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
  • Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches
Title: Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches
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
Award ID(s):
1927373
PAR ID:
10326050
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Remote Sensing
Volume:
13
Issue:
22
ISSN:
2072-4292
Page Range / eLocation ID:
4572
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, International Conference on Machine Learning and Applications (ICMLA))
    This paper explores the problem of deploying machine learning (ML)-based object detection and segmentation models on edge platforms to enable realtime caveline detection for Autonomous Underwater Vehicles (AUVs) used for under-water cave exploration and mapping. We specifically investigate three ML models, i.e., U-Net, Vision Transformer (ViT), and YOLOv8, deployed on three edge platforms: Raspberry Pi-4, Intel Neural Compute Stick 2 (NCS2), and NVIDIA Jetson Nano. The experimental results unveil clear tradeoffs between model accuracy, processing speed, and energy consumption. The most accurate model has shown to be U-Net with an 85.53 F1-score and 85.38 Intersection Over Union (IoU) value. Meanwhile, the highest inference speed and lowest energy consumption are achieved by the YOLOv8 model deployed on Jetson Nano operating in the high-power and low-power modes, respectively. The comprehensive quantitative analyses and comparative results provided in the paper highlight important nuances that can guide the deployment of caveline detection systems on underwater robots for ensuring safe and reliable AUV navigation during underwater cave exploration and mapping missions. 
    more » « less
  2. ; ; ; ; ; (, IEEE)
    This paper addresses the challenge of deploying machine learning (ML)-based segmentation models on edge platforms to facilitate real-time scene segmentation for Autonomous Underwater Vehicles (AUVs) in underwater cave exploration and mapping scenarios. We focus on three ML models-U-Net, CaveSeg, and YOLOv8n-deployed on four edge platforms: Raspberry Pi-4, Intel Neural Compute Stick 2 (NCS2), Google Edge TPU, and NVIDIA Jetson Nano. Experimental results reveal that mobile models with modern architectures, such as YOLOv8n, and specialized models for semantic segmentation, like U-Net, offer higher accuracy with lower latency. YOLOv8n emerged as the most accurate model, achieving a 72.5 Intersection Over Union (IoU) score. Meanwhile, the U-Net model deployed on the Coral Dev board delivered the highest speed at 79.24 FPS and the lowest energy consumption at 6.23 mJ. The detailed quantitative analyses and comparative results presented in this paper offer critical insights for deploying cave segmentation systems on underwater robots, ensuring safe and reliable AUV navigation during cave exploration and mapping missions. 
    more » « less
  3. ; ; ; ; ; (, IEEE)
    This paper addresses the challenge of deploying machine learning (ML)-based segmentation models on edge platforms to facilitate real-time scene segmentation for Autonomous Underwater Vehicles (AUVs) in underwater cave exploration and mapping scenarios. We focus on three ML models-U-Net, CaveSeg, and YOLOv8n-deployed on four edge platforms: Raspberry Pi-4, Intel Neural Compute Stick 2 (NCS2), Google Edge TPU, and NVIDIA Jetson Nano. Experimental results reveal that mobile models with modern architectures, such as YOLOv8n, and specialized models for semantic segmentation, like U-Net, offer higher accuracy with lower latency. YOLOv8n emerged as the most accurate model, achieving a 72.5 Intersection Over Union (IoU) score. Meanwhile, the U-Net model deployed on the Coral Dev board delivered the highest speed at 79.24 FPS and the lowest energy consumption at 6.23 mJ. The detailed quantitative analyses and comparative results presented in this paper offer critical insights for deploying cave segmentation systems on underwater robots, ensuring safe and reliable AUV navigation during cave exploration and mapping missions. 
    more » « less
  4. ; ; ; ; ; ; ; ; (, Arctic Science)
    Increased industrial development in the Arctic has led to a rapid expansion of infrastructure in the region. Localized impacts of infrastructure on snow distribution, road dust, and snowmelt timing and duration feeds back into the coupled Arctic system causing a series of cascading effects that remain poorly understood. We quantify spatial and temporal patterns of snow-off dates in the Prudhoe Bay Oilfield, Alaska, using Sentinel-2 data. We derive the Normalized Difference Snow Index to quantify snow persistence in 2019–2020. The Normalized Difference Vegetation Index and Normalized Difference Water Index were used to show linkages of vegetation and surface hydrology, in relationship to patterns of snowmelt. Newly available infrastructure data were used to analyze snowmelt patterns in relation infrastructure. Results show a relationship between snowmelt and distance to infrastructure varying by use and traffic load, and orientation relative to the prevailing wind direction (up to 1 month difference in snow-free dates). Post-snowmelt surface water area showed a strong negative correlation (up to −0.927) with distance to infrastructure. Results from field observations indicate an impact of infrastructure on winter near-surface ground temperature and snow depth. This study highlights the impact of infrastructure on a large area beyond the direct human footprint and the interconnectedness between snow-off timing, vegetation, surface hydrology, and near-surface ground temperatures. 
    more » « less
  5. ; (, Remote Sensing)
    The Total Operating Characteristic (TOC) measures how the ranks of an index variable distinguish between presence and absence in a binary reference variable. Previous methods to generate the TOC required the reference data to derive from a census or a simple random sample. However, many researchers apply stratified random sampling to collect reference data because stratified random sampling is more efficient than simple random sampling for many applications. Our manuscript derives a new methodology that uses stratified random sampling to generate the TOC. An application to flood mapping illustrates how the TOC compares the abilities of three indices to diagnose water. The TOC shows visually and quantitatively each index’s diagnostic ability relative to baselines. Results show that the Modified Normalized Difference Water Index has the greatest diagnostic ability, while the Normalized Difference Vegetation Index has diagnostic ability greater than the Normalized Difference Water Index at the threshold where the Diagnosed Presence equals the Abundance of water. Some researchers consider only one accuracy metric at only one threshold, whereas the TOC allows visualization of several metrics at all thresholds. The TOC gives more information and clearer interpretation compared to the popular Relative Operating Characteristic. Our software generates the TOC from a census, simple random sample, or stratified random sample. The TOC Curve Generator is free as an executable file at a website that our manuscript gives. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email