| Title: | DELWAVE 1.0 : deep learning surrogate model of surface wave climate in the Adriatic Basin |
|---|
| Authors: | ID Mlakar, Peter (Author)
ID Ricchi, Antonio (Author)
ID Carniel, Sandro (Author)
ID Bonaldo, Davide (Author)
ID Ličer, Matjaž (Author) |
|---|
| Files: |  URL - Source URL, visit https://doi.org/10.5194/gmd-17-4705-2024
 PDF - Presentation file, download (9,04 MB)
MD5: 8D76F57D675F473AE94CF49BC887B45B
|
|---|
| Language: | English |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: |  NIB - National Institute of Biology
|
|---|
| Abstract: | We propose a new point-prediction model, the DEep Learning WAVe Emulating model (DELWAVE), which successfully emulates the behaviour of a numerical surface ocean wave model (Simulating WAves Nearshore, SWAN) at a sparse set of locations, thus enabling numerically cheap large-ensemble prediction over synoptic to climate timescales. DELWAVE was trained on COSMO-CLM (Climate Limited-area Model) and SWAN input data during the period of 1971–1998, tested during 1998–2000, and cross-evaluated over the far-future climate time window of 2071–2100. It is constructed from a convolutional atmospheric encoder block, followed by a temporal collapse block and, finally, a regression block. DELWAVE reproduces SWAN model significant wave heights with a mean absolute error (MAE) of between 5 and 10 cm, mean wave directions with a MAE of 10–25°, and a mean wave period with a MAE of 0.2 s. DELWAVE is able to accurately emulate multi-modal mean wave direction distributions related to dominant wind regimes in the basin. We use wave power analysis from linearised wave theory to explain prediction errors in the long-period limit during southeasterly conditions. We present a storm analysis of DELWAVE, employing threshold-based metrics of precision and recall to show that DELWAVE reaches a very high score (both metrics over 95 %) of storm detection. SWAN and DELWAVE time series are compared to each other in the end-of-century scenario (2071–2100) and compared to the control conditions in the 1971–2000 period. Good agreement between DELWAVE and SWAN is found when considering climatological statistics, with a small (≤ 5 %), though systematic, underestimate of 99th-percentile values. 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. |
|---|
| Keywords: | surrogate modelling, deep learning, DEep Learning WAVe Emulating model, DELWAVE, Simulating WAves Nearshore, SWAN |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Publication date: | 17.06.2024 |
|---|
| Year of publishing: | 2024 |
|---|
| Number of pages: | str. 4705-4725 |
|---|
| Numbering: | Vol. 17, iss. 12 |
|---|
| PID: | 20.500.12556/DiRROS-20061  |
|---|
| UDC: | 004.9 |
|---|
| ISSN on article: | 1991-959X |
|---|
| DOI: | 10.5194/gmd-17-4705-2024 |
|---|
| COBISS.SI-ID: | 203614211 |
|---|
| Note: | Soavtorji: Antonio Ricchi, Sandro Carniel, Davide Bonaldo, and Matjaž Ličer;
|
|---|
| Publication date in DiRROS: | 05.08.2024 |
|---|
| Views: | 18 |
|---|
| Downloads: | 8 |
|---|
| Metadata: |     |
|---|
|
:
|
Copy citation |
|---|
| | | | Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
