Phillipe A. Wernette Daniel D. Buscombe Sharon Fitzpatrick Jaycee Favela Nicholas Enwright Evan Goldstein Erin Dunand 20220319 list of images and details in csv format; imagery in NumPy binary file format data release DOI:10.5066/P91NP87I Pacific Coastal and Marine Science Center, Santa Cruz, California U.S. Geological Survey https://doi.org/10.5066/P91NP87I 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. 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. Any use of trade, product, or firm names is for descriptive purposes only and does not imply endorsement by the U.S. Government. 20080101 20201231 date range of imagery in library Planned As needed -180.0 180.0 90.0 -90.0 USGS Metadata Identifier USGS:9cdb71c1-cc5a-4786-9232-93d7e7a340cf ISO 19115 Topic Category environment geoscientificinformation Data Categories for Marine Planning distributions Physical Habitats and Geomorphology habitat infrastructure structures USGS Thesaurus image analysis mitigation of coastal hazards remote sensing aerial photography multispectral imaging visible light imaging datasets geospatial datasets image collections earth sciences geography geology life sciences botany ecology social sciences biological and physical processes hazards human impacts land use change land use and land cover coastal ecosystems Marine Realms Information Bank (MRIB) keywords agents of coastal change coastal processes anthropogenic agents of coastal change coastal development coastal protection structures effects of coastal change human responses to coastal change earth system bay beach cape cliff coast coastal barrier coastal plain cove dune island lagoon lake marsh mudflat ocean shore swamp tidal flat tidal inlet beach zone communities breakwater/shoreline stabilization structure bridge canal jetty environment hazards and disasters erosion floods remote sensing aerial and satellite photography biology ecology computer science geography environmental geography physical geography geology information science None U.S. Geological Survey USGS Coastal and Marine Hazards and Resources Program CMHRP Pacific Coastal and Marine Science Center PCMSC St. Petersburg Coastal and Marine Science Center SPCMSC Wetland and Aquatic Research Center WARC Woods Hole Coastal and Marine Science Center WHCMSC Geographic Names Information System (GNIS) United States None 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. U.S. Geological Survey, Pacific Coastal and Marine Science Center PCMSC Science Data Coordinator mailing and physical

2885 Mission Street

Santa Cruz CA 95060 831-427-4747 pcmsc_data@usgs.gov coast_train_thumbnail.png Split graphic with the original image on the left and the segmented right half of the image on the right. PNG Images were processed using Doodler software (Buscombe, 2022) in Windows operating systems. Daniel D. Buscombe 2022 software software release DOI:10.5066/P9YVHL23 Pacific Coastal and Marine Science Center, Santa Cruz, California U.S. Geological Survey 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 https://doi.org/10.5066/P9YVHL23 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. 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. 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. 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. 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. 20211231 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. 20211231 Edited to correct spelling of author name. No data were changed. (scochran@usgs.gov) 20230504 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. CoastTrain_imagery_details.csv Table containing detailed information about the imagery in this dataset. Producer defined name Name of image source Producer defined Unique identifier of image name. publisher Original publisher of the image source Producer defined Unique identifier of image publisher. labels 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. Producer defined Unique identifier of label image file. images The original image file used in classification. Producer defined Unique identifier of image filename. annotation_image_filename Image filename with annotations. Producer defined Unique identifier of annotation image filename. classes_array An array of classification classes in the image. Producer defined water Classified as water Producer defined whitewater Classified as whitewater Producer defined surf Classified as surf Producer defined mud_silt Classified as mud or fine sediment Producer defined sand Classified as bare sand Producer defined gravel Classified as gravel Producer defined gravel_shell Classified as mixture of gravel and shells Producer defined cobble_gravel Classified as gravel with cobbles Producer defined bedrock Classified as exposed bedrock Producer defined ice_snow Classified as ice or snow Producer defined bare_ground Classified as bare ground Producer defined sediment Classified as bare sediment Producer defined other_natural_terrain Classified as other natural terrain Producer defined other_bare_natural_terrain Classified as other bare natural terrain Producer defined vegetated Classified as vegetation Producer defined vegetated_ground Classified as ground with vegetation Producer defined vegetated_surface Classified as vegetation Producer defined marsh_vegetation Classified as marsh vegetation Producer defined terrestrial_vegetation Classified as terrestrial vegetation Producer defined agricultural Classified as agricultural Producer defined cloud Classified as cloud Producer defined development Classified as consisting of human development Producer defined dev Classified as consisting of human development Producer defined coastal_defense Classified as coastal defense Producer defined buildings Classified as building Producer defined pavement_road Classified as pavement Producer defined vehicles Classified as vehicles Producer defined people Classified as person Producer defined other_anthro Classified as other anthropogenic object Producer defined unusual Classified as unusal object or land cover Producer defined unknown Classified as unknown land cover Producer defined no_data No data contained in pixels Producer defined nodata No data contained in pixels Producer defined num_classes Number of classification classes in the image. Producer defined 1 12 classes_integer One integer per class in num_classes. Producer defined 0 12 classes_present_integer An array of integer classes present in the image. Producer defined 0 12 classes_present_array An array of classes present in the image. Producer defined Values present in image from classes pen_width Final width in pixels of pen used to annotate in the Doodler program. Producer defined 1 10 CRF_theta Internal classifier hyperparameter used by the Doodler program. Producer defined 1 1 CRF_mu Internal classifier hyperparameter used by the Doodler program. Producer defined 1 99 CRF_downsample_factor Internal classifier hyperparameter used by the Doodler program. Producer defined 1 5 Classifier_downsample_factor Internal classifier hyperparameter used by the Doodler program. Producer defined 1 8 prob_of_unary_potential Internal classifier hyperparameter used by the Doodler program. Producer defined 0.1 3.0 doodle_spatial_density Proportion of the image annotated. Producer defined 0.000526323 0.999627422 num_of_scales Internal classifier hyperparameter used by the Doodler program. Producer defined 3 3 acc_georef Accuracy, in meters, of the specification of 'XMin', 'XMax' and 'YMin', 'YMax'. Producer defined 1 11.248 epsg EPSG code for the projected coordinate system. See 'CRS' attribute for a complete description of codes used. Producer defined 26910 32618 year Acquisition year of the image source. Producer defined 2008 2021 month Acquisition month of the image source. Producer defined 1 12 day Acquisition day of the image source. Producer defined 1 31 hour Acquisition hour of the image source. Producer defined 0 23 minute Acquisition minute of the image source. Producer defined 0 59 second Acquisition second of the image source. Producer defined 0 59 XMin Minimum easting of the image footprint. Producer defined 233870.0 787860.0 XMax Maximum easting of the image footprint. Producer defined 235750.0 790530.0 YMin Minimum northing of the image footprint. Producer defined 2875253.0 5332914.0 YMax Maximum northing of the image footprint. Producer defined 2884030.0 5333378.0 LonMin Minimum longitude (WGS84) of image footprint. Producer defined -124.0922272 -69.95201111 LonMax Maximum longitude (WGS84) of image footprint. Producer defined -124.0478924 -69.9405098 LatMin Minimum longitude (WGS84) of image footprint. Producer defined 25.98761753 48.14810677 LatMax Maximum latitude (WGS84) of image footprint. Producer defined 26.06287667 48.15232107 CRS The projected coordinate system description relating to XMin, XMax, YMin, YMax. Producer defined Projected coordinate system definition px_m Horizontal size of pixel in meters. Producer defined 0.15 15 ImageHeightPx Number of pixels in horizontal dimension of height. Producer defined 31 2481 ImageWidthPx Number of pixels in horizontal dimension of width. Producer defined 32 2209 ImageBands Number of bands in the image. Producer defined 3 3 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). 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. U.S. Geological Survey - CMGDS mailing and physical

2885 Mission Street

Santa Cruz CA 95060 831-427-4747 pcmsc_data@usgs.gov 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. 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. comma-delimited text none https://doi.org/10.5066/P91NP87I CSV files can be downloaded using the Network_Resource_Name link then scrolling down to the Land Cover Data section. NPY 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. https://doi.org/10.5066/P91NP87I Imagery data can be downloaded using the Network_Resource_Name link then scrolling down to the Land Cover Data section. None. These data can be viewed with Doodler software (Buscombe, 2022; https://doi.org/10.5066/P9YVHL23). 20220504 U.S. Geological Survey, Pacific Coastal and Marine Science Center PCMSC Science Data Coordinator mailing and physical

2885 Mission Street

Santa Cruz CA 95060 831-427-4747 pcmsc_data@usgs.gov Content Standard for Digital Geospatial Metadata FGDC-STD-001-1998