A Deep‐Learning Model Cascade for Automating Large‐Scale Shoreline Mapping From Satellite Imagery
- 1U.S. Geological Survey Pacific Coastal and Marine Science Center Santa Cruz CA USA
- 2Now at Applied Coastal Research and Engineering Section Washington State Department of Ecology Olympia WA USA
- 3Now at School of Marine and Atmospheric Sciences Stony Brook University Stony Brook NY USA
Abstract
This study describes a machine learning model cascade for automating large‐scale shoreline mapping from time‐series of coastal satellite imagery. Our model cascade consists of independent supervised deep learning models for image suitability, image segmentation, and image segmentation suitability. The segmentation model determines shoreline locations, while the other models in this cascade filter imagery not suitable for segmentation or segmentations not suitable for shoreline detection. The SegFormer‐based segmentation model is trained with almost 2,300 labeled satellite images from a large variety of globally distributed coastal environments. The image segmentation model operates on imagery that has been deemed suitable by an image classification model that classifies whole satellite images as either suitable or unsuitable for segmentation. Another supervised whole image classification model is used to determine the suitability of each segmentation output. Finally, a spatial kernel density filters removes outlier shoreline points, with further timeseries analysis techniques to remove any remaining outliers. This study demonstrates the effectiveness of this system at two sites that are challenging to map: one at a sandy spit near Moses Point Fishing Village, Alaska, USA, and one at the mouth of the Elwha River, Washington, USA. This study demonstrates that these automated techniques produce shorelines with similar or better accuracies when compared to semi‐automated techniques. Ensembling model outputs better constrains the error and uncertainty of shoreline positions. Together, the set of models presented in this paper constitute an operational workflow for the generation and quality control of large‐scale records of satellite‐derived shoreline change.
Related
- Multidecadal satellite-derived sandy shoreline change along the Mediterranean coast of Morocco
- Shoreline kinematics in Libreville (Gabon) derived from very high spatial resolution (VHR) imagery using machine and deep learning techniques
- Mapping soil particle fractions by training digital soil mapping models with surrogate measurements obtained from laboratory and satellite Vis-NIR spectral data
- From plot to region: canopy height-mediated mangrove aboveground biomass mapping by synergizing UAV-LiDAR and multi-source satellite data
- Butterfly Effect and the Kinetic Energy Cascade in Probabilistic Machine Learning Weather Prediction Models
BibTeX
@article{lundine2026deeplearning,
title = {{A Deep‐Learning Model Cascade for Automating Large‐Scale Shoreline Mapping From Satellite Imagery}},
author = {Mark A. Lundine and Daniel D. Buscombe and Sharon F. Batiste and Catherine N. Janda and Jonathan Warrick},
journal = {Earth and Space Science},
year = {2026},
month = nov,
doi = {10.1029/2025ea004410},
url = {https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2025EA004410},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A Deep‐Learning Model Cascade for Automating Large‐Scale Shoreline Mapping From Satellite Imagery
AU - Mark A. Lundine
AU - Daniel D. Buscombe
AU - Sharon F. Batiste
AU - Catherine N. Janda
AU - Jonathan Warrick
PY - 2026
DA - 2026/11/01
JO - Earth and Space Science
DO - 10.1029/2025ea004410
UR - https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2025EA004410
AB - This study describes a machine learning model cascade for automating large‐scale shoreline mapping from time‐series of coastal satellite imagery. Our model cascade consists of independent supervised deep learning models for image suitability, image segmentation, and image segmentation suitability. The segmentation model determines shoreline locations, while the other models in this cascade filter imagery not suitable for segmentation or segmentations not suitable for shoreline detection. The SegFormer‐based segmentation model is trained with almost 2,300 labeled satellite images from a large variety of globally distributed coastal environments. The image segmentation model operates on imagery that has been deemed suitable by an image classification model that classifies whole satellite images as either suitable or unsuitable for segmentation. Another supervised whole image classification model is used to determine the suitability of each segmentation output. Finally, a spatial kernel density filters removes outlier shoreline points, with further timeseries analysis techniques to remove any remaining outliers. This study demonstrates the effectiveness of this system at two sites that are challenging to map: one at a sandy spit near Moses Point Fishing Village, Alaska, USA, and one at the mouth of the Elwha River, Washington, USA. This study demonstrates that these automated techniques produce shorelines with similar or better accuracies when compared to semi‐automated techniques. Ensembling model outputs better constrains the error and uncertainty of shoreline positions. Together, the set of models presented in this paper constitute an operational workflow for the generation and quality control of large‐scale records of satellite‐derived shoreline change.
SN - 2333-5084
SN - 2333-5084
ER -