Preprints
https://doi.org/10.5194/gmd-2021-167
https://doi.org/10.5194/gmd-2021-167

Submitted as: methods for assessment of models 19 Aug 2021

Submitted as: methods for assessment of models | 19 Aug 2021

Review status: this preprint is currently under review for the journal GMD.

Using Neural Network Ensembles to Separate Biogeochemical and Physical Components in Earth System Models

Christopher Holder, Anand Gnanadesikan, and Marie Aude-Pradal Christopher Holder et al.
  • Morton K. Blaustein Department of Earth and Planetary Sciences, Johns Hopkins University, Baltimore, MD, United States of America

Abstract. Earth system models (ESMs) are useful tools for predicting and understanding past and future aspects of the climate system. However, the biological and physical parameters used in ESMs can have wide variations in their estimates. Even small changes in these parameters can yield unexpected results without a clear explanation of how a particular outcome was reached. The standard method for estimating ESM sensitivity is to compare spatiotemporal distributions of variables from different runs of a single ESM. However, a potential pitfall of this method is that ESM output could match observational patterns because of compensating errors. For example, if a model predicts overly weak upwelling and low nutrient concentrations, it may compensate for this by allowing phytoplankton to have a high sensitivity to nutrients. Recently, it has been demonstrated that neural network ensembles (NNEs) are capable of extracting relationships between predictor and target variables within ocean biogeochemical models. Being able to view the relationships between variables, along with spatiotemporal distributions, allows for a more mechanistically based examination of ESM outputs. Here, we investigated whether we could apply NNEs to help us determine why different ESMs produce different results. We tested this using three cases. The first and second case use different runs of the same ESM, except the physical circulations differ between them in the first case while the biological equations differ between them in the second. Our results indicate that the NNEs were capable of extracting the relationships between variables, allowing us to distinguish between differences due to changes in circulation (which do not change relationships) from changes in biogeochemical formulation (which do change relationships).

Christopher Holder et al.

Status: open (until 29 Oct 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Christopher Holder et al.

Data sets

Dataset and scripts for manuscript "Using Neural Network Ensembles to Separate Biogeochemical and Physical Components in Earth System Models" Holder, Christopher; Gnanadesikan, Anand; Aude-Pradal, Marie http://doi.org/10.5281/zenodo.4774438

Model code and software

Dataset and scripts for manuscript "Using Neural Network Ensembles to Separate Biogeochemical and Physical Components in Earth System Models" Holder, Christopher; Gnanadesikan, Anand; Aude-Pradal, Marie http://doi.org/10.5281/zenodo.4774438

Christopher Holder et al.

Viewed

Total article views: 347 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
290 54 3 347 1 1
  • HTML: 290
  • PDF: 54
  • XML: 3
  • Total: 347
  • BibTeX: 1
  • EndNote: 1
Views and downloads (calculated since 19 Aug 2021)
Cumulative views and downloads (calculated since 19 Aug 2021)

Viewed (geographical distribution)

Total article views: 302 (including HTML, PDF, and XML) Thereof 302 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 28 Sep 2021
Download
Short summary
It can be challenging to understand why Earth System Models (ESMs) produce specific results, because one can arrive at the same result simply by changing the values of the parameters. In our manuscript, we demonstrated that it was possible to use machine learning to figure out how and why particular components of an ESM (such as biology or ocean circulations) were affecting the output. This work could be applied to observations to improve the accuracy of the formulations used in ESMs.