Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology
<p>We introduce a proof of concept to parametrise the unresolved subgrid scale of sea-ice dynamics with deep learning techniques. Instead of parametrising single processes, a single neural network is trained to correct all model variables at the same time. This data-driven approach is applied...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-07-01
|
| Series: | The Cryosphere |
| Online Access: | https://tc.copernicus.org/articles/17/2965/2023/tc-17-2965-2023.pdf |
| Summary: | <p>We introduce a proof of concept to parametrise the unresolved subgrid scale of sea-ice dynamics with deep learning techniques.
Instead of parametrising single processes, a single neural network is trained to correct all model variables at the same time.
This data-driven approach is applied to a regional sea-ice model that accounts exclusively for dynamical processes with a Maxwell elasto-brittle rheology.
Driven by an external wind forcing in a <span class="inline-formula">40 km×200 km</span> domain, the model generates examples of sharp transitions between unfractured and fully fractured sea ice.
To correct such examples, we propose a convolutional U-Net architecture which extracts features at multiple scales.
We test this approach in twin experiments: the neural network learns to correct forecasts from low-resolution simulations towards high-resolution simulations for a lead time of about 10 min.
At this lead time, our approach reduces the forecast errors by more than <span class="inline-formula">75 <i>%</i></span>, averaged over all model variables.
As the most important predictors, we identify the dynamics of the model variables.
Furthermore, the neural network extracts localised and directional-dependent features, which point towards the shortcomings of the low-resolution simulations.
Applied to correct the forecasts every 10 min, the neural network is run together with the sea-ice model.
This improves the short-term forecasts up to an hour.
These results consequently show that neural networks can correct model errors from the subgrid scale for sea-ice dynamics.
We therefore see this study as an important first step towards hybrid modelling to forecast sea-ice dynamics on an hourly to daily timescale.</p> |
|---|---|
| ISSN: | 1994-0416 1994-0424 |