Towards Learned Emulation of Interannual Water Isotopologue Variations in General Circulation Models

TL;DR

This paper explores machine learning methods, specifically CNNs, to emulate interannual water isotopologue variations in climate models, aiming to replace explicit physics-based simulations and improve climate data analysis.

Contribution

It demonstrates the potential of CNNs, including spherical and flat architectures, to approximate isotopic compositions in climate models, highlighting current limitations and future directions.

Findings

CNNs explain about 40% of variance in isotopic composition.

Spherical CNNs do not outperform flat UNet architectures.

Performance drops when generalizing to other climate models.

Abstract

Simulating abundances of stable water isotopologues, i.e. molecules differing in their isotopic composition, within climate models allows for comparisons with proxy data and, thus, for testing hypotheses about past climate and validating climate models under varying climatic conditions. However, many models are run without explicitly simulating water isotopologues. We investigate the possibility to replace the explicit physics-based simulation of oxygen isotopic composition in precipitation using machine learning methods. These methods estimate isotopic composition at each time step for given fields of surface temperature and precipitation amount. We implement convolutional neural networks (CNNs) based on the successful UNet architecture and test whether a spherical network architecture outperforms the naive approach of treating Earth's latitude-longitude grid as a flat image. Conducting a case study on a last millennium run with the iHadCM3 climate model, we find that roughly 40\% of the temporal variance in the isotopic composition is explained by the emulations on interannual and monthly timescale, with spatially varying emulation quality. A modified version of the standard UNet architecture for flat images yields results that are equally good as the predictions by the spherical CNN. We test generalization to last millennium runs of other climate models and find that while the tested deep learning methods yield the best results on iHadCM3 data, the performance drops when predicting on other models and is comparable to simple pixel-wise linear regression. An extended choice of predictor variables and improving the robustness of learned climate--oxygen isotope relationships should be explored in future work.