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.


Title: Towards Generalizable Deep Learning Models for Radar Echogram Layer Tracking
{"Abstract":["The accelerated melting of ice sheets in Greenland and Antarctica, driven by climate warming, is significantly contributing to global sea level rise. To better understand this phenomenon, airborne radars have been deployed to create echogram images that map snow accumulation patterns in these regions. Utilizing advanced radar systems developed by the Center for Remote Sensing and Integrated Systems (CReSIS), around 1.5 petabytes of climate data have been collected. However, extracting ice-related information, such as accumulation rates, remains limited due to the largely manual and time-consuming process of tracking internal layers in radar echograms. This highlights the need for automated solutions.\n\nMachine learning and deep learning algorithms are well-suited for this task, given their near human performance on optical images. The overlap between classical radar signal processing and machine learning techniques suggests that combining concepts from both fields could lead to optimized soluti  more » « less
Award ID(s):
1838236 2126503
PAR ID:
10656766
Author(s) / Creator(s):
Publisher / Repository:
Zenodo
Date Published:
Subject(s) / Keyword(s):
Machine Learning Snow Radar
Format(s):
Medium: X
Institution:
University of Kansas
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, Remote Sensing)
    null (Ed.)
    Climate change is extensively affecting ice sheets resulting in accelerating mass loss in recent decades. Assessment of this reduction and its causes is required to project future ice mass loss. Annual snow accumulation is an important component of the surface mass balance of ice sheets. While in situ snow accumulation measurements are temporally and spatially limited due to their high cost, airborne radar sounders can achieve ice sheet wide coverage by capturing and tracking annual snow layers in the radar images or echograms. In this paper, we use deep learning to uniquely identify the position of each annual snow layer in the Snow Radar echograms taken across different regions over the Greenland ice sheet. We train with more than 15,000 images generated from radar echograms and estimate the thickness of each snow layer within a mean absolute error of 0.54 to 7.28 pixels, depending on dataset. A highly precise snow layer thickness can help improve weather models and, thus, support glaciological studies. Such a well-trained deep learning model can be used with ever-growing datasets to aid in the accurate assessment of snow accumulation on the dynamically changing ice sheets. 
    more » « less
  2. ; ; ; (, Proceedings of the AAAI Symposium Series)
    The melting of ice sheets significantly contributes to sea level rise, highlighting the crucial need to comprehend the structure of ice for climate benefits. The stratigraphy of ice sheets revealed through ice layer radargrams gives us a window into historical depth-age correlations and accumulation rates. Harnessing this knowledge is not only crucial for interpreting both past and present ice dynamics, especially concerning the Greenland ice sheet, but also for making informed decisions to mitigate the impacts of climate change. Ice layer tracing is prevalently conducted using manual or semi-automatic approaches, requiring significant time and expertise. This study aims to address the need for efficient and precise tracing methods in a two-step process. This is achieved by utilizing an unsupervised annotation method (i.e., ARESELP) to train deep learning models, thereby reducing the need for extensive and time-consuming manual annotations. Four prominent deep learning-based segmentation techniques, namely U-Net, U-Net+VGG19, U-Net+Inception, and Attention U-Net, are benchmarked. Additionally, various thresholding methods such as binary, Otsu, and CLAHE have been explored to achieve optimal enhancement for the true label annotation images. Our preliminary experiments indicate that the combination of attention U-Net with specific processing techniques yields the best performance in terms of the binary IoU metric. 
    more » « less
  3. ; ; ; ; ; ; ; ; ; ; et al (, The Cryosphere)
    Abstract. Arctic rain on snow (ROS) deposits liquid water onto existing snowpacks. Upon refreezing, this can form icy crusts at the surface or within the snowpack. By altering radar backscatter and microwave emissivity, ROS over sea ice can influence the accuracy of sea ice variables retrieved from satellite radar altimetry, scatterometers, and passive microwave radiometers. During the Arctic Ocean MOSAiC (Multidisciplinary drifting Observatory for the Study of Arctic Climate) expedition, there was an unprecedented opportunity to observe a ROS event using in situ active and passive microwave instruments similar to those deployed on satellite platforms. During liquid water accumulation in the snowpack from rain and increased melt, there was a 4-fold decrease in radar energy returned at Ku- and Ka-bands. After the snowpack refroze and ice layers formed, this decrease was followed by a 6-fold increase in returned energy. Besides altering the radar backscatter, analysis of the returned waveforms shows the waveform shape changed in response to rain and refreezing. Microwave emissivity at 19 and 89 GHz increased with increasing liquid water content and decreased as the snowpack refroze, yet subsequent ice layers altered the polarization difference. Corresponding analysis of the CryoSat-2 waveform shape and backscatter as well as AMSR2 brightness temperatures further shows that the rain and refreeze were significant enough to impact satellite returns. Our analysis provides the first detailed in situ analysis of the impacts of ROS and subsequent refreezing on both active and passive microwave observations, providing important baseline knowledge for detecting ROS over sea ice and assessing their impacts on satellite-derived sea ice variables. 
    more » « less
  4. ; ; (, FastTIMES)
    Northern peatlands are unique ecosystems typically located in boreal latitudes that sustain unique habitats and species. They are a critical component of the global carbon cycle, acting both as a carbon reservoir (via peat accumulation after sequestration of carbon dioxide from the atmosphere) and as a carbon source to the atmosphere (by releasing methane and carbon dioxide, two greenhouse gases produced by microbes that thrive in the conditions found in peatlands). Although the ecology of peatlands has been well studied for many decades, the geological controls on peatland development and groundwater flow patterns are not completely understood. In Maine (USA), peatlands began forming about 10,000 years ago following the retreat of the ice sheets at the end of the last ice age. They formed in depressions, often starting as lakes or wetlands, within the landscape carved by glaciers and draped with sediments. Almost two decades of research in several peatlands in Maine suggest that glacial landforms buried beneath peatlands may play a key role in regulating both the hydrology (including the presence of open water pools at the surface) and release of methane gasses from peatlands. Subsurface images using an array of hydrogeophysical methods (including ground-penetrating radar, GPR) constrained with direct coring has revealed the presence of buried esker complexes beneath (or close to) surface pools. Hydrological measurements further suggest that the presence of these permeable esker deposits (mainly gravel and sand) may enhance the connection of peatland water to underlying groundwater and help sustain these pools. Whereas geological maps show that the presence of esker systems in Maine are widespread, satellite-derived digital elevation models (DEMs) reveal that they are often proximal to peatland boundaries, further suggesting that they may commonly extend below the peat formation and control hydrology and carbon dynamics in more peatlands than previously thought. Better understanding of how the critical zone influences coupled water and carbon cycling in northern peatlands may improve the understanding of their contribution to radiative forcing of climate as the climate warms. 
    more » « less
  5. ; ; ; ; ; ; (, Annals of Glaciology)
    Abstract We used measurements of radar-detected stratigraphy, surface ice-flow velocities and accumulation rates to investigate relationships between local valley-glacier and regional ice-sheet dynamics in and around the Schmidt Hills, Pensacola Mountains, Antarctica. Ground-penetrating radar profiles were collected perpendicular to the long axis of the Schmidt Hills and the margin of Foundation Ice Stream (FIS). Within the valley confines, the glacier consists of blue ice, and profiles show internal stratigraphy dipping steeply toward the nunataks and truncated at the present-day ablation surface. Below the valley confines, the blue ice is overlain by firn. Data show that upward-progressing overlap of actively accumulating firn onto valley-glacier ice is slightly less than ice flow out of the valleys over the past ∼1200 years. The apparent slightly negative mass balance (-0.25 cm a -1 ) suggests that ice-margin elevations in the Schmidt Hills may have lowered over this time period, even without a change in the surface elevation of FIS. Results suggest that (1) mass-balance gradients between local valley glaciers and regional ice sheets should be considered when using local information to estimate regional ice surface elevation changes; and (2) interpretation of shallow ice structures imaged with radar can provide information about local ice elevation changes and stability. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email