Brought to you by SLGO, the St. Lawrence regional association of CIOOS
|
|
Brought to you by SLGO, the St. Lawrence regional association of CIOOS |
| Dataset Title: | Classification of Benthic Substrates (Data) Using Supervised and Unsupervised Machine Learning Models on the North Shore of the St. Lawrence Maritime Estuary | Données de classification de substrats benthiques générées par Intelligence Artificielle sur la rive nord de l'estuaire maritime 
|
| Institution: | The Interdisciplinary Centre for the Development of Ocean Mapping (Dataset ID: cidcoBenthicSubstrateAi) |
| Information: | Summary
| License
| FGDC
| ISO 19115
| Metadata
| Background
| Subset
| Files
| Make a graph
|
Attributes {
s {
marineRegion {
String units "unitless";
}
location {
String units "unitless";
}
measurementID {
String units "unitless";
}
time {
String _CoordinateAxisType "Time";
String axis "T";
String ioos_category "Time";
String long_name "Time";
String standard_name "time";
String time_origin "01-JAN-1970 00:00:00";
String units "seconds since 1970-01-01T00:00:00Z";
}
latitude {
String _CoordinateAxisType "Lat";
String axis "Y";
Float64 colorBarMaximum 90.0;
Float64 colorBarMinimum -90.0;
String ioos_category "Location";
String long_name "Latitude";
String standard_name "latitude";
String units "degrees_north";
}
longitude {
String _CoordinateAxisType "Lon";
String axis "X";
Float64 colorBarMaximum 180.0;
Float64 colorBarMinimum -180.0;
String ioos_category "Location";
String long_name "Longitude";
String standard_name "longitude";
String units "degrees_east";
}
depth {
String _CoordinateAxisType "Height";
String _CoordinateZisPositive "down";
Float32 actual_range -1.17, 72.048;
String axis "Z";
String ioos_category "Location";
String long_name "Sea Floor Depth";
String nerc_identifier "https://vocab.nerc.ac.uk/collection/P07/current/CFV13N17/";
String positive "down";
String source_name "sea_floor_depth_below_sea_surface";
String standard_name "depth";
String units "m";
}
boosting_class_id {
Int32 actual_range 0, 5;
String description "Index of substrate classification according to supervised model : 0 - Block; 1 - Cobble; 2 - Gravel; 3 - Bedrock; 4 - Sand; 5 - Sandy Mud";
String long_name "Boosting Class ID";
String original_name "boosting class";
String units "unitless";
}
boosting_class {
String units "unitless";
}
gmm_class_id {
Int32 actual_range 0, 6;
String description "Index of substrate classification according to unsupervised model: 0 - Fit the most with the supervised sand class; 1 - Unknown class; 2 - Fit the most with the supervised gravel class; 3 - Unknown class; 4 - Fit the most with the supervised block class; 5 - Fit the most with the supervised cobble class; 6 - Fit the most with the supervised bedrock class";
String long_name "GMM Class ID";
String original_name "gmm class";
String units "unitless";
}
gmm_class {
String units "unitless";
}
}
NC_GLOBAL {
String cdm_data_type "Point";
String comment "Do not use unsupervised model data for navigation purposes";
String comment_fr "Ne pas utiliser à des fins de navigation et en particulier les données du modèle non supervisé";
String contributor_institution "CIDCO, CIDCO, Fisheries and Oceans Canada, CIDCO, CIDCO";
String contributor_name "Guillaume Labbé-Morissette, Patrick Charron-Morneau, Yanick Gendreau, Théau Leclercq, Dominic Ndeh Munang";
String contributor_role "owner, distributor, collaborator, metadata custodian, collaborator";
String Conventions "CF-1.10, COARDS ACDD-1.3";
String creator_name "Interdisciplinary Centre for the Development of Ocean Mapping";
String creator_name_fr "Centre Interdisciplinaire de Développement en Cartographie des Océans (CIDCO)";
String creator_type "institution";
String DOI "https://doi.org/10.26071/ogsl-66c132fc-b150";
String featureType "Point";
String geodeticDatum_description "EPSG: 26919 - NAD83 / UTM zone 19N";
String geospatial_lat_units "degrees_north";
String geospatial_lon_units "degrees_east";
Float64 geospatial_vertical_max 72.048;
Float64 geospatial_vertical_min -1.17;
String geospatial_vertical_positive "down";
String geospatial_vertical_units "m";
String grid_mapping_epsg_code "EPSG:4326";
String grid_mapping_epsg_code_url "https://epsg.io/4326";
String grid_mapping_geographic_crs_name "WGS 84";
String grid_mapping_inverse_flattening "298.2572236";
String grid_mapping_name "latitude_longitude";
String grid_mapping_prime_meridian_name "Greenwich";
String grid_mapping_semi_major_axis "6378137";
String history
"Data and metadata were standardized and then checked with the SLGO data validation tool.
2024-11-22T04:38:09Z (local files)
2024-11-22T04:38:09Z https://erddap.ogsl.ca/erddap/tabledap/cidcoBenthicSubstrateAi.html";
String infoUrl "https://www.cidco.ca/";
String institution "The Interdisciplinary Centre for the Development of Ocean Mapping";
String institution_fr "Centre Interdisciplinaire de Développement en Cartographie des Océans";
String instrument "Multibeam echosounder, Hydrins attitude sensor, Septentrio GNSS Receiver";
String instrument_0_description "MBES Reson Seabat 7125SV dual frequency (400 and 200 kHz)";
String instrument_0_identifier "https://vocab.nerc.ac.uk/collection/L22/current/TOOL0772/";
String instrument_0_name "Multibeam Echosounder";
String instrument_1_description "Navigation correction (roll, pitch, heading, heave)";
String instrument_1_identifier "https://vocab.nerc.ac.uk/collection/L22/current/TOOL0833/";
String instrument_1_name "Hydrins attitude sensor";
String instrument_2_description "GNSS (Global Navigation Satellite System) Receiver and Antenna using for positioning";
String instrument_2_identifier "https://vocab.nerc.ac.uk/collection/L05/current/301/";
String instrument_2_name "Septentrio GNSS Receiver";
String instrument_fr "Sondeur multifaisceaux, station inertielle Hydrins, recepteur GNSS Septentrio";
String keywords "artificial intelligence, benthic substrates classification, benthic substrates mapping, supervised machine learning, unsupervised machine learning";
String keywords_fr "cartographie des substrats benthiques, classification des substrats benthiques, apprentissage automatique supervisé, apprentissage automatique non supervisé, intelligence artificielle";
String keywords_vocabulary "GCMD Science Keywords";
String license "Creative Commons Attribution 4.0 International license CC-BY 4.0. Allows for open sharing and adaptation of the data provided that the original creator is attributed";
String licenseUrl "https://creativecommons.org/licenses/by/4.0/";
String location "St Ludger";
String marine_region "St. Lawrence Estuary";
String mission_time_coverage_end "2019-10-18";
String mission_time_coverage_start "2018-10-15";
String platform "research vessel";
String platform_vocabulary "https://vocab.nerc.ac.uk/collection/L06/current/";
String publisher_email "\"info@ogsl.ca\"";
String publisher_name "St. Lawrence Global Observatory";
String publisher_name_fr "Observatoire global du Saint-Laurent";
String publisherID "https://ror.org/03wfagk22";
String related_datasets "https://erddap.ogsl.ca/erddap/tabledap/cidcoBenthicSubstrateAiImages.html";
String sourceUrl "(local files)";
String standard_name_nerc_vocabulary "The NERC Vocabulary Server (NVS)";
String standard_name_other_vocabulary "dwc: Darwin Core List of Terms (v 2023-09); dcmi: Dublin Core Metadata Initiative Metadata Terms (v 2020-01)";
String standard_name_vocabulary "CF Standard Name Table v79";
String subsetVariables "location, time, boosting_class_id, boosting_class, gmm_class_id, gmm_class";
String summary "The substrate classification data were generated with two machine learning models: (1) A first model trained with field truth data from Fisheries and Oceans Canada and using a gradient reinforcement method. (2) A second model trained without field truth data and based on a Gaussian mixture method. The aim of generating this data is to facilitate the classification of substrates for various fields (fishing, dredging, gas and oil) via artificial intelligence, and to make it more accessible because it is less expensive from an operational point of view.";
String summary_fr "Les données de classifications des substrats ont été générés avec deux modèles d'apprentissage automatique : (1) Un premier modèle entraîné avec des données de vérité terrain provenant de Pêches et Océans Canada et utilisant une méthode de renforcement du gradient. (2) Un deuxième modèle entraîné sans données de vérité terrain et s'appuyant sur une méthode de mélange gaussien. L'ambition de la génération de ces données est de faciliter la classification des substrats pour des domaines variés (la pêche, le dragage, gaz et pétrole) via l'intelligence artificielle, et la rendre plus accessible car moins couteux d'un point de vue opérationnel.";
String title "Classification of Benthic Substrates (Data) Using Supervised and Unsupervised Machine Learning Models on the North Shore of the St. Lawrence Maritime Estuary | Données de classification de substrats benthiques générées par Intelligence Artificielle sur la rive nord de l'estuaire maritime";
}
}
Data Access Protocol (DAP) and its
selection constraints.
The URL specifies what you want: the dataset, a description of the graph or the subset of the data, and the file type for the response.
Tabledap request URLs must be in the form
https://coastwatch.pfeg.noaa.gov/erddap/tabledap/datasetID.fileType{?query}
For example,
https://coastwatch.pfeg.noaa.gov/erddap/tabledap/pmelTaoDySst.htmlTable?longitude,latitude,time,station,wmo_platform_code,T_25&time>=2015-05-23T12:00:00Z&time<=2015-05-31T12:00:00Z
Thus, the query is often a comma-separated list of desired variable names,
followed by a collection of
constraints (e.g., variable<value),
each preceded by '&' (which is interpreted as "AND").
For details, see the tabledap Documentation.