Speeding up quantum dissipative dynamics of open systems with kernel methods DOI Creative Commons
Arif Ullah, Pavlo O. Dral

New Journal of Physics, Journal Year: 2021, Volume and Issue: 23(11), P. 113019 - 113019

Published: Oct. 22, 2021

The future forecasting ability of machine learning (ML) makes ML a promising tool for predicting long-time quantum dissipative dynamics open systems. In this article, we employ nonparametric algorithm (kernel ridge regression as representative the kernel methods) to study widely-used spin-boson (SB) model. Our model takes short-time an input and is used fast propagation dynamics, greatly reducing computational effort in comparison with traditional approaches. Presented results show that performs well both symmetric asymmetric SB models. approach not limited can be extended complex

Language: Английский

Machine Learning for Electronically Excited States of Molecules DOI Creative Commons
Julia Westermayr, Philipp Marquetand

Chemical Reviews, Journal Year: 2020, Volume and Issue: 121(16), P. 9873 - 9926

Published: Nov. 19, 2020

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

Language: Английский

Citations

349

Molecular excited states through a machine learning lens DOI
Pavlo O. Dral, Mario Barbatti

Nature Reviews Chemistry, Journal Year: 2021, Volume and Issue: 5(6), P. 388 - 405

Published: May 20, 2021

Language: Английский

Citations

181

Perspective on integrating machine learning into computational chemistry and materials science DOI Open Access
Julia Westermayr, Michael Gastegger, Kristof T. Schütt

et al.

The Journal of Chemical Physics, Journal Year: 2021, Volume and Issue: 154(23)

Published: June 21, 2021

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 the construction high-dimensional interatomic potentials. Not a day goes by without another proof principle published on how can represent predict quantum mechanical properties-be they observable, such as polarizabilities, or not, atomic charges. As is becoming pervasive simulation, we provide an overview atomistic computational modeling transformed incorporation approaches. From perspective practitioner field, assess common workflows to structure, dynamics, spectroscopy affected ML. Finally, discuss tighter lasting integration with chemistry materials science be achieved what it will mean for research practice, software development, postgraduate training.

Language: Английский

Citations

171

Choosing the right molecular machine learning potential DOI Creative Commons
Max Pinheiro, Fuchun Ge, Nicolas Ferré

et al.

Chemical Science, Journal Year: 2021, Volume and Issue: 12(43), P. 14396 - 14413

Published: Jan. 1, 2021

Quantum-chemistry simulations based on potential energy surfaces of molecules provide invaluable insight into the physicochemical processes at atomistic level and yield such important observables as reaction rates spectra. Machine learning potentials promise to significantly reduce computational cost hence enable otherwise unfeasible simulations. However, surging number begs question which one choose or whether we still need develop yet another one. Here, address this by evaluating performance popular machine in terms accuracy cost. In addition, deliver structured information for non-specialists guide them through maze acronyms, recognize each potential's main features, judge what they could expect from

Language: Английский

Citations

143

Ab Initio Machine Learning in Chemical Compound Space DOI Creative Commons
Bing Huang, O. Anatole von Lilienfeld

Chemical Reviews, Journal Year: 2021, Volume and Issue: 121(16), P. 10001 - 10036

Published: Aug. 13, 2021

Chemical compound space (CCS), the set of all theoretically conceivable combinations chemical elements and (meta-)stable geometries that make up matter, is colossal. The first-principles based virtual sampling this space, for example, in search novel molecules or materials which exhibit desirable properties, therefore prohibitive but smallest subsets simplest properties. We review studies aimed at tackling challenge using modern machine learning techniques on (i) synthetic data, typically generated quantum mechanics methods, (ii) model architectures inspired by mechanics. Such Quantum Machine Learning (QML) approaches combine numerical efficiency statistical surrogate models with an ab initio view matter. They rigorously reflect underlying physics order to reach universality transferability across CCS. While state-of-the-art approximations problems impose severe computational bottlenecks, recent QML developments indicate possibility substantial acceleration without sacrificing predictive power

Language: Английский

Citations

130

Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning DOI Creative Commons
Marcel F. Langer,

Alex Goeßmann,

Matthias Rupp

et al.

npj Computational Materials, Journal Year: 2022, Volume and Issue: 8(1)

Published: March 16, 2022

Computational study of molecules and materials from first principles is a cornerstone physics, chemistry, science, but limited by the cost accurate precise simulations. In settings involving many simulations, machine learning can reduce these costs, often orders magnitude, interpolating between reference This requires representations that describe any molecule or material support interpolation. We comprehensively review discuss current relations them, using unified mathematical framework based on many-body functions, group averaging, tensor products. For selected state-of-the-art representations, we compare energy predictions for organic molecules, binary alloys, Al-Ga-In sesquioxides in numerical experiments controlled data distribution, regression method, hyper-parameter optimization.

Language: Английский

Citations

118

SchNetPack 2.0: A neural network toolbox for atomistic machine learning DOI Open Access
Kristof T. Schütt, Stefaan S. P. Hessmann, Niklas W. A. Gebauer

et al.

The Journal of Chemical Physics, Journal Year: 2023, Volume and Issue: 158(14)

Published: March 21, 2023

SchNetPack is a versatile neural network toolbox that addresses both the requirements of method development and application atomistic machine learning. Version 2.0 comes with an improved data pipeline, modules for equivariant networks, PyTorch implementation molecular dynamics. An optional integration Lightning Hydra configuration framework powers flexible command-line interface. This makes easily extendable custom code ready complex training tasks, such as generation 3D structures.

Language: Английский

Citations

47

Automatic discovery of photoisomerization mechanisms with nanosecond machine learning photodynamics simulations DOI Creative Commons
Jingbai Li, Patrick Reiser, Benjamin R. Boswell

et al.

Chemical Science, Journal Year: 2021, Volume and Issue: 12(14), P. 5302 - 5314

Published: Jan. 1, 2021

Photochemical reactions are widely used by academia and industry to construct complex molecular architecturesviamechanisms that often inaccessible other means.

Language: Английский

Citations

79

Machine learning and excited-state molecular dynamics DOI Creative Commons
Julia Westermayr, Philipp Marquetand

Machine Learning Science and Technology, Journal Year: 2020, Volume and Issue: 1(4), P. 043001 - 043001

Published: June 12, 2020

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

Language: Английский

Citations

71

Deep learning study of tyrosine reveals that roaming can lead to photodamage DOI
Julia Westermayr, Michael Gastegger, Dóra Vörös

et al.

Nature Chemistry, Journal Year: 2022, Volume and Issue: 14(8), P. 914 - 919

Published: June 2, 2022

Language: Английский

Citations

43