For best experience please turn on javascript and use a modern browser!
You are using a browser that is no longer supported by Microsoft. Please upgrade your browser. The site may not present itself correctly if you continue browsing.
Van 't Hoff Institute for Molecular Sciences Van 't Hoff Institute for Molecular Sciences

In search of catalysts for optimal CO2 conversion using data science

Interdisciplinary PhD project in Inverse Design funded by UvA Data Science Centre

10 November 2021

A collaborative PhD project at the Van 't Hoff Institute for Molecular Sciences (HIMS) and the Informatics Institute (IvI) will research new data science methods for the discovery of novel catalysts for optimal CO2 conversion. Funded by the UvA Data Science Centre, the project is a collaboration between computational chemist Dr Bernd Ensing (HIMS, AI4Science Lab), catalysis engineer Dr Shiju Raveendran (HIMS, Catalysis Engineering), and machine learning experts Prof. Max Welling and Dr Jan-Willem van de Meent (IvI, AMLAB).
graphic representation of the research project
Traditionally, experiments and molecular modelling are used to measure the properties of many materials to find the most suitable material for a desired function, for example to catalyse a chemical reaction with high efficiency. Instead, here machine learning algorithms will be developed that can learn from experimental and simulation data and predict optimal materials given the desired properties.

The UvA Data Science Centre seeks to accelerate data-driven research within the University of Amsterdam. As part of its mission to foster interdisciplinary research, it recently announced the funding of seven PhD positions researching new data science methods to tackle challenging problems in specific domains.

The PhD project awarded in the chemistry domain focuses on the development of catalytic materials that enable the use of CO2 as a building block for high value-added chemicals and fuels - instead of treating it as a waste. In an Inverse Design approach, novel machine learning approaches will be developed (e.g. deep generative modelling, deep probabilistic programming) that are able to infer optimal catalyst materials and process conditions given a set of desired chemical and process properties. 

Read more