The Next Generation of Surrogate Modelling in Environmental Science

9th - 11th July 2018
The Welcome Centre, Lancaster University

The workshop brought together statisticians, computer scientists and environmental modellers to discuss how we could work more effectively together, with a particular focus on surrogate models.  

Models that are used to simulate different parts of the earth system are essential tools for overcoming environmental challenges (e.g. climate change or air pollution). However, these models are often slow to run, meaning that they are limited in terms of:

(i) the level of spatial and temporal resolution they can operate at
(ii) the number of runs that can be carried out for comprehensive quantification of model uncertainty

For example, a typical global atmospheric chemistry-climate model may take 24 hours of computer time to complete a one-year simulation, half of which is used in solving the extensive system of differential equations needed to represent the chemistry. A solution is to replace the slowest part of the model with a simpler statistical model called a Gaussian process emulator. However, carrying this out presents a major challenge: the outputs of the part of the complex model that we are emulating are typically multivariate. The covariances between the different output variables cannot be ignored – as is commonly done in current uses of emulators – because these outputs are used for further calculations in other parts of the model.

The workshop welcomed almost 40 researchers from academia and industry, half of whom were external to the university. It involved 12 excellent talks which were followed by two half days of some very useful discussions. We agreed on two activities following on from this workshop:

(i) the planning and implementation of a ‘surrogate modelling competition’ with prizes to be donated by an industry partner
(ii) a review paper to discuss how we can bring together applied science modellers (who want to use surrogate models) and those who currently use surrogate models (e.g. statisticians)

If you would like to be involved in any of these follow-on activities or you would like more details about the workshop, please e-mail Ed at


A full list of abstracts and biographies are available here.

Oliver WildAtmospheric Chemistry Modelling
Lancaster University
Presentation / Video

Amber Leeson
Challenges in modelling future Ice Sheet Change

Lancaster University
Presentation / Video

Anna Harper
Modelling land surface processes with JULES

University of Exeter
Presentation / Video

Chris Nemeth
An introduction to Gaussian processes and a little bit of big data
Lancaster University
Presentation / Video

Ed RyanUsing a Gaussian process emulator to “open the hood” on an atmospheric chemical transport model
Lancaster University
Presentation / Video

Jill JohnsonUsing Gaussian process emulators to evaluate and constrain uncertainty in a global aerosol model
University of Leeds

James SalterEmulation and calibration for high-dimensional output: optimal basis selection
Exeter University

Javier GonzálezCurrent applications of GP emulators involving multivariate output in model optimisation problems
Amazon, Cambridge UK

Vincent DutordoirDeep Gaussian Processes for Non-Stationary Surrogate Modelling
Presentation / Audio

Laura MansfieldPredicting global climate response to emissions without running complex climate models: Some first steps
University of Reading

Stefano MarelliCompressive polynomial chaos expansions for high-dimensional-output models
ETH Zurich
Presentation / Audio

James HensmanGaussian processes: powerful, elegant, and now practical
Presentation / Audio


Ed is a senior research associate at Lancaster University. His current research uses Gaussian process emulators to carry out sensitivity analysis, uncertainty analysis and model calibration of atmospheric chemical transport models. For more information, please see

Oliver is Professor of Atmospheric Chemistry at Lancaster University. His research involves developing and applying numerical models of atmospheric processes to learn more about atmospheric composition, chemistry and transport, and to understand how natural and anthropogenic emissions of trace gases affect regional air quality and global climate. For more information, please see