Bayesian optimization for chemical reactions
Reaction optimization is challenging and traditionally delegated to domain experts who
iteratively propose increasingly optimal experiments. Problematically, the reaction …
iteratively propose increasingly optimal experiments. Problematically, the reaction …
Accelerating explicit solvent models of heterogeneous catalysts with machine learning interatomic potentials
Realistically modelling how solvents affect catalytic reactions is a longstanding challenge
due to its prohibitive computational cost. Typically, an explicit atomistic treatment of the …
due to its prohibitive computational cost. Typically, an explicit atomistic treatment of the …
3DReact: Geometric Deep Learning for Chemical Reactions
Geometric deep learning models, which incorporate the relevant molecular symmetries
within the neural network architecture, have considerably improved the accuracy and data …
within the neural network architecture, have considerably improved the accuracy and data …
Comment on 'physics-based representations for machine learning properties of chemical reactions'
In a recent article in this journal, van Gerwen et al (2022 Mach. Learn.: Sci. Technol. 3
045005) presented a kernel ridge regression model to predict reaction barrier heights. Here …
045005) presented a kernel ridge regression model to predict reaction barrier heights. Here …
Bayesian optimisation for additive screening and yield improvements–beyond one-hot encoding
Reaction additives are critical in dictating the outcomes of chemical processes making their
effective screening vital for research. Conventional high-throughput experimentation tools …
effective screening vital for research. Conventional high-throughput experimentation tools …
Partial density of states representation for accurate deep neural network predictions of x-ray spectra
C Middleton, BFE Curchod, TJ Penfold - Physical Chemistry Chemical …, 2024 - pubs.rsc.org
The performance of a machine learning (ML) algorithm for chemistry is highly contingent
upon the architect's choice of input representation. This work introduces the partial density of …
upon the architect's choice of input representation. This work introduces the partial density of …
Structure-free Mendeleev encodings of material compounds for machine learning
Z Zhuang, AS Barnard - Chemistry of Materials, 2023 - ACS Publications
Machine learning is a powerful tool to predict the properties of materials for a variety of
applications. However, generating data sets of carefully characterized materials can be time …
applications. However, generating data sets of carefully characterized materials can be time …
Unifying theory of electronic descriptors of metal surfaces upon perturbation
We present a unifying theory for predicting electronic descriptors (eg, the d-band center ε d)
of transition and noble metal surfaces by interpretable deep learning. Distinct from black-box …
of transition and noble metal surfaces by interpretable deep learning. Distinct from black-box …
Genetic algorithms for the discovery of homogeneous catalysts
In this account, we discuss the use of genetic algorithms in the inverse design process of
homogeneous catalysts for chemical transformations. We describe the main components of …
homogeneous catalysts for chemical transformations. We describe the main components of …
Putting Chemical Knowledge to Work in Machine Learning for Reactivity
K Jorner - Chimia, 2023 - research-collection.ethz.ch
Machine learning has been used to study chemical reactivity for a long time in fields such as
physical organic chemistry, chemometrics and cheminformatics. Recent advances in …
physical organic chemistry, chemometrics and cheminformatics. Recent advances in …