Iskanje po repozitoriju

A+ | A- | | SLO | ENG

Povzetek: 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.
Ključne besede: deep learning, reconstruction algorithms, satellite measurements
Objavljeno v DiRROS: 14.10.2025; Ogledov: 458; Prenosov: 230
Celotno besedilo (19,22 MB)
Gradivo ima več datotek! Več...

Povzetek: 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.
Ključne besede: sea level modeling, deep learning, storm surges
Objavljeno v DiRROS: 03.04.2025; Ogledov: 788; Prenosov: 446
Celotno besedilo (8,49 MB)
Gradivo ima več datotek! Več...

Povzetek: 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.
Ključne besede: morje, numerično modeliranje, naravne nesreče, cirkulacijski modeli, izlitja nafte, onesnaževanje, POM, Jadransko morje
Objavljeno v DiRROS: 26.03.2025; Ogledov: 727; Prenosov: 468
Celotno besedilo (1,46 MB)
Gradivo ima več datotek! Več...

Povzetek: 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.
Ključne besede: coastal monitoring, Mediterranean Sea, multi-platform observing systems, oceanography
Objavljeno v DiRROS: 05.08.2024; Ogledov: 1156; Prenosov: 732
Celotno besedilo (12,59 MB)
Gradivo ima več datotek! Več...

Povzetek: 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.
Ključne besede: surrogate modelling, deep learning, DEep Learning WAVe Emulating model, DELWAVE, Simulating WAves Nearshore, SWAN
Objavljeno v DiRROS: 05.08.2024; Ogledov: 1024; Prenosov: 660
Celotno besedilo (9,04 MB)
Gradivo ima več datotek! Več...