1. |
2. Training and test datasets, pretrained weights and predictions for HIDRA3 : version v1Marko Rus, Hrvoje Mihanović, Matjaž Ličer, Matej Kristan, 2024, complete scientific database of research data Abstract: HIDRA3 is a state-of-the-art deep neural model for multi-point sea-level prediction based on past sea level observations and future tidal and geophysical forecasts. Published data contain HIDRA3 pretrained weights, predictions for all 50 ensembles, geophysical training and evaluation data and SSH observations from Koper (Slovenia). The structure of the data is described in README.md.
Keywords: sea level modeling, deep learning, storm surges
Published in DiRROS: 13.04.2026; Views: 191; Downloads: 219
 Link to file
This document has many files! More... |
3. Dynamic sinking and surface-area based decay modeling reduce estimates of gelatinous zooplankton-mediated carbon export to the Deep SeaČrtomir Perharič, Martin Vodopivec, Gerhard J. Herndl, Matjaž Ličer, 2026, original scientific article Abstract: Gelatinous zooplankton (GZ) have been proposed as a potentially important but largely overlooked contributor to the biological carbon pump. However, estimates of GZ-derived carbon transfer efficiency to the ocean floor reflect uncertainties in key parameters that govern carbon export, leading to contrasting interpretations of the role of GZ in the biological carbon pump. This study addresses key simplifications in previous models, that is, constant sinking speed and mass-depending decay, by introducing (a) vertical sinking dynamically coupled to GZ biomass loss due to microbial decay and (b) a novel surface-area-dependent formulation of GZ biomass degradation. Under these new assumptions, global GZ carbon exports and transfer efficiencies are recomputed, capturing processes not considered in earlier models. While global GZ export from the euphotic zone remains similar to previous estimates , accounting for of the total global particulate organic carbon (POC) export, introducing a sinking speed coupled to GZ biomass reduces GZ POC export to the seafloor by (to ). Adding the surface-area based decay reduces export to the seafloor by (to ). These results indicate that while GZ remains a major contributor to carbon export from the euphotic zone, earlier models overestimated GZ contribution to deep-ocean carbon sequestration. Our modeling assumptions are generic and transferable to other types of sinking and decaying particles and can be leveraged to improve estimates of POC export, thus advancing the understanding of the mechanical aspects of the biological carbon pump.
Published in DiRROS: 25.03.2026; Views: 293; Downloads: 215
 Full text (4,17 MB)
This document has many files! More...
This document is also a collection of 1 document! |
4. CRITER 1.0 : a coarse reconstruction with iterative refinement network for sparse spatio-temporal satellite dataMatjaž Zupančič Muc, Vitjan Zavrtanik, Alexander Barth, Aida Alvera-Azcárate, Matjaž Ličer, Matej Kristan, 2025, original scientific article Abstract: Satellite observations of sea surface temperature (SST) are essential for accurate weather forecasting and climate modeling. However, these data often suffer from incomplete coverage due to cloud obstruction and limited satellite swath width, which requires development of dense reconstruction algorithms. The current state of the art struggles to accurately recover high-frequency variability, particularly in SST gradients in ocean fronts, eddies, and filaments, which are crucial for downstream processing and predictive tasks. To address this challenge, we propose a novel two-stage method CRITER (Coarse Reconstruction with ITerative Refinement Network), which consists of two stages. First, it reconstructs low-frequency SST components utilizing a Vision Transformer-based model, leveraging global spatio-temporal correlations in the available observations. Second, a UNet type of network iteratively refines the estimate by recovering high-frequency details. Extensive analysis on datasets from the Mediterranean, Adriatic, and Atlantic seas demonstrates CRITER's superior performance over the current state of the art. Specifically, CRITER achieves up to 44 % lower reconstruction errors of the missing values and over 80 % lower reconstruction errors of the observed values compared to the state of the art.
Keywords: deep learning, reconstruction algorithms, satellite measurements
Published in DiRROS: 14.10.2025; Views: 759; Downloads: 366
Full text (19,22 MB)
This document has many files! More... |
5. Application of the HIDRA2 deep-learning model for sea level forecasting along the Estonian coast of the Baltic SeaAmirhossein Barzandeh, Matjaž Ličer, Marko Rus, Matej Kristan, Ilja Maljutenko, Jüri Elken, Priidik Lagemaa, Rivo Uiboupin, 2025, original scientific article Abstract: 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.
Keywords: sea flooding, deep learning, convolutional networks
Published in DiRROS: 08.09.2025; Views: 807; Downloads: 391
Full text (6,41 MB)
This document has many files! More... |
6. HIDRA3 : a deep-learning model for multipoint ensemble sea level forecasting in the presence of tide gauge sensor failuresMarko Rus, Hrvoje Mihanović, Matjaž Ličer, Matej Kristan, 2025, original scientific article Abstract: Accurate modeling of sea level and storm surge dynamics with several days of temporal horizons is essential for effective coastal flood responses and the protection of coastal communities and economies. The classical approach to this challenge involves computationally intensive ocean models that typically calculate sea levels relative to the geoid, which must then be correlated with local tide gauge observations of sea surface height (SSH). A recently proposed deep-learning model, HIDRA2 (HIgh-performance Deep tidal Residual estimation method using Atmospheric data, version 2), avoids numerical simulations while delivering competitive forecasts. Its forecast accuracy depends on the availability of a sufficiently long history of recorded SSH observations used in training. This makes HIDRA2 less reliable for locations with less abundant SSH training data. Furthermore, since the inference requires immediate past SSH measurements as input, forecasts cannot be made during temporary tide gauge failures. We address the aforementioned issues using a new architecture, HIDRA3, that considers observations from multiple locations, shares the geophysical encoder across the locations, and constructs a joint latent state that is decoded into forecasts at individual locations. The new architecture brings several benefits: (i) it improves training at locations with scarce historical SSH data, (ii) it enables predictions even at locations with sensor failures, and (iii) it reliably estimates prediction uncertainties. HIDRA3 is evaluated by jointly training on 11 tide gauge locations along the Adriatic. Results show that HIDRA3 outperforms HIDRA2 and the Mediterranean basin Nucleus for European Modelling of the Ocean (NEMO) setup of the Copernicus Marine Environment Monitoring Service (CMEMS) by ∼ 15 % and ∼ 13 % mean absolute error (MAE) reductions at high SSH values, creating a solid new state of the art. The forecasting skill does not deteriorate even in the case of simultaneous failure of multiple sensors in the basin or when predicting solely from the tide gauges far outside the Rossby radius of a failed sensor. Furthermore, HIDRA3 shows remarkable performance with substantially smaller amounts of training data compared with HIDRA2, making it appropriate for sea level forecasting in basins with high regional variability in the available tide gauge data.
Keywords: sea level modeling, deep learning, storm surges
Published in DiRROS: 03.04.2025; Views: 986; Downloads: 637
Full text (8,49 MB)
This document has many files! More...
This document is also a collection of 2 documents! |
7. Uporaba numeričnih modelov ob razlitjih nafte na morjuDušan Žagar, Vanja Ramšak, Matjaž Ličer, Boris Petelin, Vlado Malačič, 2012, review article Abstract: Razlitje nafte v morju ima številne škodljive posledice na okolje in gospodarstvo. Potrebno je takojšnje ukrepanje pristojnih služb, ki si ob razlitju lahko pomagajo tudi z matematičnimi modeli, s katerimi je mogoče simulirati procese širjenja in razgradnje nafte. V prispevku je predstavljen pregled procesov in modelov širjenja naftnih madežev v morskem okolju. Opisan je model NAFTA3d in prikazana je njegova uporaba. Predstavljeni so vhodni podatki in rezultati modela na dveh možnih razlitjih v Tržaškem zalivu, pri čemer so upoštevane dejanske (nestacionarne) vremenske in hidrodinamične razmere. Prikazane so simulacije po taktičnem in prognostičnem načinu. Z vgrajenimi procesi in možnostjo povezav z različnimi modeli cirkulacije je lahko model NAFTA3d koristno dodatno orodje za ustrezne službe, ki skrbijo za omejitev širjenja in omilitev posledic ob morebitnih razlitjih nafte na morju.
Keywords: morje, numerično modeliranje, naravne nesreče, cirkulacijski modeli, izlitja nafte, onesnaževanje, NAFTA3d, Jadransko morje
Published in DiRROS: 26.03.2025; Views: 923; Downloads: 783
Full text (1,53 MB)
This document has many files! More... |
8. Numerični modeli za določanje stanja morja v Jadranskem morjuMatjaž Ličer, Dušan Žagar, Maja Jeromel, Martin Vodopivec, 2012, review article Abstract: V prispevku predstavljamo glavne razloge za numerično modeliranje morja v Jadranskem morju in na kratko opisujemo modele, ki se trenutno uporabljajo v ta namen. Predstavljeni so cirkulacijski model POM za severno Jadransko morje, valovni model SWAN in model razlitja ogljikovodikov v morskem okolju NAFTA3d. Prikazani so tudi nekateri rezultati vseh navedenih modelov in trenutni načrti njihove implementacije.
Keywords: morje, numerično modeliranje, naravne nesreče, cirkulacijski modeli, izlitja nafte, onesnaževanje, POM, Jadransko morje
Published in DiRROS: 26.03.2025; Views: 1058; Downloads: 733
Full text (1,46 MB)
This document has many files! More... |
9. Criteria for the definition of relevant assessment scales for the pelagic habitat : deliverable D2.1bJanja Francé, Martin Vodopivec, Matjaž Ličer, Sanda Skejić, Cecilia Totti, Erika Magaletti, Antonella Penna, Roberta Congestri, Ivano Vascotto, 2023, final research report Published in DiRROS: 19.12.2024; Views: 1237; Downloads: 367
Full text (2,52 MB) |
10. Coastal high-frequency radars in the Mediterranean : Applications in support of science priorities and societal needsEmma Reyes, Eva Aguiar, Michele Bendoni, Maristella Berta, Carlo Brandini, Alejandro Cáceres-Euse, Fulvio Capodici, Vanessa Cardin, Daniela Cianelli, Giuseppe Ciraolo, Matjaž Ličer, 2022, review article Abstract: The Mediterranean Sea is a prominent climate-change hot spot, with many socioeconomically vital coastal areas being the most vulnerable targets for maritime safety, diverse met-ocean hazards and marine pollution. Providing an unprecedented spatial and temporal resolution at wide coastal areas, high-frequency radars (HFRs) have been steadily gaining recognition as an effective land-based remote sensing technology for continuous monitoring of the surface circulation, increasingly waves and occasionally winds. HFR measurements have boosted the thorough scientific knowledge of coastal processes, also fostering a broad range of applications, which has promoted their integration in coastal ocean observing systems worldwide, with more than half of the European sites located in the Mediterranean coastal areas. In this work, we present a review of existing HFR data multidisciplinary science-based applications in the Mediterranean Sea, primarily focused on meeting end-user and science-driven requirements, addressing regional challenges in three main topics: (i) maritime safety, (ii) extreme hazards and (iii) environmental transport process. Additionally, the HFR observing and monitoring regional capabilities in the Mediterranean coastal areas required to underpin the underlying science and the further development of applications are also analyzed. The outcome of this assessment has allowed us to provide a set of recommendations for future improvement prospects to maximize the contribution to extending science-based HFR products into societally relevant downstream services to support blue growth in the Mediterranean coastal areas, helping to meet the UN's Decade of Ocean Science for Sustainable Development and the EU's Green Deal goals.
Keywords: coastal monitoring, Mediterranean Sea, multi-platform observing systems, oceanography
Published in DiRROS: 05.08.2024; Views: 1428; Downloads: 883
Full text (12,59 MB)
This document has many files! More... |
