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

Abstract

Excited-state dynamics simulations are a powerful tool to investigate photo-induced reactions of molecules and materials and provide complementary information to experiments. Since the applicability of these simulation techniques is limited by the costs of the underlying electronic structure calculations, we develop and assess different machine learning models for this task. The machine learning models are trained on {\emph ab initio} calculations for excited electronic states, using the methylenimmonium cation (CH${}_2$NH${}_2^{+}$) as a model system. For the prediction of excited-state properties, multiple outputs are desirable, which is straightforward with neural networks but less explored with kernel ridge regression. We overcome this challenge for kernel ridge regression in the case of energy predictions by encoding the electronic states explicitly in the inputs, in addition to the molecular representation. We adopt this strategy also for our neural networks for comparison. Such a state encoding enables not only kernel ridge regression with multiple outputs but leads also to more accurate machine learning models for state-specific properties. An important goal for excited-state machine learning models is their use in dynamics simulations, which needs not only state-specific information but also couplings, i.e., properties involving pairs of states. Accordingly, we investigate the performance of different models for such coupling elements. Furthermore, we explore how combining all properties in a single neural network affects the accuracy. As an ultimate test for our machine learning models, we carry out excited-state dynamics simulations based on the predicted energies, forces and couplings and, thus, show the scopes and possibilities of machine learning for the treatment of electronically excited states.

References in corpus (17)

• The NumPy array: a structure for efficient numerical computation
• SchNet - a deep learning architecture for molecules and materials
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• FCHL revisited: faster and more accurate quantum machine learning
• Alchemical and structural distribution based representation for improved QML
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Machine learning enables long time scale molecular photodynamics simulations
• Inclusion of machine learning kernel ridge regression potential energy surfaces in on-the-fly nonadiabatic molecular dynamics simulation
• Non-adiabatic Effects in the Dissociation of Oxygen Molecules at the Al(111) Surface
• Machine Learning Exciton Dynamics
• Operators in Machine Learning: Response Properties in Chemical Space
• Bayesian machine learning for quantum molecular dynamics
• Signatures of nonadiabatic O2 dissociation at Al(111): First-principles fewest-switches study
• Perspective: Accurate ro-vibrational calculations on small molecules

Cited by in corpus (18)

• Machine learning for electronically excited states of molecules
• Neural Network Based in Silico Simulation of Combustion Reactions
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• High-Dimensional Neural Network Potentials for Magnetic Systems Using Spin-Dependent Atom-Centered Symmetry Functions
• 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
• Machine learning and excited-state molecular dynamics
• Roaming leads to amino acid photodamage: A deep learning study of tyrosine
• MLatom software ecosystem for surface hopping dynamics in Python with quantum mechanical and machine learning methods
• Multi-Fidelity Machine Learning for Excited State Energies of Molecules
• Optimized Multifidelity Machine Learning for Quantum Chemistry
• The loss of the property of locality of the kernel in high-dimensional Gaussian process regression on the example of the fitting of molecular potential energy surfaces
• A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
• Thawed Gaussian wavepacket dynamics with $\Delta$-machine learned potentials
• A simple approach to rotationally invariant machine learning of avector quantity
• XMCQDPT2-Fidelity Transfer-Learning Potentials and a Wavepacket Oscillation Model with Power-Law Decay for Ultrafast Photodynamics
• Improving Molecular Force Fields Across Configurational Space by Combining Supervised and Unsupervised Machine Learning