomas F. Miller,et al.  Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states. , 2020, The Journal of chemical physics.

[19]  Edward O. Pyzer-Knapp,et al.  Welcome to the first issue of Applied AI Letters , 2020 .

[20]  Jonas A. Finkler,et al.  A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer , 2020, Nature Communications.

[21]  Andrea Grisafi,et al.  Multi-scale approach for the prediction of atomic scale properties , 2020, Chemical science.

[22]  Reiner Sebastian Sprick,et al.  A mobile robotic chemist , 2020, Nature.

[23]  Volker L. Deringer,et al.  An accurate and transferable machine learning potential for carbon. , 2020, The Journal of chemical physics.

[24]  Alexandre Tkatchenko,et al.  Accurate Many-Body Repulsive Potentials for Density-Functional Tight Binding from Deep Tensor Neural Networks. , 2020, The journal of physical chemistry letters.

[25]  Anatole von Lilienfeld,et al.  Thousands of reactants and transition states for competing E2 and S N 2 reactions , 2020, Mach. Learn. Sci. Technol..

[26]  Alice E. A. Allen,et al.  The ONETEP linear-scaling density functional theory program. , 2020, The Journal of chemical physics.

[27]  Bing Huang,et al.  Impact of non-normal error distributions on the benchmarking and ranking of quantum machine learning models , 2020, Mach. Learn. Sci. Technol..

[28]  O Anatole von Lilienfeld,et al.  Introducing Machine Learning: Science and Technology , 2020, Mach. Learn. Sci. Technol..

[29]  Alain C. Vaucher,et al.  Automated extraction of chemical synthesis actions from experimental procedures , 2019, Nature Communications.

[30]  K. Müller,et al.  Exploring chemical compound space with quantum-based machine learning , 2019, Nature Reviews Chemistry.

[31]  Sebastian Dick,et al.  Machine learning accurate exchange and correlation functionals of the electronic density , 2019, Nature Communications.

[32]  F. Noé,et al.  Deep-neural-network solution of the electronic Schrödinger equation , 2019, Nature Chemistry.

[33]  O. Anatole von Lilienfeld,et al.  Machine learning the computational cost of quantum chemistry , 2019, Mach. Learn. Sci. Technol..

[34]  Pieter P. Plehiers,et al.  A robotic platform for flow synthesis of organic compounds informed by AI planning , 2019, Science.

[35]  O. A. von Lilienfeld,et al.  Atoms in Molecules From Alchemical Perturbation Density Functional Theory. , 2019, The journal of physical chemistry. B.

[36]  Kristof T. Schütt,et al.  Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions , 2019, Nature Communications.

[37]  Justin S. Smith,et al.  Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning , 2019, Nature Communications.

[38]  A. Aspuru-Guzik,et al.  Self-driving laboratory for accelerated discovery of thin-film materials , 2019, Science Advances.

[39]  N. Sapir,et al.  Feather moult and bird appearance are correlated with global warming over the last 200 years , 2019, Nature Communications.

[40]  K. Müller,et al.  Quantum chemical accuracy from density functional approximations via machine learning , 2020, Nature Communications.

[41]  K. Sanderson.  Automation: Chemistry shoots for the Moon , 2019, Nature.

[42]  Rampi Ramprasad,et al.  Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia. , 2019, ACS applied materials & interfaces.

[43]  Ryo Nagai,et al.  Completing density functional theory by machine learning hidden messages from molecules , 2019, npj Computational Materials.

[44]  Turab Lookman,et al.  Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design , 2019, npj Computational Materials.

[45]  Leroy Cronin,et al.  Organic synthesis in a modular robotic system driven by a chemical programming language , 2019, Science.

[46]  Alberto Fabrizio,et al.  Transferable Machine-Learning Model of the Electron Density , 2018, ACS central science.

[47]  R. Sarpong,et al.  Bio-inspired synthesis of xishacorenes A, B, and C, and a new congener from fuscol† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c9sc02572c , 2019, Chemical science.

[48]  Bing Huang,et al.  Boosting Quantum Machine Learning Models with a Multilevel Combination Technique: Pople Diagrams Revisited. , 2018, Journal of chemical theory and computation.

[49]  Leroy Cronin,et al.  Controlling an organic synthesis robot with machine learning to search for new reactivity , 2018, Nature.

[50]  Thomas F. Miller,et al.  Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis. , 2018, Journal of chemical theory and computation.

[51]  Marcus Elstner,et al.  Generalized Density-Functional Tight-Binding Repulsive Potentials from Unsupervised Machine Learning. , 2018, Journal of chemical theory and computation.

[52]  Alán Aspuru-Guzik,et al.  The Matter Simulation (R)evolution , 2018, ACS central science.

[53]  Adrian E. Roitberg,et al.  Less is more: sampling chemical space with active learning , 2018, The Journal of chemical physics.

[54]  P. Ayers,et al.  Chemical transferability of functional groups follows from the nearsightedness of electronic matter , 2017, Proceedings of the National Academy of Sciences.

[55]  Bing Huang,et al.  Quantum machine learning using atom-in-molecule-based fragments selected on the fly , 2017, Nature Chemistry.

[56]  M. G. Medvedev,et al.  Density functional theory is straying from the path toward the exact functional , 2017, Science.

[57]  Raghunathan Ramakrishnan,et al.  Genetic Optimization of Training Sets for Improved Machine Learning Models of Molecular Properties. , 2016, The journal of physical chemistry letters.

[58]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[59]  O. A. von Lilienfeld,et al.  Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity. , 2016, The Journal of chemical physics.

[60]  Nicola Marzari,et al.  Materials modelling: The frontiers and the challenges. , 2016, Nature materials.

[61]  Stefano de Gironcoli,et al.  Reproducibility in density functional theory calculations of solids , 2016, Science.

[62]  M. Rupp,et al.  Machine Learning for Quantum Mechanical Properties of Atoms in Molecules , 2015, 1505.00350.

[63]  Adrienn Ruzsinszky,et al.  Strongly Constrained and Appropriately Normed Semilocal Density Functional. , 2015, Physical review letters.

[64]  Walter Thiel,et al.  Machine Learning of Parameters for Accurate Semiempirical Quantum Chemical Calculations , 2015, Journal of chemical theory and computation.

[65]  Matthias Rupp,et al.  Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach. , 2015, Journal of chemical theory and computation.

[66]  Richard J Ingham,et al.  Organic synthesis: march of the machines. , 2015, Angewandte Chemie.

[67]  Richard Van Noorden,et al.  The top 100 papers , 2014, Nature.

[68]  K. Burke.  Perspective on density functional theory. , 2012, The Journal of chemical physics.

[69]  Klaus-Robert Müller,et al.  Finding Density Functionals with Machine Learning , 2011, Physical review letters.

[70]  W. Kohn,et al.  Nearsightedness of electronic matter. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[71]  M C Payne,et al.  "Learn on the fly": a hybrid classical and quantum-mechanical molecular dynamics simulation. , 2004, Physical review letters.

[72]  Christopher H. Bryant,et al.  Functional genomic hypothesis generation and experimentation by a robot scientist , 2004, Nature.

[73]  Ann E. Mattsson,et al.  In Pursuit of the "Divine" Functional , 2002, Science.

[74]  Gerbrand Ceder,et al.  Predicting Properties from Scratch , 1998, Science.

[75]  Martin Head-Gordon,et al.  Sparsity of the Density Matrix in Kohn-Sham Density Functional Theory and an Assessment of Linear System-Size Scaling Methods , 1997 .

[76]  Klaus Schulten,et al.  A Numerical Study on Learning Curves in Stochastic Multilayer Feedforward Networks , 1996, Neural Computation.

[77]  Kohn,et al.  Density functional and density matrix method scaling linearly with the number of atoms. , 1996, Physical review letters.

[78]  Lawrence D. Jackel,et al.  Learning Curves: Asymptotic Values and Rate of Convergence , 1993, NIPS.

[79]  W. Kohn,et al.  Self-Consistent Equations Including Exchange and Correlation Effects , 1965 .

[80]  O Anatole von Lilienfeld,et al.  Quantum Machine Learning in Chemical Compound Space. , 2018, Angewandte Chemie.

[81]  P. Kirkpatrick,et al.  Chemical space , 2004, Nature.