Scientific Machine Learning at University of Leeds


Welcome to the website for people interested in scientific machine learning (SciML) at Leeds (SciML is the discipline of combining machine learning with scientific computing see e.g. for an overview). This website serves to organise our work and allow others to join us.

If you’re based at Leeds and would like to join:

  • you can simply make a pull-request to add yourself to this website:
  • or instead of a pull request, use the automated form here

We meet the first Friday of every month at 11am UK/local time in our home in LIDA (Leeds Institute for Data Analytics), Worsley Building, 11th Floor, room 11.87. (.ics-file download to add the event to your calendar). We also organise seminars and workshops, as well as send out a monthly newsletter.

View the SciML newsletter archives here.


  • Leif Denby

    Self-supervised/unsupervised learning, convolutional networks

    meso-scale cloud organisation, denoising of LIDAR water vapour observations

  • Chetan Deva

    Random Forests, XGBoost, Long Short-Term Memory

    Modelling Plant Behaviour across G*E, Time Series Forecasting of Vegetation Dynamics

  • Samuel Bancroft

    Semi-supervised/self-supervised learning, convolutional networks

    crop type classification, satellite time series classification, crop yield estimation

  • Jonathan Coney

    Supervised learning, convolutional networks

    segmentation of atmospheric gravity waves, learning physical characteristics from model output

  • Trystan Surawy-Stepney

    Weakly-supervised learning, Convolutional networks, Numerical modelling

    Glacier damage identification, SAR data, Glacial process modelling

  • Ben Wallis

    Supervised learning, Convolutional networks, Bayesian methods

    Tidewater glacier dynamics, Ice ocean interaction

  • Joey Smith

    Random Forests, GANs

    Storm tracking and initiation prediction, Precipitation nowcasting

  • Maria Luisa Taccari

    Operator learning, PINNs, Supervised learning, Convolutional networks

    Groundwater prediction, Surrogate modelling

  • Calum S. Skene

    Neural networks, Neural operators, Reservoir computing

    Geophysical and astrophysical turbulence

  • Dody Dharma

    Supervised learning, Continuous Convolution, Graph Neural Networks, Multilayer Perceptron, LSTM

    Deformbale Solid and Fluid Simulation, Vorticity Conservation

  • Naomi Shakespeare-Rees

    PINN's, Convolutional Networks

    Geomagnetic fields, Core Flows

  • Shenghao Qiu

    Machine learning Compiler, Graph Neural Network, Self-supervised learning, Convolutional Networks

    Parallel and Distributed Deep Learning, Models acceleration, Tensors and models backend graph optimization

  • Shu Zhang

    Random Forests, XGBoost, LSTM

    Tropospheric ozone forcast, Weather classification, Time series decomposition of air pollutants

  • Phil Livermore

    Physics informed neural networks

    Reconstruction of earth/planetary magnetic fields from sparse data, deep earth geophysics, inverse theory

  • Jakub Lewandowski

    Supervised learning, physics-informed neural networks

    Weather nowcasting, parametrization of atmospheric processes

  • Joe Gallear

    Supervised learning, neural networks, random forests

    Crop yield estimation, impacts of climate variability, effects of extreme events

  • Sam Llanwarne

    Neural Networks, Segmentation, auto-encoding, classification, Want to use transformers and graphs more

    very large histology tissue image, preprocessing and classification

  • Andy Nowacki

    Neural networks, classification

    Detection and location of earthquakes and icequakes, subsurface structure and characterisation

  • John Chong Zhang

    Neural networks, inversions, filters

    mineral system exploration, subsurface structure, geophysical potential fields

  • Miranda Horne

    Operator Learning, Physics Constrained Neural Networks

    Computational Fluid Dynamics, Inverse Modelling, Interior Air Control

  • Longwei Chen

    Physics-informed neural networks, deeponet, Bayesian PINN

    Planetary magnetic field modelling, asteroid gravity modelling, geophysical inverse problem

  • Leyuan Wu

    Physics informed neural networks

    Earth and planets' gravity field modelling

  • Jack Smith

    Cnns, synthetic data, gans

    Semantic segmentation of masonry lined tunnel joints, structural condition assessment

  • Fergus Shone

    Informed machine learning, Physics-informed neural networks

    Haemodynamic flow super-resolution, 4D-flow MRI, Left ventricular remodelling

  • Alhanof Alolyan

    Deep reinforcement learning, deep learning

    Computer-aided design, crowd simulation

  • Claire Bartholomew

    Supervised learning, CNNs

    Precipitation nowcasting, Convection / thunderstorm prediction

  • Jacob Connolly

    Supervised learning, Random Forests

    InSAR Time series, Noise reduction in SAR data

  • Andy Hooper

    Ica, deep learning,

    Radar interferometry (insar), volcano deformation, tectonic deformation

  • Mark Richardson

    Fortran, mpi, openmp

    Met office um, dynamo, cesm

  • Eric Atwell

    Text analytics, sketchengine, chatbots

    University teaching and assessment, understanding quran and hadith, detecting bias and fake news

  • Simon Peatman

    Neural networks

    Classification of convective weather systems

  • Andy Turner

    Multi-layered Perceptron, Fuzzy Inference

    Predicting spatial and temporal change, Forecasting climate change impacts, River level forecating