| Naslov: | Application of the HIDRA2 deep-learning model for sea level forecasting along the Estonian coast of the Baltic Sea |
|---|
| Avtorji: | ID Barzandeh, Amirhossein (Avtor)
ID Ličer, Matjaž (Avtor)
ID Rus, Marko (Avtor)
ID Kristan, Matej (Avtor)
ID Maljutenko, Ilja (Avtor)
ID Elken, Jüri (Avtor)
ID Lagemaa, Priidik (Avtor)
ID Uiboupin, Rivo (Avtor) |
|---|
| Datoteke: |  URL - Izvorni URL, za dostop obiščite https://os.copernicus.org/articles/21/1315/2025/
 PDF - Predstavitvena datoteka, prenos (6,41 MB)
MD5: E3EB03E25C15DDAB40B4FB182F0E8A65
|
|---|
| Jezik: | Angleški jezik |
|---|
| Tipologija: | 1.01 - Izvirni znanstveni članek |
|---|
| Organizacija: |  NIB - Nacionalni inštitut za biologijo
|
|---|
| Povzetek: | Sea level predictions, typically derived from 3D hydrodynamic models, are computationally intensive and subject to uncertainties stemming from physical representation and inaccuracies in initial or boundary conditions. As a complementary alternative, data-driven machine learning models provide a computationally efficient solution with comparable accuracy. This study employs the deep-learning model HIDRA2 to forecast hourly sea levels at five coastal stations along the Estonian coastline of the Baltic Sea, evaluating its performance across various forecast lead times. Compared to the regional NEMOBAL and subregional NEMOEST hydrodynamic models, HIDRA2 frequently outperforms both, particularly in terms of overall forecast skill. While HIDRA2 shows limitations in resolving high-frequency sea level variability above (6h) 1, it effectively reproduces energy in lower-frequency bands below (18h) 1. Errors tend to average out over longer time windows encompassing multiple seiche periods, enabling HIDRA2 to surpass the overall performance of the NEMO models. These findings underscore HIDRA2’s potential as a robust, efficient, and reliable tool for operational sea level forecasting and coastal management in the eastern Baltic Sea region. |
|---|
| Ključne besede: | sea flooding, deep learning, convolutional networks |
|---|
| Status publikacije: | Objavljeno |
|---|
| Verzija publikacije: | Objavljena publikacija |
|---|
| Datum objave: | 14.07.2025 |
|---|
| Leto izida: | 2025 |
|---|
| Št. strani: | str. 1315–1327 |
|---|
| Številčenje: | Vol. 21, issue 4 |
|---|
| PID: | 20.500.12556/DiRROS-23534  |
|---|
| UDK: | 574.5 |
|---|
| ISSN pri članku: | 1812-0792 |
|---|
| DOI: | 10.5194/os-21-1315-2025 |
|---|
| COBISS.SI-ID: | 243923971 |
|---|
| Opomba: | Nasl. z nasl. zaslona;
Soavtorji: Matjaž Ličer, Marko Rus, Matej Kristan, Ilja Maljutenko, Jüri Elken, Priidik Lagemaa, Rivo Uiboupin;
Opis vira z dne 25. 7. 2025;
|
|---|
| Datum objave v DiRROS: | 08.09.2025 |
|---|
| Število ogledov: | 362 |
|---|
| Število prenosov: | 154 |
|---|
| Metapodatki: |    |
|---|
|
:
|
Kopiraj citat |
|---|
| | | | Objavi na: |  |
|---|
Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše
podrobnosti ali sproži prenos. |
