Estimating carbon pools in the shelf sea environment: reanalysis or model-informed machine learning?

TL;DR

This paper introduces a neural network ensemble approach to estimate carbon pools in shelf seas, providing a cost-effective alternative to reanalyses and enhancing understanding of carbon cycle dynamics with uncertainty quantification.

Contribution

It presents a novel application of model-informed deep ensemble learning to estimate shelf sea carbon pools, improving accuracy and uncertainty assessment over traditional reanalysis methods.

Findings

Deep ensembles accurately reproduce reanalysis outputs for carbon pools.

The approach offers uncertainty quantification for carbon pool estimates.

Potential for scenario analysis in climate change studies.

Abstract

Shelf seas are important for carbon sequestration and carbon cycle, but shelf sea observations for carbon pools are often sparse, or highly uncertain. Alternative can be provided by reanalyses, but these are often expensive to run. We propose to use an ensemble of neural networks (i.e. deep ensemble) to learn from a coupled physics-biogeochemistry model the relationship between the directly observable variables and carbon pools. We demonstrate for North-West European Shelf (NWES) sea environment, that when the deep ensemble trained on a model free run simulation is applied to the NWES reanalysis, it is capable to reproduce the reanalysis outputs for carbon pools and additionally provide uncertainty information. We focus on explainability of the results and demonstrate potential use of the deep ensembles for future climate what-if scenarios. We suggest that model-informed machine learning presents a viable alternative to expensive reanalyses and could complement observations, wherever they are missing and/or highly uncertain.