AI-Enhanced Bayesian Experimental Design for Reaction Kinetics: Bridging Statistics and Chemistry

Add to your list(s) Download to your calendar using vCal

• Dasha Semochkina (University of Southampton)
• Friday 27 June 2025, 12:15-12:45
• Seminar Room 1, Newton Institute.

If you have a question about this talk, please contact nobody.

RCLW03 - Accelerating statistical inference and experimental design with machine learning

Bayesian Optimal Experimental Design (BOED) provides a rigorous framework for selecting experiments that maximise expected information gain. Despite its theoretical appeal, BOED remains underutilised in applied sciences like chemistry, largely due to the significant computational demands it imposes. In this talk, I present a computationally efficient BOED framework tailored to chemical reaction kinetics. By combining Gaussian process emulation with Bayesian design principles, we reduce the cost of evaluating complex utility functions, making the design of informative experiments both tractable and practical. A key focus is on optimising control parameters to enhance the precision of kinetic parameter estimates, particularly in data-sparse experimental regimes where classical approaches struggle. This work sits at the interface of statistics, machine learning, and the physical sciences, and aims to make principled design methods more accessible to practitioners. I will discuss both methodological and applied aspects, including the integration of prior information, uncertainty quantification, and broader implications for experiment planning in scientific domains.

This talk is part of the Isaac Newton Institute Seminar Series series.

This talk is included in these lists:

• All CMS events
• Featured lists
• INI info aggregator
• Isaac Newton Institute Seminar Series
• School of Physical Sciences
• Seminar Room 1, Newton Institute
• bld31

Note that ex-directory lists are not shown.