DELWAVE 1.0: deep learning surrogate model of surface wave climate in the Adriatic Basin

Mlakar, Peter; Ricchi, Antonio; Carniel, Sandro; Bonaldo, Davide; Ličer, Matjaž

doi:https://doi.org/10.5194/gmd-17-4705-2024

Articles | Volume 17, issue 12

https://doi.org/10.5194/gmd-17-4705-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-17-4705-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 17, issue 12

Model description paper

|

17 Jun 2024

Model description paper |

| 17 Jun 2024

DELWAVE 1.0: deep learning surrogate model of surface wave climate in the Adriatic Basin

Peter Mlakar, Antonio Ricchi, Sandro Carniel, Davide Bonaldo, and Matjaž Ličer

Supplement

https://doi.org/10.5194/gmd-17-4705-2024-supplement

Data sets

DELWAVE 1.0: Training and test datasets Peter Mlakar et al. https://doi.org/10.5281/zenodo.7816888

Model code and software

DELWAVE convolutional neural network Peter Mlakar https://doi.org/10.5281/zenodo.10990866

10m wind components of the dynamical downscaling with COSMO-CLM of historical (1979/2005) 10 and future climate (2006/2100) data under scenario RCP4.5 and RCP8.5 at 8 km over Italy P. Mercogliano https://doi.org/10.25424/cmcc-3hph-jy15

Short summary

We propose a new point-prediction model, the DEep Learning WAVe Emulating model (DELWAVE), which successfully emulates the Simulating WAves Nearshore model (SWAN) over synoptic to climate timescales. Compared to control climatology over all wind directions, the mismatch between DELWAVE and SWAN is generally small compared to the difference between scenario and control conditions, suggesting that the noise introduced by surrogate modelling is substantially weaker than the climate change signal.