Emulation of high-resolution land surface models using sparse Gaussian processes with application to JULES

Baker, Evan; Harper, Anna B.; Williamson, Daniel; Challenor, Peter

doi:https://doi.org/10.5194/gmd-15-1913-2022

Articles | Volume 15, issue 5

https://doi.org/10.5194/gmd-15-1913-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-15-1913-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 15, issue 5

Methods for assessment of models

|

08 Mar 2022

Methods for assessment of models |

| 08 Mar 2022

Emulation of high-resolution land surface models using sparse Gaussian processes with application to JULES

Evan Baker, Anna B. Harper, Daniel Williamson, and Peter Challenor

Supplement

https://doi.org/10.5194/gmd-15-1913-2022-supplement

Data sets

Gross Primary Productivity simulations of Great Britain for emulation, 2001--2010 from JULES land surface model Evan Baker, Anna Harper, Daniel Williamson, and Peter Challenor https://doi.org/10.5285/789bea37-0450-4822-9857-3dc848feb937

Short summary

We have adapted machine learning techniques to build a model of the land surface in Great Britain. The model was trained using data from a very complex land surface model called JULES. Our model is faster at producing simulations and predictions and can investigate many different scenarios, which can be used to improve our understanding of the climate and could also be used to help make local decisions.