Nanosecond Photodynamics Simulations of a Cis-Trans Isomerization Are Enabled by Machine Learning

Li, Jingbai; Reiser, Patrick; Eberhard, André; Friederich, Pascal; López, Steven R.

doi:10.26434/chemrxiv.13047863

Cited by 4 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML shows great promise in nonadiabatic excited-state simulations 16,17 as documented by recent works using NNs to construct excited-state energy landscapes to perform fewest-switches surface hopping MD at longer time scales or with more comprehensive ensemble averaging. 66,68,217 Similar progress has been achieved in nonadiabatic dynamics at metal surfaces, where NNs have been used to construct excited-state landscapes 4,218 and continuous representations of the electronic friction tensor 219 used in molecular dynamics with electronic friction simulations 220,221 . It is evident that ML methods will play an important role in extending the range of applications for MQCD methods in the coming years.…”

Section: ML Enables Classical and Quantum Dynamics For Systems Of Unp...mentioning

confidence: 92%

Perspective on integrating machine learning into computational chemistry and materials science

Westermayr,

Gastegger,

Schütt

et al. 2021

Preprint

View full text Add to dashboard Cite

Machine learning (ML) methods are being used in almost every conceivable area of electronic structure theory and molecular simulation. In particular, ML has become firmly established in the construction of high-dimensional interatomic potentials. Not a day goes by without another proof of principle being published on how ML methods can represent and predict quantum mechanical properties -be they observable, such as molecular polarizabilities, or not, such as atomic charges. As ML is becoming pervasive in electronic structure theory and molecular simulation, we provide an overview of how various aspects of atomistic computational modelling are being transformed by the incorporation of ML approaches. From the perspective of the practitioner in the field, we assess how common workflows to predict structure, dynamics, and spectroscopy are affected by ML. Finally, we discuss how a deeper and lasting integration of ML methods with computational chemistry and materials science can be achieved and what it will mean for research practice, software development, and postgraduate training.

show abstract

Section: ML Enables Classical and Quantum Dynamics For Systems Of Unp...mentioning

confidence: 92%

Perspective on integrating machine learning into computational chemistry and materials science

Westermayr,

Gastegger,

Schütt

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A similar idea has seen previous wide use for generating the initial conditions for FSSH simulations, − though only the coordinate information is used in this study to generate the data set rather than both coordinate and velocity information as for generating the initial conditions for FSSH simulations. We also briefly mention that KRR has been recently used in combination with Wigner sampling for computing absorption cross sections, and a recent preprint has also used Wigner sampling in part to generate an initial data set for nonadiabatic machine learning-based dynamical simulation …”

Section: Theoretical Methodsmentioning

confidence: 99%

“…We also briefly mention that KRR has been recently used in combination with Wigner sampling for computing absorption cross sections, 37 and a recent preprint has also used Wigner sampling in part to generate an initial data set for nonadiabatic machine learning-based dynamical simulation. 38 However, if the true m and ω of the system are used for Wigner sampling, the resulting Gaussian is too broad to correctly sample the needed region of configurational space. Therefore, as outlined in the Supporting Information, the value of γ is fit to improve the prediction of the KRR model.…”

Section: ■ Theoretical Methodsmentioning

confidence: 99%

Mixed Quantum–Classical Dynamics with Machine Learning-Based Potentials via Wigner Sampling

Ardiansyah

Brorsen

2020

J. Phys. Chem. A

View full text Add to dashboard Cite

Machine learning-based approaches for surface hopping (SH) offer the prospect of SH simulations with ab initio accuracy, but with a computational cost more similar to classical molecular dynamics simulations. However, such approaches in the adiabatic basis are difficult due to the need to fit a machine learning model to reproduce the nonadiabatic coupling, which rapidly changes in the vicinity of a conical intersection. Previous approaches have typically dealt with this difficulty by either computing the hopping probabilities using methods that do not require the explicit nonadiabatic coupling or by employing adaptive sampling. In this study, we introduce a new approach using a simple modification of Wigner sampling to generate appropriate training data. Test SH simulations on the two-state spin-boson Hamiltonian system show that Wigner sampling with an appropriately selected data set can reduce the size of the training data set by up to a factor of 7.5 per degree of freedom compared to previously linear sampling-based approaches.

show abstract

“…As another benefit of the ML models, it was shown that a large ensemble of trajectories could be calculated, still at a lower cost than a few trajectories with the reference method. 94 Recently, Li et al 669 The performance of KRR in comparison to NNs was assessed by us together with von Lilienfeld and co-workers. 95 The operator formalism 670 and the FCHL representation 127,530 were used to fit the three singlet states of CH 2 NH 2 + using the previously generated training set of 4000 data points.…”

Section: Of Secondary Outputsmentioning

confidence: 99%

Machine Learning for Electronically Excited States of Molecules

2020

View full text Add to dashboard Cite

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 not only how machine learning is employed 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 and approaches for nonadiabatic dynamics simulations and describe tricks and problems when using them in machine learning for excited states of molecules.

show abstract

Nanosecond Photodynamics Simulations of a Cis-Trans Isomerization Are Enabled by Machine Learning

Cited by 4 publications

References 18 publications

Perspective on integrating machine learning into computational chemistry and materials science

Perspective on integrating machine learning into computational chemistry and materials science

Mixed Quantum–Classical Dynamics with Machine Learning-Based Potentials via Wigner Sampling

Machine Learning for Electronically Excited States of Molecules

Contact Info

Product

Resources

About