Automated Knowledge Discovery
Automated knowledge discovery streamlines the process of identifying meaningful mathematical models from experimental data. By employing algorithms that can recognise patterns and derive equations, this approach facilitates the creation of predictive and interpretable models for chemical reactions. This is particularly important in fields like reaction engineering, where understanding the dynamics of chemical systems is crucial for process design, optimisation and control. Automated knowledge discovery methods not only speed up the discovery of kinetic models but also enhances our understanding of complex chemical processes through symbolic models, making them a powerful tool in chemical process development.
Miguel Ángel de Carvalho Servia
Automated Knowledge Discovery Methods in Reaction Engineering
Miguel Carvalho is a chemical engineering PhD candidate at Imperial College London, affiliated with the EPSRC CDT in Next Generation Synthesis and Reaction Technology. He earned an MEng in chemical engineering from The University of Manchester (2021) and an MRes in advanced molecular synthesis from Imperial College London (2022). His research intersects data science, chemical engineering, and chemistry, concentrating on algorithmic solutions for automated knowledge discovery in reaction engineering and catalysis.