skip to content

Department of Chemical Engineering and Biotechnology

The application of machine learning in (bio)chemical engineering is a rapidly developing field with a very fast pace of discovery and innovation.

We invite you to an open international conference / workshop comprising of talks, poster presentations and discussions on the topics of machine learning-based optimisation, classification and regression ML algorithms for (bio)chemical engineering applications, data mining and automation in (bio)chemical engineering, and more in-depth topics, such as specific methods of tackling various uncertainties in model development.

The event is the 2nd conference in this series and is hosted by two EPSRC projects: “Combining Chemical Robotics and Statistical Methods to Discover Complex Functional Products”, a collaboration between the Universities of Cambridge, Glasgow and Southampton, and “Cognitive Chemical Manufacturing”, a collaboration between the Universities of Leeds, Nottingham and UCL. As well as presentations from the two projects, we are inviting abstract submissions for oral and poster presentations at the conference.

There will be a dinner on the evening of Monday 8 July and lunch will be provided on both days.

The event is free but please register here


Day 1: 11:00 - 18:30 (Registration from 10:00 and buffet dinner from 18:30)

Back-off for Optimal Design of Experiments Under Structural Model Mismatch Using Gaussian Process Panagiotis Petsagkourakis, University College London

Mechanistic modelling and AI/ML: mutually exclusive or complementary? Dr Joao Moreira, PSE Ltd

Kernel-based learning approach to diesel engine emission modelling Changmin Yu, Cambridge Centre for Advanced Research and Education in Singapore (CARES Ltd)

Noisy, sparse and nonlinear: Approaching the Bermuda Triangle of physicochemical inference with deep filtering C. Poelking, Department of Chemical Engineering and Biotechnology, University of Cambridge

Real time optimization via machine learning: a Gaussian processes approach E.A. del Rio Chanona, Centre for Process Systems Engineering (CPSE), Department of Chemical Engineering, Imperial College London

Keynote talk: Machine learning computer added chemical synthesis Prof. Klavs Jensen, MIT

Synthesis prediction from an industrial drug design perspective Ola Engkvist, AstraZeneca

Confronting the unknown: uncertainty in molecular deep learning Matthew Robinson, Cavendish Laboratory, University of Cambridge

Symbolic regression for the automated physical model identification in reaction engineering Liwei Cao, Department of Chemical Engineering and Biotechnology, University of Cambridge

The metaphysics of chemical reactivity and the universal organic synthesis engine: the Chemputer Prof. Leroy Cronin, University of Glasgow

EPSRC projects updates:

Combining Chemical Robotics and Statistical Methods to Discover Complex Functional Products Prof. Alexei Lapkin

Cognitive Chemical Manufacturing Dr Richard Bourne

Day 2: 09:00 - 14:00

Invited talk: Challenges in Protein-Structure-Driven Machine Learning and Applications in Biotechnology Dr Jochen Sieg, Hamburg University.

Error-controlled exploration of chemical reaction networks with Gaussian Processes Gregor N. Simm, Department of Engineering, University of Cambridge.

Identification of strategic molecules in large reaction networks Jana Marie Weber, Department of Chemical Engineering and Biotechnology, University of Cambridge

Statistical learning through designed experiments Prof. David Woods, University of Southampton

Bridge designs for experiments with constraints and multiple responses: a case study Dr Emily Matthews, Unviersity of Southampton

LARA with SiLA2 - an integrated open source platform providing experimental data for Machine Learning / AI and cheminformatics Mark Dörr (University Greifswald)

Two-Stage Reinforcement Learning for Batch Bioprocess Optimization Under Uncertainty Panagiotis Petsagkourakis, University College of London

Deterministic global optimization with machine-learning surrogate models embedded Arthur Schweidtmann, AVT-RWTH Aachen

Deep learning based surrogate modelling and optimisation for excreted microalgal biofuel production and photobioreactor design Dongda Zhang, School of Chemical Engineering and Analytical Science, University of Manchester

EPSRC project meeting (closed event)

1. Who should attend?

Anyone interested in the application of ML/AI in (bio)chemical engineering and in predictive scalability of reactions. We welcome delegates from academia, industry and government. We are looking to bring in people with a wealth of experience in the many different subject areas that are needed so that we can form interdisciplinary partnerships and work together to further the field.

2. What will I get out of it?

You will be able to network with like-minded people who have research interests that complement yours. There will be several keynotes around the major workshop topics to spark discussion and ideas. There will be an opportunity to present your own research in oral and/or poster sessions, and there will be plenty of opportunity to have general discussions and some specific topic-based discussions in smaller groups.

3. What are the aims of this workshop?

This workshop aims to to drive progress in the area and facilitate collaboration by introducing people to make new interdisciplinary teams, and to produce new grant applications. To achieve this we may commission literature reviews, papers, or small scale investigations to test out new ideas. We welcome ideas and suggestions about how to go forward in this area and how best to achieve our aims.

4. What are the main themes of these workshops?

The main themes these workshops seek to address are: ML/AI in (bio)chemical engineering, chemical robotics, machine learning methods for process development and optimisation, model development and related topics.

5. Could I present at ‘ML/AI in (bio)chemical engineering’?

There will be opportunities to present both talks and posters. Please send a one side of A4 abstract to Prof. Alexei Lapkin, who is coordinating the organising committee of the conference, by 5 April, indicating your preference of oral/poster presentation.

6. Where do I find accommodation closest to the venue?

The event will be held in the Department of Chemical Engineering and Biotechnology, University of Cambridge, located on West Cambridge Site (Philippa Fawcett Drive, CB3 0AS). The site is easily reached from the centre of Cambridge on the University bus (U). It is about 10-15 min cycling distance from the city centre, or a 30 min walk (from Kings College’ gate). We recommend to explore available hotels using your favourite hotel booking services, but also looking specifically at listings of B&B offers by Colleges, such as B&B at Churchill College, the closest college to the event venue. 

This event is free but please register using the link below. 

Event Scientific Committee and Organisers:

Prof. Alexei Lapkin (Cambridge)

Dr Danilo Russo (Cambridge)

Dr Richard Bourne (Leeds)

Dr Federico Galvanin (University College London)

Monday, 8 July, 2019 - 11:00 to Tuesday, 9 July, 2019 - 16:00
Contact name: 
Prof Alexei Lapkin
Contact email: 
Event location: 
Department of Chemical Engineering and Biotechnology, Philippa Fawcett Drive, Cambridge, CB3 0AS

Latest news

‘Transformational’ approach to machine learning could accelerate search for new disease treatments

1 December 2021

Researchers have developed a new approach to machine learning that ‘learns how to learn’ and out-performs current machine learning methods for drug design.

Mystery of new, high-performance solar cell materials revealed in stunning clarity

22 November 2021

Researchers from our Optoelectronic Materials and Device Spectroscopy group used a suite of correlative, multimodal microscopy methods to...

Miguel Anaya awarded Royal Academy of Engineering Research Fellowship

9 November 2021

Dr Miguel Anaya, researcher with our Optoelectronic Materials and Device Spectroscopy Group, has been awarded a Research Fellowship by the Royal Academy of Engineering (RAEng), to support his development as an independent researcher.