Materials Design and Informatics Group

Department of Chemistry

rutile.png

Department of Chemistry

University College London

London WC1H 0AJ

Materials Design and Informatics Group (MDIG) is a research collective, working to accelerate develoment of new green energy materials. We are based at UCL, in the Department of Chemistry.

We use a combination of data-driven methods (such as deep learning and Bayesian statistics) and quantum mechanics calculations to design new materials on computers and to help accelerate the experimental characterisation of materials. We work with other academics, national facilities and companies.

news

Feb 9, 2026 Welcome to Prakriti who has joind the group as a Postdoctoral Fellow on an EPSRC grant designing new materials for green cooling.
Feb 5, 2026 New publication alert Leveraging transfer learning for accurate estimation of ionic migration barriers in solids
Jan 30, 2026 New publication alert Self-optimizing machine learning potential assisted automated workflow for highly efficient complex systems material design
Dec 15, 2025 New publication alert The carbon cost of materials discovery: Can machine learning really accelerate the discovery of new photovoltaics?
Dec 10, 2025 New publication alert General Learning of the Electric Response of Inorganic Materials

selected publications

  1. Computational screening of all stoichiometric inorganic materials
    Daniel W Davies, Keith T Butler, Adam J Jackson, and 4 more authors
    Chem 2016
  2. Machine learning for molecular and materials science
    Keith T Butler, Daniel W Davies, Hugh Cartwright, and 2 more authors
    Nature 2018
  3. Designing interfaces in energy materials applications with first-principles calculations
    Keith T Butler, Gopalakrishnan Sai Gautam, and Pieremanuele Canepa
    npj Computational Materials 2019
  4. Distributed representations of atoms and materials for machine learning
    Luis M Antunes, Ricardo Grau-Crespo, and Keith T Butler
    npj Computational Materials 2022
  5. Entropy-based active learning of graph neural network surrogate models for materials properties
    Johannes Allotey, Keith T Butler, and Jeyan Thiyagalingam
    The Journal of Chemical Physics 2021
  6. Interpretable and explainable machine learning for materials science and chemistry
    Felipe Oviedo, Juan Lavista Ferres, Tonio Buonassisi, and 1 more author
    Accounts of Materials Research 2022