Coast Train--Labeled imagery for training and evaluation of data-driven models for image segmentation

Metadata also available as - [Questions & Answers] - [Parseable text] - [XML]

Metadata:

Identification_Information
Data_Quality_Information
Spatial_Data_Organization_Information
Entity_and_Attribute_Information
Distribution_Information
Metadata_Reference_Information

Identification_Information:

Citation:

Citation_Information:

Originator: Phillipe A. Wernette
Originator: Daniel D. Buscombe
Originator: Sharon Fitzpatrick
Originator: Jaycee Favela
Originator: Nicholas Enwright
Originator: Evan Goldstein
Originator: Erin Dunand
Publication_Date: 20220319
Title:

Coast Train--Labeled imagery for training and evaluation of data-driven models for image segmentation

Geospatial_Data_Presentation_Form:

list of images and details in csv format; imagery in NumPy binary file format

Series_Information:

Series_Name: data release
Issue_Identification: DOI:10.5066/P91NP87I

Publication_Information:

Publication_Place:

Pacific Coastal and Marine Science Center, Santa Cruz, California

Publisher: U.S. Geological Survey

Online_Linkage: https://doi.org/10.5066/P91NP87I

Description:

Abstract:

Coast Train is a library of images of coastal environments, annotations, and corresponding thematic label masks (or ‘label images’) collated for the purposes of training and evaluating machine learning (ML), deep learning, and other models for image segmentation. It includes image sets from both geospatial satellite, aerial, and UAV imagery and orthomosaics, as well as non-geospatial oblique and nadir imagery. Images include a diverse range of coastal environments from the U.S. Pacific, Gulf of Mexico, Atlantic, and Great Lakes coastlines, consisting of time-series of high-resolution (≤1m) orthomosaics and satellite image tiles (10–30m). Each image, image annotation, and labelled image is available as a single NPZ zipped file. NPZ files follow the following naming convention: {datasource}_{numberofclasses}_{threedigitdatasetversion}.zip, where {datasource} is the source of the original images (for example, NAIP, Landsat 8, Sentinel 2), {numberofclasses} is the number of classes used to annotate the images, and {threedigitdatasetversion} is the three-digit code corresponding to the dataset version (in other words, 001 is version 1). Each zipped folder contains a collection of NPZ format files, each of which corresponds to an individual image. An individual NPZ file is named after the image that it represents and contains (1) a CSV file with detail information for every image in the zip folder and (2) a collection of the following NPY files: orig_image.npy (original input image unedited), image.npy (original input image after color balancing and normalization), classes.npy (list of classes annotated and present in the labelled image), doodles.npy (integer image of all image annotations), color_doodles.npy (color image of doodles.npy), label.npy (labelled image created from the classes present in the annotations), and settings.npy (annotation and machine learning settings used to generate the labelled image from annotations). All NPZ files can be extracted using the utilities available in Doodler (Buscombe, 2022). A merged CSV file containing detail information on the complete imagery collection is available at the top level of this data release, details of which are available in the Entity and Attribute section of this metadata file.

Purpose:

Training machine learning (ML) and other models for segmentation will greatly facilitate the creation of land cover maps from geospatial imagery with greater specificity, as well as mapping coastal sediments, transient waterbodies, landforms, and other features of interest, in both geospatial and non-geospatial imagery. Coast Train adheres to the principle of ‘Map Once, Use Many Times’ and is well positioned to transfer learning across a wide range of coastal environments.

Supplemental_Information:

Any use of trade, product, or firm names is for descriptive purposes only and does not imply endorsement by the U.S. Government.

Time_Period_of_Content:

Time_Period_Information:

Range_of_Dates/Times:

Beginning_Date: 20080101
Ending_Date: 20201231

Currentness_Reference: date range of imagery in library

Status:

Progress: Planned
Maintenance_and_Update_Frequency: As needed

Spatial_Domain:

Bounding_Coordinates:

West_Bounding_Coordinate: -180.0
East_Bounding_Coordinate: 180.0
North_Bounding_Coordinate: 90.0
South_Bounding_Coordinate: -90.0

Keywords:

Theme:

Theme_Keyword_Thesaurus: USGS Metadata Identifier
Theme_Keyword: USGS:9cdb71c1-cc5a-4786-9232-93d7e7a340cf

Theme:

Theme_Keyword_Thesaurus: ISO 19115 Topic Category
Theme_Keyword: environment
Theme_Keyword: geoscientificinformation

Theme:

Theme_Keyword_Thesaurus: Data Categories for Marine Planning
Theme_Keyword: distributions
Theme_Keyword: Physical Habitats and Geomorphology
Theme_Keyword: habitat
Theme_Keyword: infrastructure
Theme_Keyword: structures

Theme:

Theme_Keyword_Thesaurus: USGS Thesaurus
Theme_Keyword: image analysis
Theme_Keyword: mitigation of coastal hazards
Theme_Keyword: remote sensing
Theme_Keyword: aerial photography
Theme_Keyword: multispectral imaging
Theme_Keyword: visible light imaging
Theme_Keyword: datasets
Theme_Keyword: geospatial datasets
Theme_Keyword: image collections
Theme_Keyword: earth sciences
Theme_Keyword: geography
Theme_Keyword: geology
Theme_Keyword: life sciences
Theme_Keyword: botany
Theme_Keyword: ecology
Theme_Keyword: social sciences
Theme_Keyword: biological and physical processes
Theme_Keyword: hazards
Theme_Keyword: human impacts
Theme_Keyword: land use change
Theme_Keyword: land use and land cover
Theme_Keyword: coastal ecosystems

Theme:

Theme_Keyword_Thesaurus: Marine Realms Information Bank (MRIB) keywords
Theme_Keyword: agents of coastal change
Theme_Keyword: coastal processes
Theme_Keyword: anthropogenic agents of coastal change
Theme_Keyword: coastal development
Theme_Keyword: coastal protection structures
Theme_Keyword: effects of coastal change
Theme_Keyword: human responses to coastal change
Theme_Keyword: earth system
Theme_Keyword: bay
Theme_Keyword: beach
Theme_Keyword: cape
Theme_Keyword: cliff
Theme_Keyword: coast
Theme_Keyword: coastal barrier
Theme_Keyword: coastal plain
Theme_Keyword: cove
Theme_Keyword: dune
Theme_Keyword: island
Theme_Keyword: lagoon
Theme_Keyword: lake
Theme_Keyword: marsh
Theme_Keyword: mudflat
Theme_Keyword: ocean
Theme_Keyword: shore
Theme_Keyword: swamp
Theme_Keyword: tidal flat
Theme_Keyword: tidal inlet
Theme_Keyword: beach zone communities
Theme_Keyword: breakwater/shoreline stabilization structure
Theme_Keyword: bridge
Theme_Keyword: canal
Theme_Keyword: jetty
Theme_Keyword: environment
Theme_Keyword: hazards and disasters
Theme_Keyword: erosion
Theme_Keyword: floods
Theme_Keyword: remote sensing
Theme_Keyword: aerial and satellite photography
Theme_Keyword: biology
Theme_Keyword: ecology
Theme_Keyword: computer science
Theme_Keyword: geography
Theme_Keyword: environmental geography
Theme_Keyword: physical geography
Theme_Keyword: geology
Theme_Keyword: information science

Theme:

Theme_Keyword_Thesaurus: None
Theme_Keyword: U.S. Geological Survey
Theme_Keyword: USGS
Theme_Keyword: Coastal and Marine Hazards and Resources Program
Theme_Keyword: CMHRP
Theme_Keyword: Pacific Coastal and Marine Science Center
Theme_Keyword: PCMSC
Theme_Keyword: St. Petersburg Coastal and Marine Science Center
Theme_Keyword: SPCMSC
Theme_Keyword: Wetland and Aquatic Research Center
Theme_Keyword: WARC
Theme_Keyword: Woods Hole Coastal and Marine Science Center
Theme_Keyword: WHCMSC

Place:

Place_Keyword_Thesaurus: Geographic Names Information System (GNIS)
Place_Keyword: United States

Access_Constraints: None
Use_Constraints:

USGS-authored or produced data and information are in the public domain from the U.S. Government and are freely redistributable with proper metadata and source attribution. Please recognize and acknowledge the U.S. Geological Survey as the originator(s) of the dataset and in products derived from these data.

Point_of_Contact:

Contact_Information:

Contact_Organization_Primary:

Contact_Organization:

U.S. Geological Survey, Pacific Coastal and Marine Science Center

Contact_Person: PCMSC Science Data Coordinator

Contact_Address:

Address_Type: mailing and physical
Address: 2885 Mission Street
City: Santa Cruz
State_or_Province: CA
Postal_Code: 95060

Contact_Voice_Telephone: 831-427-4747
Contact_Electronic_Mail_Address: pcmsc_data@usgs.gov

Browse_Graphic:

Browse_Graphic_File_Name: coast_train_thumbnail.png
Browse_Graphic_File_Description:

Split graphic with the original image on the left and the segmented right half of the image on the right.

Browse_Graphic_File_Type: PNG

Native_Data_Set_Environment:

Images were processed using Doodler software (Buscombe, 2022) in Windows operating systems.

Cross_Reference:

Citation_Information:

Originator: Daniel D. Buscombe
Publication_Date: 2022
Title:

Doodler--A web application built with plotly/dash for image segmentation with minimal supervision

Geospatial_Data_Presentation_Form: software
Series_Information:

Series_Name: software release
Issue_Identification: DOI:10.5066/P9YVHL23

Publication_Information:

Publication_Place:

Pacific Coastal and Marine Science Center, Santa Cruz, California

Publisher: U.S. Geological Survey

Other_Citation_Details:

Buscombe, D.D., 2022, Doodler--A web application built with plotly/dash for image segmentation with minimal supervision: U.S. Geological Survey software release, https://doi.org/10.5066/P9YVHL23

Online_Linkage: https://doi.org/10.5066/P9YVHL23

Data_Quality_Information:

Attribute_Accuracy:

Attribute_Accuracy_Report:

Mean Intersection over Union (IoU) scores for quantifying inter-labeler agreement were computed using 120 images across two datasets, namely NAIP (70 image pairs) and Sentinel-2 (50 image pairs), that have been labeled independently by experienced labelers. Mean IoU is the standard way to report agreement between two realizations of the same label image. Further, because IoU quantifies spatial overlap and is prone to class imbalance, Kullback-Leibler divergence scores were also computed to quantify agreement between class-frequency distributions. When comparing IoU and Dice scores, it is preferable to examine agreement using multiple independent metrics. The mean of mean IoU scores was 0.88, which we recommend using as an expected irreducible error. Previous research suggests that mean IoU scores tend to be inversely correlated with number of classes; therefore, this error is a conservative estimate.

Logical_Consistency_Report:

All annotation values are integer based, with each integer corresponding to a unique class. The program used to generate the final classified/labelled images ensured that every pixel in the original image is classified into one of the annotated classes. There is no possibility that the actual values are outside of the reported ranges of values.

Completeness_Report:

Dataset is considered complete for the information presented, as described in the abstract. Users are advised to read the rest of the metadata record carefully for additional details.

Positional_Accuracy:

Horizontal_Positional_Accuracy:

Horizontal_Positional_Accuracy_Report:

A formal accuracy assessment of the horizontal positional information in the dataset has not been conducted. Each of the input data sources has its own horizontal accuracy available in their source metadata.

Lineage:

Process_Step:

Process_Description:

Image Annotation/Doodling--Each image was opened using Doodler with the class list provided in the metadata sheet. The user would then select a single class from the options on the right and click and hold on the image to begin drawing a line (annotate/doodle) where the selected class exists on the image. Annotations can be quick and as simple as a point or single line or as complex as a meandering or looping back series of lines. This annotation process was repeated one or more times for every class present in the image.

Process_Date: 20211231

Process_Step:

Process_Description:

Image Classification/Segmentation--Once image annotations were complete for all classes present in the image, the program will segment the image and classify every pixel in it by checking the “Compute/Show segmentation” box on the right. If the final image is not accurate to the classes present and their distribution, then the user can uncheck the “Compute/Show segmentation” box and repeat the annotation and classification/segmentation steps until they are satisfied with the final segmented image.

Process_Date: 20211231

Process_Step:

Process_Description:

Edited to correct spelling of author name. No data were changed. (scochran@usgs.gov)

Process_Date: 20230504

Spatial_Data_Organization_Information:

Indirect_Spatial_Reference:

Original images were downloaded at sites along the conterminous U.S. coastline, including sites along the U.S. Atlantic, Gulf of Mexico, Pacific, and Great Lakes coasts. Sites were selected to provide a representative sample of an array of coastal types (for example, sandy, cliff, marsh, wetland, developed). Refer to the self-contained NPZ files for more information on locations of original images.

Entity_and_Attribute_Information:

Detailed_Description:

Entity_Type:

Entity_Type_Label: CoastTrain_imagery_details.csv
Entity_Type_Definition:

Table containing detailed information about the imagery in this dataset.

Entity_Type_Definition_Source: Producer defined

Attribute:

Attribute_Label: name
Attribute_Definition: Name of image source
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Unrepresentable_Domain: Unique identifier of image name.

Attribute:

Attribute_Label: publisher
Attribute_Definition: Original publisher of the image source
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Unrepresentable_Domain: Unique identifier of image publisher.

Attribute:

Attribute_Label: labels
Attribute_Definition:

The image label file. One-hot-encoded label image (2D raster) in 8-bit unsigned integer. Each integer encodes a class label, incrementing through 'classes' starting at zero.

Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Unrepresentable_Domain: Unique identifier of label image file.

Attribute:

Attribute_Label: images
Attribute_Definition: The original image file used in classification.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Unrepresentable_Domain: Unique identifier of image filename.

Attribute:

Attribute_Label: annotation_image_filename
Attribute_Definition: Image filename with annotations.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Unrepresentable_Domain: Unique identifier of annotation image filename.

Attribute:

Attribute_Label: classes_array
Attribute_Definition: An array of classification classes in the image.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: water
Enumerated_Domain_Value_Definition: Classified as water
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: whitewater
Enumerated_Domain_Value_Definition: Classified as whitewater
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: surf
Enumerated_Domain_Value_Definition: Classified as surf
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: mud_silt
Enumerated_Domain_Value_Definition: Classified as mud or fine sediment
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: sand
Enumerated_Domain_Value_Definition: Classified as bare sand
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: gravel
Enumerated_Domain_Value_Definition: Classified as gravel
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: gravel_shell
Enumerated_Domain_Value_Definition: Classified as mixture of gravel and shells
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: cobble_gravel
Enumerated_Domain_Value_Definition: Classified as gravel with cobbles
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: bedrock
Enumerated_Domain_Value_Definition: Classified as exposed bedrock
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: ice_snow
Enumerated_Domain_Value_Definition: Classified as ice or snow
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: bare_ground
Enumerated_Domain_Value_Definition: Classified as bare ground
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: sediment
Enumerated_Domain_Value_Definition: Classified as bare sediment
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: other_natural_terrain
Enumerated_Domain_Value_Definition: Classified as other natural terrain
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: other_bare_natural_terrain
Enumerated_Domain_Value_Definition: Classified as other bare natural terrain
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: vegetated
Enumerated_Domain_Value_Definition: Classified as vegetation
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: vegetated_ground
Enumerated_Domain_Value_Definition: Classified as ground with vegetation
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: vegetated_surface
Enumerated_Domain_Value_Definition: Classified as vegetation
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: marsh_vegetation
Enumerated_Domain_Value_Definition: Classified as marsh vegetation
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: terrestrial_vegetation
Enumerated_Domain_Value_Definition: Classified as terrestrial vegetation
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: agricultural
Enumerated_Domain_Value_Definition: Classified as agricultural
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: cloud
Enumerated_Domain_Value_Definition: Classified as cloud
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: development
Enumerated_Domain_Value_Definition: Classified as consisting of human development
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: dev
Enumerated_Domain_Value_Definition: Classified as consisting of human development
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: coastal_defense
Enumerated_Domain_Value_Definition: Classified as coastal defense
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: buildings
Enumerated_Domain_Value_Definition: Classified as building
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: pavement_road
Enumerated_Domain_Value_Definition: Classified as pavement
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: vehicles
Enumerated_Domain_Value_Definition: Classified as vehicles
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: people
Enumerated_Domain_Value_Definition: Classified as person
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: other_anthro
Enumerated_Domain_Value_Definition: Classified as other anthropogenic object
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: unusual
Enumerated_Domain_Value_Definition: Classified as unusal object or land cover
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: unknown
Enumerated_Domain_Value_Definition: Classified as unknown land cover
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: no_data
Enumerated_Domain_Value_Definition: No data contained in pixels
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute_Domain_Values:

Enumerated_Domain:

Enumerated_Domain_Value: nodata
Enumerated_Domain_Value_Definition: No data contained in pixels
Enumerated_Domain_Value_Definition_Source: Producer defined

Attribute:

Attribute_Label: num_classes
Attribute_Definition: Number of classification classes in the image.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 1
Range_Domain_Maximum: 12

Attribute:

Attribute_Label: classes_integer
Attribute_Definition: One integer per class in num_classes.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 0
Range_Domain_Maximum: 12

Attribute:

Attribute_Label: classes_present_integer
Attribute_Definition: An array of integer classes present in the image.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 0
Range_Domain_Maximum: 12

Attribute:

Attribute_Label: classes_present_array
Attribute_Definition: An array of classes present in the image.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Unrepresentable_Domain: Values present in image from classes

Attribute:

Attribute_Label: pen_width
Attribute_Definition:

Final width in pixels of pen used to annotate in the Doodler program.

Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 1
Range_Domain_Maximum: 10

Attribute:

Attribute_Label: CRF_theta
Attribute_Definition: Internal classifier hyperparameter used by the Doodler program.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 1
Range_Domain_Maximum: 1

Attribute:

Attribute_Label: CRF_mu
Attribute_Definition: Internal classifier hyperparameter used by the Doodler program.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 1
Range_Domain_Maximum: 99

Attribute:

Attribute_Label: CRF_downsample_factor
Attribute_Definition: Internal classifier hyperparameter used by the Doodler program.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 1
Range_Domain_Maximum: 5

Attribute:

Attribute_Label: Classifier_downsample_factor
Attribute_Definition: Internal classifier hyperparameter used by the Doodler program.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 1
Range_Domain_Maximum: 8

Attribute:

Attribute_Label: prob_of_unary_potential
Attribute_Definition: Internal classifier hyperparameter used by the Doodler program.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 0.1
Range_Domain_Maximum: 3.0

Attribute:

Attribute_Label: doodle_spatial_density
Attribute_Definition: Proportion of the image annotated.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 0.000526323
Range_Domain_Maximum: 0.999627422

Attribute:

Attribute_Label: num_of_scales
Attribute_Definition: Internal classifier hyperparameter used by the Doodler program.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 3
Range_Domain_Maximum: 3

Attribute:

Attribute_Label: acc_georef
Attribute_Definition:

Accuracy, in meters, of the specification of 'XMin', 'XMax' and 'YMin', 'YMax'.

Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 1
Range_Domain_Maximum: 11.248

Attribute:

Attribute_Label: epsg
Attribute_Definition:

EPSG code for the projected coordinate system. See 'CRS' attribute for a complete description of codes used.

Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 26910
Range_Domain_Maximum: 32618

Attribute:

Attribute_Label: year
Attribute_Definition: Acquisition year of the image source.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 2008
Range_Domain_Maximum: 2021

Attribute:

Attribute_Label: month
Attribute_Definition: Acquisition month of the image source.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 1
Range_Domain_Maximum: 12

Attribute:

Attribute_Label: day
Attribute_Definition: Acquisition day of the image source.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 1
Range_Domain_Maximum: 31

Attribute:

Attribute_Label: hour
Attribute_Definition: Acquisition hour of the image source.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 0
Range_Domain_Maximum: 23

Attribute:

Attribute_Label: minute
Attribute_Definition: Acquisition minute of the image source.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 0
Range_Domain_Maximum: 59

Attribute:

Attribute_Label: second
Attribute_Definition: Acquisition second of the image source.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 0
Range_Domain_Maximum: 59

Attribute:

Attribute_Label: XMin
Attribute_Definition: Minimum easting of the image footprint.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 233870.0
Range_Domain_Maximum: 787860.0

Attribute:

Attribute_Label: XMax
Attribute_Definition: Maximum easting of the image footprint.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 235750.0
Range_Domain_Maximum: 790530.0

Attribute:

Attribute_Label: YMin
Attribute_Definition: Minimum northing of the image footprint.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 2875253.0
Range_Domain_Maximum: 5332914.0

Attribute:

Attribute_Label: YMax
Attribute_Definition: Maximum northing of the image footprint.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 2884030.0
Range_Domain_Maximum: 5333378.0

Attribute:

Attribute_Label: LonMin
Attribute_Definition: Minimum longitude (WGS84) of image footprint.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: -124.0922272
Range_Domain_Maximum: -69.95201111

Attribute:

Attribute_Label: LonMax
Attribute_Definition: Maximum longitude (WGS84) of image footprint.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: -124.0478924
Range_Domain_Maximum: -69.9405098

Attribute:

Attribute_Label: LatMin
Attribute_Definition: Minimum longitude (WGS84) of image footprint.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 25.98761753
Range_Domain_Maximum: 48.14810677

Attribute:

Attribute_Label: LatMax
Attribute_Definition: Maximum latitude (WGS84) of image footprint.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 26.06287667
Range_Domain_Maximum: 48.15232107

Attribute:

Attribute_Label: CRS
Attribute_Definition:

The projected coordinate system description relating to XMin, XMax, YMin, YMax.

Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Unrepresentable_Domain: Projected coordinate system definition

Attribute:

Attribute_Label: px_m
Attribute_Definition: Horizontal size of pixel in meters.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 0.15
Range_Domain_Maximum: 15

Attribute:

Attribute_Label: ImageHeightPx
Attribute_Definition: Number of pixels in horizontal dimension of height.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 31
Range_Domain_Maximum: 2481

Attribute:

Attribute_Label: ImageWidthPx
Attribute_Definition: Number of pixels in horizontal dimension of width.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 32
Range_Domain_Maximum: 2209

Attribute:

Attribute_Label: ImageBands
Attribute_Definition: Number of bands in the image.
Attribute_Definition_Source: Producer defined
Attribute_Domain_Values:

Range_Domain:

Range_Domain_Minimum: 3
Range_Domain_Maximum: 3

Overview_Description:

Entity_and_Attribute_Overview:

Each image, image annotation, and labelled image is available as a single NPZ zipped file. NPZ files follow the following naming convention: {datasource}_{numberofclasses}_{threedigitdatasetversion}.zip, where {datasource} is the source of the original images (for example, NAIP, Landsat 8, Sentinel 2), {numberofclasses} is the number of classes used to annotate the images, and {threedigitdatasetversion} is the three digit code corresponding to the dataset version (in other words, 001 is version 1). Each zipped folder contains a collection of NPZ format files, each of which corresponds to an induvial image. An individual NPZ file is named after the image that it represents and contains (1) a CSV file with metadata information for every image and (2) a collection of the following NPY files: orig_image.npy (original input image unedited), image.npy (original input image after color balancing and normalization), classes.npy (list of classes annotated and present in the labelled image), doodles.npy (integer image of all image annotations), color_doodles.npy (color image of doodles.npy), label.npy (labelled image created from the classes present in the annotations), and settings.npy (annotation and machine learning settings used to generate the labelled image from annotations). All NPZ files can be extracted using the utilities available in Doodler (Buscombe, 2022; https://doi.org/10.5066/P9YVHL23).

Entity_and_Attribute_Detail_Citation:

The entity and attribute information was generated by the individual and/or agency identified as the originator of the data set. Please review the rest of the metadata record for additional details and information.

Distribution_Information:

Distributor:

Contact_Information:

Contact_Organization_Primary:

Contact_Organization: U.S. Geological Survey - CMGDS

Contact_Address:

Address_Type: mailing and physical
Address: 2885 Mission Street
City: Santa Cruz
State_or_Province: CA
Postal_Code: 95060

Contact_Voice_Telephone: 831-427-4747
Contact_Electronic_Mail_Address: pcmsc_data@usgs.gov

Resource_Description:

Images are provided in NPZ format. Each NPZ file corresponds to a single image that has been annotated/labelled and classified/segmented. The NPZ file names consist of the {image_source}_{number_of_classes}_{data_release_version_number}, delimited by underscores. The first element {image_source} represents the original source of the image (for example, Landsat 8 would be “L8”, Sentinel 2 would be “S2”), the second element {number_of_classes} represents the number of classes used during labelling (for example, “6 classes”, “11classes”, and The third element {data_release_version_number} represents the data release version that the image is part of (for example, all datasets for version 1 will have “001” as the third part of the NPZ filename). Each NPZ file contains at least seven (7) different NPY files: (1) orig_image.npy (original input image unedited), (2) image.npy (original input image after color balancing and normalization), (3) classes.npy (list of classes annotated and present in the labelled image), (4) doodles.npy (integer image of all image annotations), (5) color_doodles.npy (color image of doodles.npy), (6) label.npy (labelled image created from the classes present in the annotations), and (7) settings.npy (annotation and machine learning settings used to generate the labelled image from annotations). Some NPZ files may contain one or more additional sets of seven files with one or more zeros appended to the beginning of the NPY file names. These additional files are grouped by the number of zeros preceding the regular files described above and represent previous attempts at annotation and classification/segmentation for that image. For example, all NPY files with one zero appended to the beginning of the NPY file names represent the first attempt, all NPY files with two zeros appended to the beginning of the NPY file names represent the second attempt, etc. A merged CSV file (CoastTrain_imagery_details.csv) contains detailed information on the complete imagery collection.

Distribution_Liability:

Unless otherwise stated, all data, metadata and related materials are considered to satisfy the quality standards relative to the purpose for which the data were collected. Although these data and associated metadata have been reviewed for accuracy and completeness and approved for release by the U.S. Geological Survey (USGS), no warranty expressed or implied is made regarding the display or utility of the data on any other system or for general or scientific purposes, nor shall the act of distribution constitute any such warranty.

Standard_Order_Process:

Digital_Form:

Digital_Transfer_Information:

Format_Name: comma-delimited text
File_Decompression_Technique: none

Digital_Transfer_Option:

Online_Option:

Computer_Contact_Information:

Network_Address:

Network_Resource_Name: https://doi.org/10.5066/P91NP87I

Access_Instructions:

CSV files can be downloaded using the Network_Resource_Name link then scrolling down to the Land Cover Data section.

Digital_Form:

Digital_Transfer_Information:

Format_Name: NPY
File_Decompression_Technique:

Each ZIP file contains multiple NPZ files. Individual NPZ files can be unzipped and all NPY files converted to readable raster formats by using utility scripts associated with Doodler (Buscombe, 2022; https://doi.org/10.5066/P9YVHL23). NPZ files were compressed using deflate compression.

Digital_Transfer_Option:

Online_Option:

Computer_Contact_Information:

Network_Address:

Network_Resource_Name: https://doi.org/10.5066/P91NP87I

Access_Instructions:

Imagery data can be downloaded using the Network_Resource_Name link then scrolling down to the Land Cover Data section.

Fees: None.

Technical_Prerequisites:

These data can be viewed with Doodler software (Buscombe, 2022; https://doi.org/10.5066/P9YVHL23).

Metadata_Reference_Information:

Metadata_Date: 20220504
Metadata_Contact:

Contact_Information:

Contact_Organization_Primary:

Contact_Organization:

U.S. Geological Survey, Pacific Coastal and Marine Science Center

Contact_Person: PCMSC Science Data Coordinator

Contact_Address:

Address_Type: mailing and physical
Address: 2885 Mission Street
City: Santa Cruz
State_or_Province: CA
Postal_Code: 95060

Contact_Voice_Telephone: 831-427-4747
Contact_Electronic_Mail_Address: pcmsc_data@usgs.gov

Metadata_Standard_Name: Content Standard for Digital Geospatial Metadata
Metadata_Standard_Version: FGDC-STD-001-1998

This page is <https://cmgds.marine.usgs.gov/catalog/pcmsc/DataReleases/CMGDS_DR_tool/DR_P91NP87I/CoastTrain_imagery_details_metadata.html>