Multi-Fidelity Machine Learning for Excited State Energies of Molecules

Abstract

The accurate but fast calculation of molecular excited states is still a very challenging topic. For many applications, detailed knowledge of the energy funnel in larger molecular aggregates is of key importance requiring highly accurate excited state energies. To this end, machine learning techniques can be an extremely useful tool though the cost of generating highly accurate training datasets still remains a severe challenge. To overcome this hurdle, this work proposes the use of multi-fidelity machine learning where very little training data from high accuracies is combined with cheaper and less accurate data to achieve the accuracy of the costlier level. In the present study, the approach is employed to predict the first excited state energies for three molecules of increasing size, namely, benzene, naphthalene, and anthracene. The energies are trained and tested for conformations stemming from classical molecular dynamics simulations and from real-time density functional tight-binding calculations. It can be shown that the multi-fidelity machine learning model can achieve the same accuracy as a machine learning model built only on high cost training data while having a much lower computational effort to generate the data. The numerical gain observed in these benchmark test calculations was over a factor of 30 but certainly can be much higher for high accuracy data.

References in corpus (14)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Finding Density Functionals with Machine Learning
• Machine learning for electronically excited states of molecules
• Alchemical and structural distribution based representation for improved QML
• Excitons in a Photosynthetic Light-Harvesting System: A Combined Molecular Dynamics/Quantum Chemistry and Polaron Model Study
• De novo exploration and self-guided learning of potential-energy surfaces
• Data-driven learning of total and local energies in elemental boron
• $\Delta$-Machine Learning for Potential Energy Surfaces: A PIP approach to bring a DFT-based PES to CCSD(T) Level of Theory
• Machine Learning Exciton Dynamics
• 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
• Automatically growing global reactive neural network potential energy surfaces: a trajectory free active learning strategy
• UV-Visible Absorption Spectra of Solvated Molecules by Quantum Chemical Machine Learning

Cited by in corpus (6)

• Optimized Multifidelity Machine Learning for Quantum Chemistry
• Multitask methods for predicting molecular properties from heterogeneous data
• Two-dimensional electronic spectroscopy in the condensed phase using equivariant transformer accelerated molecular dynamics simulations
• Investigating Data Hierarchies in Multifidelity Machine Learning for Excitation Energies
• All-in-one foundational models learning across quantum chemical levels
• Assessing Non-Nested Configurations of Multifidelity Machine Learning for Quantum-Chemical Properties