The SOCIB Glider Facility is an example of new technologies being progressively implemented in coastal to open ocean regions allowing autonomous and sustained high-resolution monitoring of specific areas. SOCIB-GF is fully operational in JERICO-NEXT and since 2006 has accomplished 64 missions, 1.244 days in water, 14.555 nm navigated with 39.378 vertical profiles collected. SOCIB-GF human team is composed out of 2 full-time engineers, 1 full-time technician, 2 part-time field-technicians (for at sea operations), 2 part time engineers (for glider data management) and 2 part-time experienced scientists. An intense and fruitful collaboration with IMEDEA (CSIC-UIB) team also exists since the origin of glider operations. The fleet in 2016 consists of 7 Slocum gliders and 2 iRobot Seagliders, equipped for collecting both physical (T, S) and biogeochemical data (fluorescence, oxygen, etc.) at high spatial resolutions (2km). SOCIB-GF includes a pressure chamber (1.000 m) as well as ballasting and operations labs. It also has access to other SOCIB facilities such as (1) ETD (Engineering & Technology Development): Hurricane Zodiac 9.2 m RIB, Lab-Van and harbour warehouse; (2) SOCIB-R/V: a 24 m coastal catamaran and (3) Data Center: including data management, public repository, on-line web-based platform tracker -for mission monitoring- and development of tools such as the glider processing toolbox (Troupin et al., Methods in Oceanog., 2015, - freely available scripts available at https://github.com/socib/glider_toolbox).

The Argo observing network is composed of profiling floats which collect information from the ocean surface to subsurface. These floats collect vertical profiles of ocean temperature and salinity, and some also measure biogeochemical ocean properties. These data provide information about the 4-dimensional ocean, helping to understand the oceans role in the Earth s climate system and to improve future climate change estimates. As part of the Euro-Argo ERIC (European Research Infrastructure Consortium), SOCIB has contributed to the program in the Western Mediterranean Sea since 2011. Each year, SOCIB deploys three floats to maintain a set of five floats, distributed across the sea with an average spacing of 2 degrees. This ensures continuous observation capability. This dataset compiles SOCIB s contribution to Euro-Argo ERIC since January 2011.

No description is available. Visit https://dataone.org/datasets/a597343a7e7413ecf82e8fe9c814da8d for complete metadata about this dataset.

Through the long-term monitoring program called “Canales”, gliders operated by SOCIB have been deployed in the Ibiza Channel (western Mediterranean) along a semi-continuous endurance line since 2011. During the period 2011-2024, more than 70 glider missions were successfully performed, collecting temperature and salinity profiles from the surface to 950 m depth, from which geostrophic velocities were derived. Following the methodology described in Juza et al. (2025), total and water mass geostrophic transports were then computed for each completed section. The water masses are: recent and modified Atlantic Waters (AWr and AWm, respectively), Western Intermediate Water (WIW), Levantine Intermediate Water (LIW) and Western Mediterranean Deep Water (WMDW). This dataset contains the time series of the northward (positive) and southward (negative) flows for the total, AWr, AWm, WIW, LIW and WMDW transports for each transect in the Ibiza Channel from 2011 to 2024.

SOCIB Glider Missions - Canales Endurance Line - was initiated in 2011, with in kind collaboration of CSIC (IMEDEA), covering both the Mallorca and Ibiza channel in a semi-continuous operational mode and sampling physical and biogeochemical observations. The Ibiza channel is a well-established biodiversity hotspot and accordingly more intensive monitoring of the Ibiza channel is carried out to capture the mesoscale and submesoscale structures and their relation to the weekly to seasonal and annual/inter-annual variability. On the canales endurance line, ocean gliders making repeated dives from the surface to 1000 m interior of the ocean, repeating the cycle every ~5 hours, and traveling ~5 km in the horizontal during each dive. The canales endurance line is covering both the Mallorca and Ibiza channel in a semi-continuous operational mode. The glider missions typically last about 60 to 90 days, providing 6-10 sections of the Ibiza channel and 2 sections of the Mallorca channel. Since 2011 the Canales Endurance line has completed 108 glider missions, covered 53000 km over the ground, and has more than 97000 physical and biogeochemical profiles.

OceanGliders GDAC trajectories abstract=The general objective of the EBAMAR-PortoC program is to promote, jointly and coordinated with the activities carried out by other autonomous communities, the current research and technological development strategy in marine sciences of the Balearic Islands so that the new challenges in the ocean observation and, in particular, the effects of climate change in the Mediterranean Sea. Through a detailed understanding of how carbon cycling processes are varying in neritic and oceanic waters, and of the pathways that link production in surface waters with the export of organic matter to deep areas of the ocean, we seek to answer to scientific questions about ocean warming, and more specifically, how Mediterranean marine ecosystems and biogeochemical cycles respond to environmental changes or what the dynamics of the carbon cycle and marine ecosystems will be like in the future.. acknowledgement=Ministerio de Economía y Competitividad (http://www.idi.mineco.gob.es/). Govern de les Illes Balears (http://www.caib.es/). author_email=glider@socib.es cdm_data_type=Trajectory cdm_trajectory_variables=JULD, time citation=Ministerio de Economía y Competitividad (http://www.idi.mineco.gob.es/). Govern de les Illes Balears (http://www.caib.es/). comment=Data regularized, corrected and/or derived from raw glider data. Conventions=CF-1.6 EGO-1.2, COARDS, ACDD-1.3 creator=SOCIB Glider facility data_center=SOCIB Data Center data_center_email=data.centre@socib.es data_mode=R data_type=EGO glider time-series data distribution_statement=see citation Easternmost_Easting=696970.15 featureType=Trajectory format_version=1.2 geospatial_lat_max=696970.15 geospatial_lat_min=-94.01332363329217 geospatial_lat_units=degrees_north geospatial_lon_max=696970.15 geospatial_lon_min=-179.9998312997277 geospatial_lon_units=degrees_east ices_platform_code=undefined infoUrl=http://www.ego-network.org/ institution=IFREMER instrument=SCB-SLDEEP008 instrument_manufacturer=Teledyne instrument_model=Slocum G3 Deep keywords_vocabulary=GCMD Science Keywords naming_authority=EGO Northernmost_Northing=696970.15 positioning_system=GPS and dead reckoning processing_level=L1 processed data with corrections and derivations project=SOCIB Operational publisher=SOCIB qc_manual=none source=Glider observation source_files=sdeep08-2025-131-2-10-sbd(01450010) sdeep08-2025-131-2-102-sbd(01450102) sdeep08-2025-131-2-12-sbd(01450012) sdeep08-2025-131-2-14-sbd(01450014) sdeep08-2025-131-2-16-sbd(01450016) sdeep08-2025-131-2-19-sbd(01450019) sdeep08-2025-131-2-2-sbd(01450002) sdeep08-2025-131-2-21-sbd(01450021) sdeep08-2025-131-2-23-sbd(01450023) sdeep08-2025-131-2-25-sbd(01450025) sdeep08-2025-131-2-27-sbd(01450027) sdeep08-2025-131-2-31-sbd(01450031) sdeep08-2025-131-2-33-sbd(01450033) sdeep08-2025-131-2-35-sbd(01450035) sdeep08-2025-131-2-37-sbd(01450037) sdeep08-2025-131-2-39-sbd(01450039) sdeep08-2025-131-2-4-sbd(01450004) sdeep08-2025-131-2-43-sbd(01450043) sdeep08-2025-131-2-47-sbd(01450047) sdeep08-2025-131-2-51-sbd(01450051) sdeep08-2025-131-2-53-sbd(01450053) sdeep08-2025-131-2-59-sbd(01450059) sdeep08-2025-131-2-6-sbd(01450006) sdeep08-2025-131-2-61-sbd(01450061) sdeep08-2025-131-2-63-sbd(01450063) sdeep08-2025-131-2-65-sbd(01450065) sdeep08-2025-131-2-67-sbd(01450067) sdeep08-2025-131-2-69-sbd(01450069) sdeep08-2025-131-2-71-sbd(01450071) sdeep08-2025-131-2-75-sbd(01450075) sdeep08-2025-131-2-77-sbd(01450077) sdeep08-2025-131-2-79-sbd(01450079) sdeep08-2025-131-2-8-sbd(01450008) sdeep08-2025-131-2-82-sbd(01450082) sdeep08-2025-131-2-84-sbd(01450084) sdeep08-2025-131-2-86-sbd(01450086) sdeep08-2025-131-2-88-sbd(01450088) sdeep08-2025-131-2-92-sbd(01450092) sdeep08-2025-131-2-94-sbd(01450094) sdeep08-2025-131-2-96-sbd(01450096) sdeep08-2025-131-2-98-sbd(01450098) sdeep08-2025-131-2-0-tbd(01450000) sdeep08-2025-131-2-10-tbd(01450010) sdeep08-2025-131-2-100-tbd(01450100) sdeep08-2025-131-2-102-tbd(01450102) sdeep08-2025-131-2-12-tbd(01450012) sdeep08-2025-131-2-14-tbd(01450014) sdeep08-2025-131-2-16-tbd(01450016) sdeep08-2025-131-2-19-tbd(01450019) sdeep08-2025-131-2-2-tbd(01450002) sdeep08-2025-131-2-21-tbd(01450021) sdeep08-2025-131-2-23-tbd(01450023) sdeep08-2025-131-2-25-tbd(01450025) sdeep08-2025-131-2-27-tbd(01450027) sdeep08-2025-131-2-29-tbd(01450029) sdeep08-2025-131-2-31-tbd(01450031) sdeep08-2025-131-2-33-tbd(01450033) sdeep08-2025-131-2-35-tbd(01450035) sdeep08-2025-131-2-37-tbd(01450037) sdeep08-2025-131-2-39-tbd(01450039) sdeep08-2025-131-2-4-tbd(01450004) sdeep08-2025-131-2-41-tbd(01450041) sdeep08-2025-131-2-43-tbd(01450043) sdeep08-2025-131-2-45-tbd(01450045) sdeep08-2025-131-2-47-tbd(01450047) sdeep08-2025-131-2-49-tbd(01450049) sdeep08-2025-131-2-51-tbd(01450051) sdeep08-2025-131-2-53-tbd(01450053) sdeep08-2025-131-2-55-tbd(01450055) sdeep08-2025-131-2-57-tbd(01450057) sdeep08-2025-131-2-59-tbd(01450059) sdeep08-2025-131-2-6-tbd(01450006) sdeep08-2025-131-2-61-tbd(01450061) sdeep08-2025-131-2-63-tbd(01450063) sdeep08-2025-131-2-65-tbd(01450065) sdeep08-2025-131-2-67-tbd(01450067) sdeep08-2025-131-2-69-tbd(01450069) sdeep08-2025-131-2-71-tbd(01450071) sdeep08-2025-131-2-73-tbd(01450073) sdeep08-2025-131-2-75-tbd(01450075) sdeep08-2025-131-2-77-tbd(01450077) sdeep08-2025-131-2-79-tbd(01450079) sdeep08-2025-131-2-8-tbd(01450008) sdeep08-2025-131-2-82-tbd(01450082) sdeep08-2025-131-2-84-tbd(01450084) sdeep08-2025-131-2-86-tbd(01450086) sdeep08-2025-131-2-88-tbd(01450088) sdeep08-2025-131-2-92-tbd(01450092) sdeep08-2025-131-2-94-tbd(01450094) sdeep08-2025-131-2-96-tbd(01450096) sdeep08-2025-131-2-98-tbd(01450098)

sourceUrl=(local files) Southernmost_Northing=-94.01332363329217 standard_name_vocabulary=CF Standard Name Table v29 time_coverage_end=2025-10-06T03:13:53Z time_coverage_start=1970-01-01T00:00:00Z transmission_system=IRIDIUM update_interval=daily Westernmost_Easting=-179.9998312997277

The Black Sea is a semi-enclosed basin with limited water exchange with the open basins and significant river discharges. These inflows are critical to the Black Sea's hydrology, nutrient availability, and ecosystem biogeochemistry. In the Black Sea, the interaction of atmospheric forcing, river discharges, and mesoscale dynamics contributes to the formation of distinct water masses. The northern part of the Black Sea has a shelf exposed to seasonal hypoxia and eutrophication. In contrast, the southern half is deep and stratified, with anoxic waters below 100 meters. These characteristics made the Black Sea an enormous meromictic sea. In the DOORS project (Developing Optimal and Open Research Support), a glider mission was conducted during the DOORS field campaign from May 6 to June 17, 2023, in the Romanian Exclusive Economic Zone. The mission covered 288 nautical miles and collected 863 physical and biogeochemical profiles down to a depth of 1000 meters. During the glider mission, we performed ten transects to the shelf and close to the Danube Cone. Each transect lasted around four days to complete, allowing us to better understand the temporal and spatial variability.

Lagrangian experiment in the Ibiza channel during Summer 2016, aiming to validate HF-Radar surface currents (new Antenna Pattern Measurement)

A coastal sea level reconstruction based on tide gauge observations is developed and applied to the western basin of the Mediterranean sea, including sea level anomaly (SLA) and interpolation error along the entire coastline. The reconstructions are carried out in four frequency bands: periods longer than 10 years, periods between 1 and 10 years, periods between 1 month and 1 year, and periods between 1day and 1month. Total sea level at monthly and daily resolution, obtained by merging the different frequency bands, is also provided. The reconstructions are based on an optimal interpolation method in which the correlation between tide gauge data and all coastal points has been determined from the outputs of the numerical model managed by the Balearic Islands Coastal Observing and Forecasting System (SOCIB, https://www.socib.es). The reconstructions for frequencies lower than 1 month use monthly observations from the Permanent Service for Mean Sea Level (PSMSL, https://www.psmsl.org/) database and cover the period from 1884 to 2019. For the reconstruction of higher frequencies, hourly observations from the Global Extreme Sea Level Analysis (GESLA–2, https://www.gesla.org/) dataset are used, and cover from 1980 to 2015. The compressed file includes 6 datasets in NetCDF format, for monthly, daily and the 4 frequency band reconstructions.Funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe.

Training dataset

BWILD is a dataset tailored to train Artificial Intelligence applications to automate beach seagrass wrack detection in RGB images. It includes oblique RGB images captured by SIRENA beach video-monitoring systems, along with corresponding annotations, auxiliary data and a README file. BWILD encompasses data from two microtidal sandy beaches in the Balearic Islands, Spain. The dataset consists of images with varying fields of view (9 cameras), beach wrack abundance, degrees of occupation, and diverse meteoceanic and lighting conditions. The annotations categorise image pixels into five classes: i) Landwards, ii) Seawards, iii) Diffuse wrack, iv) Intermediate wrack, and v) Dense wrack.

Technical details

The BWILD version 1.1.0 is packaged in a compressed file (BWILD_v1.1.0.zip). A total of 3286 RGB images are shared in PNG format, corresponding annotations and masks in various formats (PNG, XML, JSON,TXT), and the README file in PDF format.

Data preprocessing

The BWILD dataset utilizes snapshot images from two SIRENA beach video-monitoring systems. To facilitate annotation while maintaining a diverse range of scenarios, the original 1280x960 pixel images were cropped to smaller regions, with a uniform resolution of 640x480 pixels. A subset of images was carefully curated to minimize annotation workload while ensuring representation of various time periods, distances to camera, and environmental conditions. Image selection involved filtering for quality, clustering for diversity, and prioritizing scenes containing beach seagrass wracks. Further details are available in the README file.

Data splitting

Data splitting requirements may vary depending on the chosen Artificial Intelligence approach (e.g., splitting by entire images or by image patches). Researchers should use a consistent method and document the approach and splits used in publications, enabling reproducible results and facilitating comparisons between studies.

Classes, labels and annotations

The BWILD dataset has been labelled manually using the 'Computer Vision Annotation Tool' (CVAT), categorising pixels into five labels of interest using polygon annotations.

  Label
                                     Description

landwards Pixels that are towards the landside with respect to the shoreline

seawards Pixels that are towards the seaside with respect to the shoreline

diffuse wrack Pixels that potentially resembled beach wracks based on colour and shape, yet the annotator could not confirm this with certainty, were denoted as ‘diffuse wrack’

Intermediate wrack Pixels with low-density beach wracks or mixed beach wracks and sand surfaces

Dense wrack Pixels with high-density beach wracks

Annotations were exported from CVAT in four different formats: (i) CVAT for images (XML); (ii) Segmentation Mask 1.0 (PNG); (iii) COCO (JSON); (iv) Ultralytics YOLO Segmentation 1.0 (TXT). These diverse annotation formats can be used for various applications including object detection and segmentation, and simplify the interaction with the dataset, making it more user-friendly. Further details are available in the README file.

Parameters

RGB values or any transformation in the colour space can be used as parameters.

Data sources

A SIRENA system consists of a set of RGB cameras mounted at the top of buildings on the beachfront. These cameras take oblique pictures of the beach, with overlapping sights, at 7.5 FPS during the first 10 minutes of each hour in daylight hours. From these pictures, different products are generated, including snapshots, which correspond to the frame of the video at the 5th minute. In the Balearic Islands, SIRENA stations are managed by the Balearic Islands Coastal Observing and Forecasting System (SOCIB), and are mounted at the top of hotels located in front of the coastline. The present dataset includes snapshots from the SIRENA systems operating since 2011 at Cala Millor (5 cameras) and Son Bou (4 cameras) beaches, located in Mallorca and Menorca islands (Balearic Islands, Spain), respectively. All latest and historical SIRENA images are available at the Beamon app viewer (https://apps.socib.es/beamon).

Data quality

All images included in BWILD have been supervised by the authors of the dataset. However, variable presence of beach segrass wracks across different beach segments and seasons impose a variable distribution of images across different SIRENA stations and cameras. Users of BWILD dataset must be aware of this variance. Further details are available in the README file.

Image resolution

The resolution of the images in BWILD is of 640x480 pixels.

Spatial coverage

The BWILD version 1.1.0 contains data from two SIRENA beach video-monitoring stations, encompassing two microtidal sandy beaches in the Balearic Islands, Spain. These are: Cala Millor (clm) and Son Bou (snb).

SIRENA station Longitude Latitude

clm 3.383 39.596

snb 4.077 39.898

Contact information

For further technical inquiries or additional information about the annotated dataset, please contact jsoriano@socib.es.

Data produced in the platform Buoy BahiaDePalma. It's compound by: Conductivity and Temperature Recorder, Current profiler, Currentmeter, Multiparameter probe, Oceanographic Buoy, Status, Waves recorder, Weather Station data

Systematic and sustained high quality measurements of nearshore waves and beach morphology are crucial to unravel the effects of global warming on sandy coasts and thus be able to assess the validity of sediment transport numerical models. Such measurements are also key to understanding the morphodynamic processes that determine how the beach evolves. In 2011 a comprehensive beach monitoring program, the first in the Mediterranean Sea, started at Cala Millor Beach on the island of Mallorca (Spain). The aim was to provide long-term datasets of near-shore morphodynamics in a carbonate sandy micro-tidal and semi-embayed beach fronted by a Posidonia oceanica seagrass meadow. The dataset includes topobathymetries, shoreline positions obtained from video cameras, meteorological parameters from a weather station, currents, as well as waves and sea level from ADCP measurements and sediment size. This free and unrestricted archived dataset can be used to support the modelling of erosion-deposition patterns, calibrate beach evolution models, and as a result to propose adaptation and mitigation actions under different global change scenarios.

This dataset contains all data used in the article:

Observational characterization of atmospheric disturbances generating meteotsunamis in the Balearic Islands

Joan Villalonga*(1,2), Sebastià Monserrat (1), Damià Gomis (1,3), Gabriel Jordà*(2)

(1) Departament de Física (UIB), Palma, Spain.

(2) Centre Oceanogràfic de Balears, CN-Instituto Español de Oceanografía (IEO-CSIC), Palma, Spain.

(3) Institut Mediterrani d’Estudis Avançats (UIB-CSIC), Esporles, Spain.

Corresponding email: joan.villalonga@uib.cat

There are 7 data files:

Atm_pres_all: containing the atmospheric pressure time series measured in the different meteorological stations used in the work. Each station contain its name and position in coordinates. All the time series have a temporal resolution of 1 min. The data have been obtained from BalearsMeteo (http://balearsmeteo.com/) and from SOCIB (https://www.socib.es/).

ciutadella_SL_AtmPres: containing the sea level and atmospheric pressure records in Ciutadella from 2018 to 2021. All the time series have a temporal resolution of 1 min. The data have been provided by PortIB (https://www.portsib.es/ca/paginas/inici).

ciutadella_SL_long: containing the sea level records in Ciutadella from 2014 to 2021. All the time series have a temporal resolution of 1 min. The data have been provided by PortIB (https://www.portsib.es/ca/paginas/inici).

ciutadella_spectral_data: containing the sea level and atmospheric pressure power wavelet spectra in Ciutadella from 2018 to 2021. Computed from the data in ciutadella_SL_AtmPres.

corr_rissagues_1min_allfreq_12h: containing the maximum lagged correlation matrices between the atmospheric pressure time series measured at the 12h surrounding each meteotsunami event in 2021. They have been computed from the data in Atm_pres_all.

sepic_index_vars: containing the five ERA5 1-hour time series of the variables used to compute the meteotsunami index as described in Sepic, et al,. 2016.

wind_ciutadella: containing the time series of the wind speed and direction provided by ERA5 reanalysis over Ciutadella during the period of study.

For more details, please consult the manuscript of the article

A multi-platform synoptic experiment (ALBOREX) was conducted in 2014 in the eastern Alboran Sea in the frame of EU funded FP7 PERSEUS project. The final goal was to monitor and establish the vertical exchanges associated with mesoscale and sub-mesoscale (e.g fronts, meanders, eddies and filaments) and their contribution to upper-ocean interior exchanges.

Description of attributes for sediment mass budget at the coast for the last 10, 50 and 100 years for the Mediterranean basin and for each NUTS3 region along the coast.

Through the long-term monitoring program called “Canales”, gliders operated by SOCIB have been deployed in the Ibiza Channel (western Mediterranean) along a semi-continuous endurance line. Since 2011, more than 70 glider missions have been successfully performed, collecting temperature and salinity profiles from the surface to 950 m depth, from which geostrophic velocities were derived. Following the methodology described in Juza et al. (2025), total and water mass geostrophic transports were then computed for each completed section. The water masses are: recent and modified Atlantic Waters (AWr and AWm, respectively), Western Intermediate Water (WIW), Levantine Intermediate Water (LIW) and Western Mediterranean Deep Water (WMDW). This dataset contains the monthly climatology of the northward (positive) and southward (negative) flows for the total, AWr, AWm, WIW, LIW and WMDW transports in the Ibiza Channel over the period 2011-2022.

Lagrangian experiment in the Ibiza channel during Autumn 2018, aiming to use the novel CARTHE GPS drifters (low-cost, compact, practical, eco-friendly and able too track currents centered 40 cm below the surface) to validate HF-Radar (new Antenna Pattern Measurement) and WMOP surface velocities, capture all representative spatio-temporal scales of surface circulation, study dispersion of surface particles, perform HFR data assimilation experiment with WMOP.

The aim of this experiment was to assess the operational HF radar surface current velocities in the Ibiza Channel in a Lagrangian framework, by comparing against surface drifter derived velocities"

Training dataset

RipAID is a dataset tailored to train Artificial Intelligence applications dedicated to automating rip currents detection in RGB images. It includes oblique images captured by SIRENA beach video-monitoring systems, along with corresponding annotations in various formats (XML, JSON, TXT). RipAID encompasses images from two microtidal sandy beaches, with varying fields of view (8 cameras), rip currents characteristics, and diverse meteoceanic and lighting conditions. The RipAID dataset contains two classes: ‘rip currents’ and ‘doubt’, labeled with oriented bounding boxes.

Technical details

The RipAID version 1.0.0 is packaged in a compressed file (RipAID_v1.0.0.zip). A total of 2815 RGB images are shared in PNG format, corresponding annotations in various formats (XML, JSON, TXT), and the README file in PDF format.

Data preprocessing

The RipAID dataset comprises original resolution (1280✕960 px) snapshot images from two SIRENA beach monitoring systems. No further preprocessing was performed. Refer to the README file for more information.

Data splitting

Researchers should consistently document their splitting method and rationale in publications to ensure reproducibility and facilitate comparisons.

Classes, labels and annotations

The RipAID dataset has been labelled manually using the 'Computer Vision Annotation Tool' (CVAT). In the RipAID dataset, two classes are differentiated, and labelled using oriented bounding boxes: 'rip_current' and 'doubt'. The 'rip_current' label denotes a clearly identifiable rip current, while the 'doubt' label is assigned to features that exhibit uncertainty regarding their classification as rip currents. The "doubt" category has been included as a preventive measure to ensure a conservative approach. The README file contains further details on the criteria used to define bounding boxes.

Annotations were exported from CVAT in three different formats: (i) CVAT for images (XML); (ii) COCO (JSON); (iii) Ultralytics YOLO-OBB (TXT). The diverse annotation formats offered in RipAID simplify the interaction with the dataset.

Parameters

RGB values or any transformation in the colour space can be used as parameters.

Data sources

A SIRENA system consists of a set of RGB cameras mounted at the top of buildings on the beachfront. These cameras take oblique pictures of the beach, with overlapping sights, at 7.5 FPS during the first 10 minutes of each hour in daylight hours. From these pictures, different products are generated, including snapshots, which correspond to the frame of the video at the 5th minute. In the Balearic Islands, SIRENA stations are managed by the Balearic Islands Coastal Observing and Forecasting System (SOCIB), and are mounted at the top of hotels located in front of the coastline. The present dataset includes snapshots from 8 different cameras of the SIRENA systems operating since 2011 at Cala Millor and Son Bou beaches, located in Mallorca and Menorca islands (Balearic Islands, Spain), respectively. All latest and historical SIRENA images are available at the Beamon app viewer (https://apps.socib.es/beamon).

Data quality

The RipAID dataset has uneven image distribution across SIRENA stations, cameras, and seasons due to rip current occurrence and collection strategy. Users should be aware of this variability. Additionally, despite expert labeling, the inherent variability of rip currents can lead to labeling ambiguity, which is important to consider. Further details are available in the README file.

Image resolution

The resolution of the images in RipAID is of 1280✕960 pixels.

Spatial coverage

The RipAID version 1.0.0 contains data from two SIRENA beach video-monitoring stations, encompassing two microtidal sandy beaches in the Balearic Islands, Spain. These are: Cala Millor (clm) and Son Bou (snb).

Contact information

For further technical inquiries or additional information about the annotated dataset, please contact jsoriano@socib.es.

Un studiu hidrografic sezonier repetat al Mării Baleare, care monitorizează canalele Ibiza și Mallorca.