Long-range dispersion-inclusive machine learning potentials for structure search and optimization of hybrid organic–inorganic interfaces

J. Westermayr, S. Chaudhuri, A. Jeindl, O. T. Hofmann, R. J. Maurer, Digital Discovery DOI:10.1039/D2DD00016D (2022)

"We present an ML approach that enables fast, yet accurate, structure optimizations by combining two different types of deep neural networks trained on high-level electronic structure data. The first model is a short-ranged interatomic ML potential trained on local energies and forces, while the second is an ML model of effective atomic volumes derived from atoms-in-molecules partitioning. The latter can be used to connect short-range potentials to well-established density-dependent long-range dispersion correction methods. For two systems, specifically gold nanoclusters on diamond (110) surfaces and organic π-conjugated molecules on silver (111) surfaces, we show the ability of the models to deliver highly efficient structure optimizations and semi-quantitative energy predictions of adsorption structures."

Roadmap on Machine Learning in Electronic Structure

Kulik et al., IOP Electronic Structure DOI: 10.1088/2516-1075/ac572f (2022)

"A perspective roadmap that covers the present role and future perspective of machine learning in materials property prediction, the construction of accurate force fields, the solution of the many-body problem, and big data challenges."

Physically inspired deep learning of molecular excitations and photoemission spectra

Julia Westermayr, Reinhard J. Maurer, Chemical Science 12, 10755-10764 (2021)

"In this work, we present a deep neural network that predicts charged quasiparticle excitations for large and complex organic molecules with a rich elemental diversity and a size well out of reach of accurate many body perturbation theory calculations."

Perspective on integrating machine learning into computational chemistry and materials science

Julia Westermayr, Michael Gastegger, Kristof T. Schütt, Reinhard J. Maurer, J. Chem. Phys. 154, 230903 (2021)

"As ML is becoming pervasive in electronic structure theory and molecular simulation, we provide an overview of how atomistic computational modeling is 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."

Determining the effect of hot electron dissipation on molecular scattering experiments at metal surfaces

C. L. Box, Y. Zhang, R. Yin, B. Jiang, R. J. Maurer, JACS Au 1, 164-173 (2020)

"Vibrational state-to-state scattering of NO on Au(111) provides a testing ground for developing various nonadiabatic theories, including electronic friction theory. This system is often cited as the prime example for the breakdown of electronic friction theory, a very efficient model accounting for dissipative forces on metal-adsorbed molecules due to the creation of electron-hole-pair excitations in the metal. Here we present a comprehensive quantitative analysis of the performance of molecular dynamics with electronic friction (MDEF) in describing vibrational state-to-state scattering of NO on Au(111) and connect directly to fundamental approximations. Our analysis provides a firm baseline for the future development of nonadiabatic dynamics methods to tackle problems in surface chemistry and photocatalysis."

A deep neural network for molecular wave functions in quasi-atomic minimal basis representation

M. Gastegger, A. McSloy, M. Luya, K. T. Schütt, R. J. Maurer, J. Chem. Phys 153, 044123 (2020)

"We present an adaptation of the recently proposed SchNet for Orbitals (SchNOrb) deep convolutional neural network model [Nature Commun. 10, 5024 (2019)] for electronic wave functions in an optimised quasi-atomic minimal basis representation. For five organic molecules ranging from 5 to 13 heavy atoms, the model accurately predicts molecular orbital energies and wavefunctions and provides access to derived properties for chemical bonding analysis. Particularly for larger molecules, the model outperforms the original atomic-orbital-based SchNOrb method in terms of accuracy and scaling. "

A symmetry adapted high dimensional neural network representation of electronic friction tensor of adsorbates on metals

Yaolong Zhang, Reinhard J. Maurer, Bin Jiang, J. Chem. Phys., just accepted (2019)

"In this work, we develop a new symmetry-adapted neural network representation of electronic friction, based on our recently proposed embedded atom neural network (EANN) framework. Unlike previous methods, our new approach can readily include both molecular and surface degrees of freedom, regardless of the type of surface. Tests on the H2+Ag(111) system show that this approach yields an accurate, efficient, and continuous representation of electronic friction, making it possible to perform large scale TDPT-based MDEF simulations to study both adiabatic and nonadiabatic energy dissipation in a unified framework."

Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions

Kristof T. Schütt, Michael Gastgger, Alexandre Tkatchenko, Klaus-Robert Müller, Reinhard J. Maurer, Nature Commun. 10, 5024 (2019)

"Here we present a deep machine learning framework for the prediction of the quantum mechanical wavefunction in a local basis of atomic orbitals from which all other ground-state properties can be derived. This approach retains full access to the electronic structure via the wavefunction at force-field-like efficiency and captures quantum mechanics in an analytically differentiable representation. On several examples, we demonstrate that this opens promising avenues to perform inverse design of molecular structures for targeting electronic property optimisation and a clear path towards increased synergy of machine learning and quantum chemistry."