Machine learning and excited-state molecular dynamics

Abstract

Machine learning is employed at an increasing rate in the research field of quantum chemistry. While the majority of approaches target the investigation of chemical systems in their electronic ground state, the inclusion of light into the processes leads to electronically excited states and gives rise to several new challenges. Here, we survey recent advances for excited-state dynamics based on machine learning. In doing so, we highlight successes, pitfalls, challenges and future avenues for machine learning approaches for light-induced molecular processes.

References in corpus (22)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Machine learning for molecular simulation
• Deep learning for molecular design - a review of the state of the art
• Machine-learning based interatomic potential for amorphous carbon
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• A general method to describe intersystem crossing dynamics in trajectory surface hopping
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Representing molecule-surface interactions with symmetry-adapted neural networks
• Non-adiabatic Effects in the Dissociation of Oxygen Molecules at the Al(111) Surface
• Solving the Bose-Hubbard model with machine learning
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Bayesian machine learning for quantum molecular dynamics
• Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
• 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
• Automatically growing global reactive neural network potential energy surfaces: a trajectory free active learning strategy
• A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
• The DNA Nucleobase Thymine in Motion - Intersystem Crossing Simulated with Surface Hopping
• Rapid and accurate molecular deprotonation energies from quantum alchemy
• Direct Mapping Hidden Excited State Interaction Patterns from ab initio Dynamics and Its Implications on Force Field Development

Cited by in corpus (12)

• Machine learning for electronically excited states of molecules
• Perspective on integrating machine learning into computational chemistry and materials science
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
• Roaming leads to amino acid photodamage: A deep learning study of tyrosine
• The quest to simulate excited-state dynamics of transition metal complexes
• 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
• Automated Exploration of Reaction Network and Mechanism via Meta-dynamics Nanoreactor
• Exciting DeePMD: Learning excited state energies, forces, and non-adiabatic couplings
• Theory of Moment Propagation for Quantum Dynamics in Single-Particle Description