Optimizing Gaussian process emulation and generalized additive model fitting for rapid, reproducible earth system model analysis

Ghosh, Kunal; Regayre, Leighton A.

doi:10.5194/gmd-19-7767-2026

Articles | Volume 19, issue 16

https://doi.org/10.5194/gmd-19-7767-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-19-7767-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 19, issue 16

Development and technical paper

|

21 Aug 2026

Development and technical paper |

| 21 Aug 2026

Optimizing Gaussian process emulation and generalized additive model fitting for rapid, reproducible earth system model analysis

Kunal Ghosh and Leighton A. Regayre

Data sets

gp-gam-optimisation-dataset: Example input and output data for Gaussian Process and GAM workflow (H2SO4, January 2017) Kunal Ghosh and Leighton A. Regayre https://doi.org/10.5281/zenodo.17544324

Model code and software

gp-gam-optimisation-pipeline: High-performance workflow for Gaussian Process emulation and GAM fitting Kunal Ghosh and Leighton A. Regayre https://doi.org/10.5281/zenodo.17543623

Short summary

Understanding which parts of climate models cause uncertainty requires many large computer experiments. We developed a new workflow that greatly improves the speed and efficiency of these studies. It can analyse millions of model variations up to 25 times faster without losing accuracy, allowing scientists to explore uncertainty in more detail and make climate predictions more reliable.