Machine Learning and Hybrid Modelling for Reaction Engineering

Dr. Dongda Zhang is a Lecturer at Department of Chemical Engineering, the University of Manchester. His research focuses on the application of hybrid modelling and data intelligence in complex reaction systems. These include chemical and biochemical process modelling, optimisation, control, and data analytics. He completed his PhD research at the University of Cambridge within two years and graduated after the university special approval on Thesis Early Submission (2016). He is an Honorary Research Fellow at Imperial College London, a member of the UK Biotechnology and Biological Sciences Research Council Pool of Experts, a member of Editorial Board for ‘Biochemical Engineering Journal’, an Associate Editor of ‘Digital Chemical Engineering’, and a member of the Industrial Management Board for the Centre for Process Analytics and Control Technology. Dr Ehecatl Antonio Del Rio Chanona is a Lecturer at the Department of Chemical Engineering and the Sargent Centre for Process Systems Engineering, Imperial College London. His research interests include the application of optimisation and machine learning techniques to chemical engineering systems. He has been in receipt of numerous awards including the fellowship from the UK Engineering and Physical Sciences Research Council (2017), the Danckwerts-Pergamon Prize at the University of Cambridge (2017), the Sir William Wakeham award at Imperial College London (2019), and the Nicklin Medal by the Institution of Chemical Engineers in recognition for exceptional research that will have significant impact in areas of process systems engineering and adoption of intelligent and autonomous learning algorithms to chemical engineering (2020).

Physical Model Construction;Data-driven Model Construction;Hybrid Model Construction;Model Structure Identification;Model Uncertainty Analysis;Interpretable Machine Learning for Kinetic Rate Model Discovery;Graph Neural Networks for the Prediction of Molecular Structure–Property Relationships;Reaction Network Simulation and Model Reduction;Hybrid Modelling Under Uncertainty: Effects of Model Greyness, Data Quality and Data Quantity;A Data-efficient Transfer Learning Approach for New Reaction System Predictive Modelling;Constructing Time-varying and History-dependent Kinetic Models via Reinforcement Learning;Surrogate and Multiscale Modelling for (Bio)reactor Scale-up and Visualisation;Statistical Design of Experiments for Reaction Modelling and Optimisation;Autonomous Synthesis and Self-optimizing Reactors;Industrial Data Science for Batch Reactor Monitoring and Fault Detection