This data release serves as an archive of coastal land-cover and feature datasets derived from Landsat satellite imagery from Delaware Bay, New Jersey (NJ) to Shinnecock Bay, New York (NY). A total of 119 images acquired between 2008 and 2022 were analyzed to produce 143 thematic land-cover raster datasets. Water, bare earth (sand), and vegetated land-cover classes were mapped using successive thresholding and masking of the modified normalized difference water index (mNDWI), the normalized difference bare ...

The data release (Bernier, 2021) associated with this metadata record serves as an archive of coastal land-cover and feature datasets derived from Landsat satellite imagery at the northern Chandeleur Islands, Louisiana. To minimize the effects of tidal water-level variations, 75 cloud-free, low-water images acquired between 1984 and 2019 were analyzed. Water, bare earth (sand), vegetated, and intertidal land-cover classes were mapped from Hewes Point to Palos Island using successive thresholding and masking ...

This data release serves as an archive of coastal land-cover and feature datasets derived from Landsat satellite imagery from Delaware Bay, New Jersey (NJ) to Shinnecock Bay, New York (NY). A total of 119 images acquired between 2008 and 2022 were analyzed to produce 143 thematic land-cover raster datasets. Water, bare earth (sand), and vegetated land-cover classes were mapped using successive thresholding and masking of the modified normalized difference water index (mNDWI), the normalized difference bare ...

The data release (Bernier, 2021) associated with this metadata record serves as an archive of coastal land-cover and feature datasets derived from Landsat satellite imagery at the northern Chandeleur Islands, Louisiana. To minimize the effects of tidal water-level variations, 75 cloud-free, low-water images acquired between 1984 and 2019 were analyzed. Water, bare earth (sand), vegetated, and intertidal land-cover classes were mapped from Hewes Point to Palos Island using successive thresholding and masking ...

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, ...