skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • A Deep Learning Based Method to Delineate the Wet/Dry Shoreline and Compute Its Elevation Using High-Resolution UAS Imagery
Title: A Deep Learning Based Method to Delineate the Wet/Dry Shoreline and Compute Its Elevation Using High-Resolution UAS Imagery
Automatically detecting the wet/dry shoreline from remote sensing imagery has many benefits for beach management in coastal areas by enabling managers to take measures to protect wildlife during high water events. This paper proposes the use of a modified HED (Holistically-Nested Edge Detection) architecture to create a model for automatic feature identification of the wet/dry shoreline and to compute its elevation from the associated DSM (Digital Surface Model). The model is generalizable to several beaches in Texas and Florida. The data from the multiple beaches was collected using UAS (Uncrewed Aircraft Systems). UAS allow for the collection of high-resolution imagery and the creation of the DSMs that are essential for computing the elevations of the wet/dry shorelines. Another advantage of using UAS is the flexibility to choose locations and metocean conditions, allowing to collect a varied dataset necessary to calibrate a general model. To evaluate the performance and the generalization of the AI model, we trained the model on data from eight flights over four locations, tested it on the data from a ninth flight, and repeated it for all possible combinations. The AP and F1-Scores obtained show the success of the model’s prediction for the majority of cases, but the limitations of a pure computer vision assessment are discussed in the context of this coastal application. The method was also assessed more directly, where the average elevations of the labeled and AI predicted wet/dry shorelines were compared. The absolute differences between the two elevations were, on average, 2.1 cm, while the absolute difference of the elevations’ standard deviations for each wet/dry shoreline was 2.2 cm. The proposed method results in a generalizable model able to delineate the wet/dry shoreline in beach imagery for multiple flights at several locations in Texas and Florida and for a range of metocean conditions.  more » « less
Award ID(s):
2019758
PAR ID:
10422687
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Remote Sensing
Volume:
14
Issue:
23
ISSN:
2072-4292
Page Range / eLocation ID:
5990
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, Geophysical Research Letters)
    Abstract Beach erosion due to large storms critically affects coastal vulnerability, but is challenging to monitor and quantify. Attributing erosion to a specific storm requires a reliable counterfactual scenario: hypothetical beach conditions, absent the storm. Calibrating models to construct counterfactuals requires numerous observations that are rarely available. Storm paths are unpredictable, making long‐term instrumentation of specific beaches costly. Optical remote sensing is hampered by persistent cloud cover. We use Sentinel‐1 satellite radar imagery to monitor shoreline changes through clouds and propose regression discontinuity as a strategy to estimate the causal effect of large storms on beach erosion. Applied to 75 beaches across Puerto Rico, the approach detects shoreline changes with a root‐mean‐square error comparable to the resolution of the imagery. Hurricane Maria caused an erosion of 3 to 5 m along its path, up to 40 m at particular beaches. Results reveal strong local disparities that are consistent with simulated nearshore hydrodynamic conditions. 
    more » « less
  2. ; ; ; ; ; (, Designsafe-CI)
    This project contains imagery collected from uncrewed aircraft system (UAS) flights over three barrier islands, Fort Myers Beach (FMB), San Carlos (SC), and Sanibel Island (SI), that are near Fort Myers, Florida, following Hurricane Ian. These barrier islands had substantial impacts from the hurricane, including the destruction of many residences and infrastructure, coastal degradation, and other environmental impacts. The imagery here was collected using a low-flying fixed-wing UAS with a high-resolution camera system that simultaneously collected oblique and nadir images from five lenses. The raw data set is very comprehensive and very dense. The extent of the collected data can be seen in the Hazmapper map. The data was processed into 3D models using structure from motion. The resulting 3D models have amazing damage detail and are measurement quality. They can be used to fully characterize damage to buildings, infrastructure, and the natural environment. The complete models are available here, with one model developed for each UAS flight (18 total flights). However, the complete models are very large data sets and require significant GPU power to open and manipulate. Thus, the data set is also divided into “tiled” areas on a 300-meter grid. Each tiled area is provided in both a full-resolution 3D model and a reduced-resolution preview that can be used for quick inspection. The tiles are named and distributed as shown here: https://arcg.is/19TLr5. The abbreviations for Fort Myers Beach (FMB), San Carlos (SC), and Sanibel Island (SI) are used throughout. The data set was collected and processed by the NHERI RAPID Facility and was part of the deployment by the Structural Engineering Extreme Events Reconnaissance Network (StEER). 
    more » « less
  3. ; ; ; (, Proceedings of the 11th International Symposium on Coastal Engineering and Science of Coastal Sediment Processes)
    Beaches and inlets throughout the U.S. have been stabilized for purposes of navigation, erosion mitigation, and economic resilience, commonly leading to changes in shoreline dynamics and downdrift erosion/accretion patterns. The developed beach of Plum Island, Massachusetts is highly dynamic, experiencing regular complex erosion / accretion patterns along much of the shoreline. We analyzed > 100 years of high-water line positions derived from satellite imagery, t-sheets, historical maps, and aerial photography. Unlike most beaches, the river-proximal sections of Plum Island are not uniformly retreating. Rather, the beach undergoes short-term erosion, followed by periods of accretion and return to a long-term mean stable shoreline position. These cycles occur over different time frames and in different segments of the beach, creating an ephemeral erosion ‘hotspot’ lasting as briefly as one year. The highly dynamic and spatially diverse nature of erosion along Plum Island provides insight into the complex nature of coupled inlet-beach dynamics over multiple timescales. 
    more » « less
  4. ; (, The Proceedings of the Coastal Sediments 2023)
    Wang, Ping; Royer, Elizabeth; Rosati, Julie D. (Ed.)
    Three cycles of beach nourishment at two barrier islands: Sand Key and Treasure Island, were studied over 17 years. Seventy-four and 17 beach profiles spaced ∼300 m apart were surveyed bimonthly to quarterly on Sand Key and Treasure Island, respectively. Six beach sections were distinguished based on beach dynamics, including 2 erosional hotspots, 1 gap in the nourishment and 3 typical erosive beaches. At most locations, the shoreline (defined at +1 m contour) returned to a similar location at the end of each cycle, indicating the nourishment successfully maintained the target beach width. The Treasure Island erosion hotspot experienced increased beach loss over time, suggesting that the current nourishment design may not be adequate. The gap in the nourishment did not experience significant sand gain on the dry beach. A mechanism to impound sand on the dry beach is necessary. The current nourishment successfully compensated the sand deficit. The mechanism causing sand deficit was not eliminated at all the sites, suggesting that the current nourishment design serves as a long-term maintenance strategy. 
    more » « less
  5. ; ; (, WORLD SCIENTIFIC)
    In this study progradation of the dune toe on the sandy, dune-backed beaches of Makah Bay, on the Pacific Ocean shorelines of the reservation lands of the Makah Tribe, were documented for the first time. A shoreline assessment was implemented that included repeat beach profile surveys using RTK-DGPS and aerial lidar, and historical change analysis using aerial photos. Analysis of GNSS and aerial lidar suggest patterns of dune toe progradation over the last decade at average rates of ~0.8 m/yr between 2010 and 2022 over almost all the 5.5 km length of beach in Makah Bay, excepting the ~250m long erosional area that prompted the study. A beach vegetation line delineated in aerial photos collected between 1952 and 2019 moved seaward at average rates of ~0.7 m/yr across the entire length of Makah Bay, suggesting that the pattern of progradation is long-lived. We assess evidence to evaluate whether this pattern of dune progradation can be explained by sediment supplies from watersheds draining to Makah Bay and conclude that local sediment supply cannot explain observed patterns. A variety of shoreline processes associated with relative sea-level fall are discussed and may explain the observed rates of shoreline progradation. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email