(left) Light excites electrons in catalyst materials, which can activate chemical dynamics and facilitate chemical reactions via coupled electron-nuclear dynamics. (right) To make the time-dependent simulation of light-driven catalysis feasible, Atomic Cluster Expansion (ACE) machine learning representations will be used to construct a quantum Hamiltonian surrogate model.

Supervisors: Dr. Reinhard J. Maurer; Dr. James Kermode

Summary: Industrial catalysis must become sustainable within our lifetime. This means creating renewable fuels and fertilizer to ensure food safety from clean energy such as sunlight and sustainable feedstocks such as atmospheric CO₂ and N₂. To achieve this, we need to be able to understand the mechanisms behind photocatalytic processes and how light excitation can selectively break chemical bonds. This is currently limited by the sheer computational cost of quantum mechanical simulation of light-driven chemistry. The aim of this project will be to create and apply machine learning models that emulate the quantum mechanical interaction between light and molecules at surfaces.

Background: Industrial catalysis must become sustainable within our lifetime. This means creating renewable fuels and fertilizer to ensure food safety from clean energy such as sunlight and sustainable feedstocks such as atmospheric CO₂ and N₂. To achieve this, we need to be able to understand the mechanisms behind photocatalytic processes and how light excitation can selectively break chemical bonds. This is currently limited by the sheer computational cost of quantum mechanical simulation of light-driven chemistry. The aim of this project will be to create and apply machine learning models that emulate the quantum mechanical interaction between light and molecules at surfaces.

Machine learning (ML) methods are revolutionising the physical sciences, for example interatomic potential representations are becoming a common approach to accelerate molecular dynamics simulations. It was recently shown that ML methods can even reconstruct quantum mechanical Hamiltonians of molecules [1] and provide models of multiple electronic states [2]. ML-based surrogate models need to be able to replicate electronic structure results with a precision of a few meV to be reliable.

Research Question for the PhD project: · Is the equivariant matrix ACE representation [6] able to capture the electronic structure and energy landscape of a metal nanocatalyst? · What and how much training data is required to generate a faithful representation of electronic structure of a molecule-metal interface? · Can we predict measurable reaction rates of light-driven catalysis by performing time-dependent quantum dynamics simulations with ML surrogate Hamiltonians?

In this project, you will develop a new machine learning representation of quantum mechanical Hamiltonians for condensed phase systems that is able to capture the electronic structure of metal nanoparticles molecule-metal nanocatalyst systems. You will generate training data based on Density Functional Theory and learn how to build such models based on the Atomic Cluster Expansion (ACE) formalism [3,4]. Once the models are constructed and validated, you will apply them to simulate different dynamical processes such as light-driven defect propagation and light-driven ultrafast dynamics of molecules at surfaces.

 

References:

[1] Schütt et al. „Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions“, Nature Commun. 10, 5024 (2019), https://www.nature.com/articles/s41467-019-12875-2

[2] Westermayr, Maurer, „Physically inspired deep learning of molecular excitations and photoemission spectra”, Chem. Sci. 12, 10755-10764 (2021), https://pubs.rsc.org/en/content/articlelanding/2021/sc/d1sc01542g

[3] Dusson et al. “Atomic Cluster Expansion: Completeness, Efficiency, and Stability”, arXiv:1911.03550, https://arxiv.org/abs/1911.03550

[4] Drautz „Atomic cluster expansion of scalar, vectorial, and tensorial properties including magnetism and charge transfer”, Phys. Rev. B 102, 024104 (2020), https://journals.aps.org/prb/abstract/10.1103/PhysRevB.102.024104