From CSIRO DAP
JSON format icon JSON RDF format icon RDF ISO19115-3 XML

Deep Learning Image Segmentation of Sandy Beaches in Southeastern Australia

Created 20/09/2025

Updated 20/09/2025

JSON format icon JSON RDF format icon RDF ISO19115-3 XML

The collection includes beach coastlines from Southeastern Australia, specifically Victoria and New South Wales, used to train an image segmentation model using the U-Net deep learning architecture for mapping sandy beaches. The dataset contains polygons that represent the outline or extent of the raster images and polygons drawn by citizen-scientists. Additionally, we provide the trained model itself, which can be utilized for further evaluation or refined through fine-tuning. The resulting predictions are also available in Shapefiles format, which can be loaded to NationalMap. This collection supplements the publication: Regional-Scale Image Segmentation of Sandy Beaches: Comparison of Training and Prediction Across Two Extensive Coastlines in Southeastern Australia (Yong et al. 2025)

Files and APIs

Additional Info

Field Value
Title Deep Learning Image Segmentation of Sandy Beaches in Southeastern Australia
Language English
Licence Not Specified
Landing Page https://data.gov.au/data/dataset/219a0517-bfc7-5ca1-91c8-d41dcdaab992
Contact Point
CSIRO Data Access Portal
CSIROEnquiries@csiro.au
Reference Period 01/01/2000
Geospatial Coverage Australia
Data Portal CSIRO DAP

Data Source

This dataset was originally found on CSIRO DAP "Deep Learning Image Segmentation of Sandy Beaches in Southeastern Australia". Please visit the source to access the original metadata of the dataset:
https://data.csiro.au/collection/csiro:62849