# Computationally-Efficient Climate Predictions using Multi-Fidelity Surrogate Modelling

arXiv: https://arxiv.org/abs/2109.07468 · HTML: https://mlsanity.com/paper/2109.07468/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 20 references that are in the map.
- First posted on arXiv 3 Aug 2021.

## Builds on (most cited first, 3 of 3)

- [Batch simulations and uncertainty quantification in Gaussian process surrogate approximate Bayesian computation](https://mlsanity.com/paper/1910.06121/) (2019)
- [ε-shotgun: ε-greedy Batch Bayesian Optimisation](https://mlsanity.com/paper/2002.01873/) (2020)
- [Computer model calibration with large non-stationary spatial outputs: application to the calibration of a climate model](https://mlsanity.com/paper/1604.04478/) (2016)

## Abstract (arXiv)

Accurately modelling the Earth's climate has widespread applications ranging from forecasting local weather to understanding global climate change. Low-fidelity simulations of climate phenomena are readily available, but high-fidelity simulations are expensive to obtain. We therefore investigate the potential of Gaussian process-based multi-fidelity surrogate modelling as a way to produce high-fidelity climate predictions at low cost. Specifically, our model combines the predictions of a low-fidelity Global Climate Model (GCM) and those of a high-fidelity Regional Climate Model (RCM) to produce high-fidelity temperature predictions for a mountainous region on the coastline of Peru. We are able to produce high-fidelity temperature predictions at significantly lower computational cost compared to the high-fidelity model alone: our predictions have an average error of 15.62^circC2 yet our approach only evaluates the high-fidelity model on 6% of the region of interest.