the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Mapping the world's coast: a global 100-m coastal typology derived from satellite data using deep learning
Abstract. We present a globally consistent, high-resolution (100 m) coastal typology dataset derived from satellite imagery and elevation data using deep learning—the first application of its kind in coastal science. Using a supervised multi-task convolutional neural network, we classified nearly 10 million coastal transects (one million km of coast) into four coastal attributes along the cross-shore profile: (1) sediment type, (2) coastal type, (3) presence or absence of built environment, and (4) presence or absence of human-made coastal defenses. The model, trained on about 1800 globally distributed samples, achieves strong predictive performance with F1 scores ranging from 0.67 to 0.83. Results show that the global coastal sediment distribution consists of approximately 40 % sandy, gravel, or shingle; 21 % muddy; 13 % rocky; and 27 % with no sediment. Considering the coastal type, 33 % of coasts are cliffed, 22 % are sediment plains, 15 % are wetlands, and 3 % are dune systems (i.e. 26,000 km). Combining sandy, gravel, shingle, and muddy sediments, we estimate that 61 % of the global coastline consists of soft sediments that are potentially easily erodible. Among sandy, gravel, or shingle coasts specifically, 20 % are cliff-backed and 16.5 % are located on built-up coasts. This global dataset, available in a cloud-optimized format at https://doi.org/10.5281/zenodo.15599096, provides a robust foundation for coastal change analysis and erosion assessment, and enables new opportunities for broad-scale vulnerability mapping and adaptation planning in the face of accelerating sea-level rise.
- Preprint
(14851 KB) - Metadata XML
- BibTeX
- EndNote
Status: open (until 04 Oct 2025)
-
CC1: 'Comment on essd-2025-388', adam young, 05 Sep 2025
reply
Lines 339-342 . The statement that Young and Carilli (2019) did not estimate a proportional global length of cliff is not correct. As noted in the paper, Young and Carilli (2019) found that 93% of the world’s coastal political regions (213 geographic units) containing some cliffed segments. However, Young and Carilli (2019) also used the near-global Shuttle Radar Topography Mission 3 arc second digital elevation model, the Arctic Coastal Dynamics Database, and estimates of cliff percentages for Greenland and Antarctica from the literature to estimate whether or not 89% of the world vector shoreline was cliffed. The results suggest coastal cliffs likely exist on about 52% of the global shoreline.
Citation: https://doi.org/10.5194/essd-2025-388-CC1
Data sets
Mapping the world's coast: a global 100 m coastal typology derived from satellite data using deep learning Floris R. Calkoen, Arjen P. Luijendijk, Susan Hanson, Robert J. Nicholls, Antonio Moreno-Rodenas, Hugo de Heer, Fedor Baart https://doi.org/10.5281/zenodo.15599096
CoastBench: A global training dataset for coastal classification using satellite imagery and elevation data Floris R. Calkoen, Arjen P. Luijendijk, Susan Hanson, Robert J. Nicholls, Antonio Moreno-Rodenas, Hugo de Heer, Fedor Baart https://doi.org/10.5281/zenodo.15800284
Model code and software
Enabling coastal analytics at Planetary Scale: CoastPy Floris Calkoen https://github.com/tuDelft-CITG/coastpy
Interactive computing environment
Enabling coastal analytics at planetary scale: tutorial notebooks Floris Calkoen https://github.com/TUDelft-CITG/coastpy/tree/main/tutorials
Viewed
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
554 | 168 | 17 | 739 | 18 | 19 |
- HTML: 554
- PDF: 168
- XML: 17
- Total: 739
- BibTeX: 18
- EndNote: 19
Viewed (geographical distribution)
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1