Autonomous, AI enhanced robotic platforms for efficient and informative data collection of formulation properties

Speaker: Will Robinson (Radboud University)

Abstract:

The space of chemical structures is large, and the combinatorial space of formulations derived from it is even more so. Optimising and discovering formulations for physicla properties tailored towards specific applications is thus a complex and time-consuming process. Experimental methods are required which provide access to large, informative data reporting on properties such as surface tension, foamability, solubility and viscosity. In this talk I will present work on integrating active learning methods for experimental design with robotic platforms for autonomous data collection. The platform combines Bayesian inference, autonomous liquid handling anpendant drop tensionmetry to autonomously characterise the response of air/water surface tension to surfactant concentration. This module lays the foundation for efficiently and autonomously generating informative datasets of the interfacial properties of surfactant formulations, paving the way to the next generation of ML models for the prediction of formulation properties.

This seminar will take place in room C1.112