We are delighted to welcome you to our AIchemy Hub’s monthly webinar series.
This month’s talks:
James Odgers – Approximate Bayesian Inference for Spectroscopy with Varying Pure Component Signals
Spectroscopy is a widely applied technique for monitoring chemical processes and the physics underpinning the technique is well understood. However, when making quantitative predictions the physical basis for spectroscopy is typically discarded due to complex effects of the environment on the observed spectral signals. In this work we present a non-parametric Bayesian approach to model the effects of changing conditions, allowing an interpretable, physics informed model to be applied in more challenging situations.
Prof. Abigail Doyle – Development of ML methods for reaction optimization and prediction
Machine learning (ML), the development and study of computer algorithms that learn from data, is increasingly important across a wide array of applications, from virtual personal assistants to social media and product recommendation systems. ML methods have also driven key developments in the natural sciences: virtual screening of drug-like molecules for medical applications, rapid prediction of physical data, and computer-aided synthesis planning have all been facilitated by ML. The development of ML tools for synthetic methodology development and catalysis could enable chemists to make data-efficient choices and learn from that data in the course of reaction prediction, reaction condition optimization, and mechanistic interrogation. This lecture will describe my group’s efforts to develop and apply open-source data science tools to numerous aspects of synthetic methodology development, including substrate scope design, ligand discovery, reaction optimization and mechanistic elucidation.
Following the presentations, there will be time for questions from the audience.
We look forward to having you attend the event!
James Odgers
PhD Student
Abigail Doyle
Professor of Chemistry
