An official website of the United States government
Precise coastal shoreline mapping is essential for monitoring changes in erosion rates, surface hydrology, and ecosystem structure and function. Monitoring water bodies in the Arctic National Wildlife Refuge (ANWR) is of high importance, especially considering the potential for oil and natural gas exploration in the region. In this work, we propose a modified variant of the Deep Neural Network based U-Net Architecture for the automated mapping of 4 Band Orthorectified NOAA Airborne Imagery using sparsely labeled training data and compare it to the performance of traditional Machine Learning (ML) based approaches—namely, random forest, xgboost—and spectral water indices—Normalized Difference Water Index (NDWI), and Normalized Difference Surface Water Index (NDSWI)—to support shoreline mapping of Arctic coastlines. We conclude that it is possible to modify the U-Net model to accept sparse labels as input and the results are comparable to other ML methods (an Intersection-over-Union (IoU) of 94.86% using U-Net vs. an IoU of 95.05% using the best performing method).
more »
« less
This content will become publicly available on January 21, 2027
Segmentation of arctic coastal shoreline and bluff edges using optical satellite imagery and deep learning
The Arctic coastline spans multiple countries, supports Indigenous livelihoods, and plays a vital role in the Arctic system. Rapid climate change is accelerating permafrost thaw, sea-level rise, and coastal erosion, underscoring the need for decision making to be informed by accurate delineation of tundra shoreline (instantaneous water line) and bluff edge (vegetation–slope boundary) position and change trends. To address this need, we compared two image segmentation approaches for mapping Arctic land and water interfaces from high-resolution satellite imagery. (1) U-Net, a supervised convolutional neural network trained on expert-annotated scenes, and (2) Differentiable Feature Clustering (DifFeat), an unsupervised model applied in a minimally supervised manner via expert-guided cluster selection. The shoreline and bluff edge boundaries were derived from the segmented land and water masks using an automated interface extraction approach. DifFeat achieved higher segmentation accuracy, with IoU values of 0.95 (water) and 0.92 (land), compared to U-Net’s 0.58 and 0.50, respectively. U-Net produced reliable results and benefited from infrared and vegetation spectral indices, but required extensive annotation and showed limited generalization to UAV imagery. DifFeat achieved superior results without manual annotation, reducing the dependence on labeled data and completing training 99.87% faster than U-Net. These findings highlight the complementary strengths of supervised and semi-supervised models for Arctic coastal mapping, with DifFeat offering a scalable, label-efficient solution for long-term coastal-change monitoring. Future work will integrate elevation data to further improve bluff edge feature detection.
more »
« less
- PAR ID:
- 10689167
- Publisher / Repository:
- Frontiers in Environmental Science
- Date Published:
- Journal Name:
- Frontiers in Environmental Science
- Volume:
- 13
- ISSN:
- 2296-665X
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Tidal creeks play a vital role in influencing geospatial evolution and marsh ecological communities in coastal landscapes. However, evaluating the geospatial characteristics of numerous creeks across a site and understanding their ecological relationships pose significant challenges due to the labor-intensive nature of manual delineation from imagery. Traditional methods rely on manual annotation in GIS interfaces, which is slow and tedious. This study explores the application of Attention-based Dense U-Net (ADU-Net), a deep learning image segmentation model, for automatically classifying creek pixels in high-resolution (0.5 m) orthorectified aerial imagery in coastal Georgia, USA. We observed that ADU-Net achieved an outstanding F1 score of 0.98 in identifying creek pixels, demonstrating its ability in tidal creek mapping. The study highlights the potential of deep learning models for automated tidal creek mapping, opening avenues for future investigations into the role of creeks in marshes’ response to environmental changes.more » « less
-
Rapid global warming is catalyzing widespread permafrost degradation in the Arctic, leading to destructive land-surface subsidence that destabilizes and deforms the ground. Consequently, human-built infrastructure constructed upon permafrost is currently at major risk of structural failure. Risk assessment frameworks that attempt to study this issue assume that precise information on the location and extent of infrastructure is known. However, complete, high-quality, uniform geospatial datasets of built infrastructure that are readily available for such scientific studies are lacking. While imagery-enabled mapping can fill this knowledge gap, the small size of individual structures and vast geographical extent of the Arctic necessitate large volumes of very high spatial resolution remote sensing imagery. Transforming this ‘big’ imagery data into ‘science-ready’ information demands highly automated image analysis pipelines driven by advanced computer vision algorithms. Despite this, previous fine resolution studies have been limited to manual digitization of features on locally confined scales. Therefore, this exploratory study serves as the first investigation into fully automated analysis of sub-meter spatial resolution satellite imagery for automated detection of Arctic built infrastructure. We tasked the U-Net, a deep learning-based semantic segmentation model, with classifying different infrastructure types (residential, commercial, public, and industrial buildings, as well as roads) from commercial satellite imagery of Utqiagvik and Prudhoe Bay, Alaska. We also conducted a systematic experiment to understand how image augmentation can impact model performance when labeled training data is limited. When optimal augmentation methods were applied, the U-Net achieved an average F1 score of 0.83. Overall, our experimental findings show that the U-Net-based workflow is a promising method for automated Arctic built infrastructure detection that, combined with existing optimized workflows, such as MAPLE, could be expanded to map a multitude of infrastructure types spanning the pan-Arctic.more » « less
-
Coastal wetlands, especially tidal marshes, play a crucial role in supporting ecosystems and slowing shoreline erosion. Accurate and cost-effective identification and classification of various marshtypes, such as high and low marshes, are important for effective coastal management and conservation endeavors. However, mapping tidal marshes is challenging due to heterogeneous coastal vegetation and dynamic tidal influences. In this study, we employ a deep learning segmentation model to automate the identification and classification of tidal marsh communities in coastal Virginia, USA, using seasonal, publicly available satellite and aerial images. This study leverages the combined capabilities of Sentinel-2 and National Agriculture Imagery Program (NAIP)imagery and a UNet architecture to accurately classify tidal marsh communities. We illustrate that by leveraging features learned from data abundant regions and small quantities of high-quality training data collected from the target region, an accuracy as high as 88% can be achieved in the classification of marsh types, specifically high marsh and low marsh, at a spatial resolution of 0.6 m.This study contributes to the field of marsh mapping by highlighting the potential of combining multispectral satellite imagery and deep learning for accurate and efficient marsh type classificationmore » « less
-
null (Ed.)Observational data of coastal change over much of the Arctic are limited largely due to its immensity, remoteness, harsh environment, and restricted periods of sunlight and ice-free conditions. Barter Island, Alaska, is one of the few locations where an extensive, observational dataset exists, which enables a detailed assessment of the trends and patterns of coastal change over decadal to annual time scales. Coastal bluff and shoreline positions were delineated from maps, aerial photographs, and satellite imagery acquired between 1947 and 2020, and at a nearly annual rate since 2004. Rates and patterns of shoreline and bluff change varied widely over the observational period. Shorelines showed a consistent trend of southerly erosion and westerly extension of the western termini of Barter Island and Bernard Spit, which has accelerated since at least 2000. The 3.2 km long stretch of ocean-exposed coastal permafrost bluffs retreated on average 114 m and at a maximum of 163 m at an average long-term rate (70 year) of 1.6 ± 0.1 m/yr. The long-term retreat rate was punctuated by individual years with retreat rates up to four times higher (6.6 ± 1.9 m/yr; 2012–2013) and both long-term (multidecadal) and short-term (annual to semiannual) rates showed a steady increase in retreat rates through time, with consistently high rates since 2015. A best-fit polynomial trend indicated acceleration in retreat rates that was independent of the large spatial and temporal variations observed on an annual basis. Rates and patterns of bluff retreat were correlated to incident wave energy and air and water temperatures. Wave energy was found to be the dominant driver of bluff retreat, followed by sea surface temperatures and warming air temperatures that are considered proxies for evaluating thermo-erosion and denudation. Normalized anomalies of cumulative wave energy, duration of open water, and air and sea temperature showed at least three distinct phases since 1979: a negative phase prior to 1987, a mixed phase between 1987 and the early to late 2000s, followed by a positive phase extending to 2020. The duration of the open-water season has tripled since 1979, increasing from approximately 40 to 140 days. Acceleration in retreat rates at Barter Island may be related to increases in both thermodenudation, associated with increasing air temperature, and the number of niche-forming and block-collapsing episodes associated with higher air and water temperature, more frequent storms, and longer ice-free conditions in the Beaufort Sea.more » « less
