Machine learning for electronically excited states of molecules

Abstract

Electronically excited states of molecules are at the heart of photochemistry, photophysics, as well as photobiology and also play a role in material science. Their theoretical description requires highly accurate quantum chemical calculations, which are computationally expensive. In this review, we focus on how machine learning is employed not only to speed up such excited-state simulations but also how this branch of artificial intelligence can be used to advance this exciting research field in all its aspects. Discussed applications of machine learning for excited states include excited-state dynamics simulations, static calculations of absorption spectra, as well as many others. In order to put these studies into context, we discuss the promises and pitfalls of the involved machine learning techniques. Since the latter are mostly based on quantum chemistry calculations, we also provide a short introduction into excited-state electronic structure methods, approaches for nonadiabatic dynamics simulations and describe tricks and problems when using them in machine learning for excited states of molecules.

References in corpus (145)

• XGBoost: A Scalable Tree Boosting System
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Machine learning and the physical sciences
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Kernel methods in machine learning
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Training deep neural networks for the inverse design of nanophotonic structures
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Progress in Time-Dependent Density-Functional Theory
• Crystal Nucleation in Liquids: Open Questions and Future Challenges in Molecular Dynamics Simulations
• Machine learning for molecular simulation
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Less is more: sampling chemical space with active learning
• Machine Learning Unifies the Modelling of Materials and Molecules
• Deep learning for molecular design - a review of the state of the art
• By-passing the Kohn-Sham equations with machine learning
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Active learning of linearly parametrized interatomic potentials
• Machine-learning based interatomic potential for amorphous carbon
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Nuclear quantum effects enter the mainstream
• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Exact factorization of the time-dependent electron-nuclear wavefunction
• Machine learning a general purpose interatomic potential for silicon
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning
• i-PI 2.0: A Universal Force Engine for Advanced Molecular Simulations
• Automated Selection of Active Orbital Spaces
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• FCHL revisited: faster and more accurate quantum machine learning
• Prediction model of band-gap for AX binary compounds by combination of density functional theory calculations and machine learning techniques
• Alchemical and structural distribution based representation for improved QML
• The Density Matrix Renormalization Group in Chemistry and Molecular Physics: Recent Developments and New Challenges
• Hierarchical modeling of molecular energies using a deep neural network
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• A general method to describe intersystem crossing dynamics in trajectory surface hopping
• Electronic Spectra from TDDFT and Machine Learning in Chemical Space
• A Transferable Machine-Learning Model of the Electron Density
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• i-PI: A Python interface for ab initio path integral molecular dynamics simulations
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Symmetries and many-body excited states with neural-network quantum states
• Perspectives on double-excitations in TDDFT
• Delta Self-Consistent Field as a method to obtain potential energy surfaces of excited molecules on surfaces
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• De novo exploration and self-guided learning of potential-energy surfaces
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• Data-driven learning of total and local energies in elemental boron
• Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
• Extending the Accuracy of the SNAP Interatomic Potential Form
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Machine learning enables long time scale molecular photodynamics simulations
• On the Completeness of Atomic Structure Representations
• Predicting Electronic Structure Properties of Transition Metal Complexes with Neural Networks
• An Efficient Matrix Product Operator Representation of the Quantum-Chemical Hamiltonian
• High-performance solution of hierarchical equations of motions for studying energy-transfer in light-harvesting complexes
• Inclusion of machine learning kernel ridge regression potential energy surfaces in on-the-fly nonadiabatic molecular dynamics simulation
• Atom-Density Representations for Machine Learning
• Pushing Configuration-Interaction to the Limit: Towards Massively Parallel MCSCF Calculations
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Representing molecule-surface interactions with symmetry-adapted neural networks
• Gaussian Process Regression for Geometry Optimization
• Troubleshooting Time-Dependent Density-Functional Theory for Photochemical Applications: Oxirane
• Quantitative wave function analysis for excited states of transition metal complexes
• Ultrafast Internal Conversion in Ethylene I. The Excited State Lifetime
• Efficient Bayesian Inference of Atomistic Structure in Complex Functional Materials
• Non-adiabatic Effects in the Dissociation of Oxygen Molecules at the Al(111) Surface
• Solving the Bose-Hubbard model with machine learning
• Machine Learning Exciton Dynamics
• Multi-reference perturbation theory with Cholesky decomposition for the density matrix renormalization group
• Deep Learning and Density Functional Theory
• Operators in Machine Learning: Response Properties in Chemical Space
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Efficient non-parametric fitting of potential energy surfaces for polyatomic molecules with Gaussian processes
• Accelerating CALYPSO Structure Prediction by Data-driven Learning of Potential Energy Surface
• Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials
• Machine learning applied to single-shot x-ray diagnostics in an XFEL
• Bayesian machine learning for quantum molecular dynamics
• Gaussian approximation potential modeling of lithium intercalation in carbon nanostructures
• A local Bayesian optimizer for atomic structures
• Using Gaussian Process Regression to Simulate the Vibrational Raman Spectra of Molecular Crystals
• Fingerprints for spin-selection rules in the interaction dynamics of O2 at Al(111)
• Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
• Automated Identification of Relevant Frontier Orbitals for Chemical Compounds and Processes
• Perspective: Essentials of Relativistic Quantum Chemistry
• Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
• Signatures of nonadiabatic O2 dissociation at Al(111): First-principles fewest-switches study
• First-Principles Semiclassical Initial Value Representation Molecular Dynamics
• Metadynamics for Training Neural Network Model Chemistries: a Competitive Assessment
• Perspective: Accurate ro-vibrational calculations on small molecules
• Ultrafast Internal Conversion in Ethylene. II. Mechanisms and Pathways for Quenching and Hydrogen Elimination
• Chemical diversity in molecular orbital energy predictions with kernel ridge regression
• When do we need to account for the geometric phase in excited state dynamics ?
• Measuring Multi-Configurational Character by Orbital Entanglement
• Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
• Equation of state of fluid methane from first principles with machine learning potentials
• Neural networks and kernel ridge regression for excited states dynamics of CH${}_2$NH${}_2^{+}$: From single-state to multi-state representations and multi-property machine learning models
• Comparing the Accuracy of High-Dimensional Neural Network Potentials and the Systematic Molecular Fragmentation Method: A Benchmark Study for all-trans Alkanes
• Symmetry-Adapted High Dimensional Neural Network Representation of Electronic Friction Tensor of Adsorbates on Metals
• Assessing computationally efficient isomerization dynamics: Delta-SCF density-functional theory study of azobenzene molecular switching
• Machine learning and excited-state molecular dynamics
• Towards a formal definition of static and dynamic electronic correlations
• A machine learning-based selective sampling procedure for identifying the low energy region in a potential energy surface: a case study on proton conduction in oxides
• A Walk Through the Approximations of Ab Initio Multiple Spawning
• Nonadiabatic ab initio molecular dynamics including spin-orbit coupling and laser fields
• Bayesian optimization for the inverse scattering problem in quantum reaction dynamics
• Automatically growing global reactive neural network potential energy surfaces: a trajectory free active learning strategy
• Excitation of Nucleobases from a Computational Perspective II: Dynamics
• A nonorthogonal state-interaction approach for matrix product state wave functions
• Photoelectron Spectra of 2-Thiouracil, 4-Thiouracil and 2,4-Dithiouracil
• Strong Vibrational Relaxation of NO Scattered from Au(111): Importance of an Accurate Adiabatic Potential Energy Surface
• Quantifying Chemical Structure and Atomic Energies in Amorphous Silicon Networks
• Machine learning density functional theory for the Hubbard model
• A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
• Excited-state potential-energy surfaces of metal-adsorbed organic molecules from Linear Expansion Δ-Self-Consistent Field Density-Functional Theory (ΔSCF-DFT)
• Why do mixed quantum-classical methods describe short-time dynamics through conical intersections so well? Analysis of geometric phase effects
• The DNA Nucleobase Thymine in Motion - Intersystem Crossing Simulated with Surface Hopping
• Transcorrelated Density Matrix Renormalization Group
• Dynamical Insights into the Decomposition of 1,2-Dioxetane
• How Do Methyl Groups Enhance the Triplet Chemiexcitation Yield of Dioxetane?
• Constraining chemical networks inAstrochemistry
• On-the-fly ab initio three thawed Gaussians approximation: A semiclassical approach to Herzberg-Teller spectra
• Approximate analytical gradients and nonadiabatic couplings for the state-average density matrix renormalization group self-consistent field method
• Nonadiabatic dynamics and multiphoton resonances in strong field molecular ionization with few cycle laser pulses
• Wasserstein metric for improved QML with adjacency matrix representations
• Excitonic Wave Function Reconstruction from Near-Field Spectra Using Machine Learning Techniques
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights

Cited by in corpus (53)

• Machine Learning Force Fields
• Physics-inspired structural representations for molecules and materials
• SELFIES and the future of molecular string representations
• A practical guide to machine learning interatomic potentials -- Status and future
• Perspective on integrating machine learning into computational chemistry and materials science
• Quantum Machine Learning for Chemistry and Physics
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Excited state, non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential
• Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
• Physically inspired deep learning of molecular excitations and photoemission spectra
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Roaming leads to amino acid photodamage: A deep learning study of tyrosine
• Machine Learning of Free Energies in Chemical Compound Space Using Ensemble Representations: Reaching Experimental Uncertainty for Solvation
• The quest to simulate excited-state dynamics of transition metal complexes
• Accurate Computation of Quantum Excited States with Neural Networks
• BuRNN: Buffer Region Neural Network Approach for Polarizable-Embedding Neural Network / Molecular Mechanics Simulations
• Lifelong Machine Learning Potentials
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Roadmap for Molecular Benchmarks in Nonadiabatic Dynamics
• A comparative study of different machine learning methods for dissipative quantum dynamics
• MLatom software ecosystem for surface hopping dynamics in Python with quantum mechanical and machine learning methods
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Fewest-Switches Surface Hopping with Long Short-Term Memory Networks
• Multi-Fidelity Machine Learning for Excited State Energies of Molecules
• Automated Exploration of Reaction Network and Mechanism via Meta-dynamics Nanoreactor
• Reinforcement learning for traversing chemical structure space: Optimizing transition states and minimum energy paths of molecules
• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• Quantum algorithms for scientific computing
• Ground and Excited States from Ensemble Variational Principles
• Ab initio machine learning of phase space averages
• Unified Deep Learning Framework for Many-Body Quantum Chemistry via Green's Functions
• Optimized Multifidelity Machine Learning for Quantum Chemistry
• Accelerating Electronic Stopping Power Predictions by 10 Million Times with a Combination of Time-Dependent Density Functional Theory and Machine Learning
• Improved decision making with similarity based machine learning: Applications in chemistry
• Weighted Active Space Protocol for Multireference Machine-Learned Potentials
• Exciting DeePMD: Learning excited state energies, forces, and non-adiabatic couplings
• Decoding Energy Decomposition Analysis: Machine-Learned Insights on the Impact of the Density Functional on the Bonding Analysis
• Machine Learning Framework for Modeling Exciton-Polaritons in Molecular Materials
• Optical line shapes of color centers in solids from classical autocorrelation functions
• Quantum Algorithm for Vibronic Dynamics: Case Study on Singlet Fission Solar Cell Design
• Molecular Hessian matrices from a machine learning random forest regression algorithm
• Investigating Data Hierarchies in Multifidelity Machine Learning for Excitation Energies
• Machine learning for predicting control landscape maps of quantum molecular dynamics: Laser-induced three-dimensional alignment of asymmetric top molecules
• Assessing Non-Nested Configurations of Multifidelity Machine Learning for Quantum-Chemical Properties
• Translational eigenstates of He@C${}_{60}$ from four-dimensional \textit{ab initio} Potential Energy Surfaces interpolated using Gaussian Process Regression
• Machine-Learned Potentials for Solvation Modeling
• Machine Learning Photodynamics Unveils a Controlled H${}_2$ Loss Channel in Methaniminium Cation
• Data-Driven Modeling of S0 -> S1 Excitation Energy in the BODIPY Chemical Space: High-Throughput Computation, Quantum Machine Learning, and Inverse Design
• HOAX: A Hyperparameter Optimization Algorithm Explorer for Neural Networks
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• Imaginary Time Spectral Transforms for Excited State Preparation
• Electronic excited states in deep variational Monte Carlo