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: Deep Sensing of Ocean Wave Heights with Synthetic Aperture Radar.
The Sentinel-1 satellites equipped with synthetic aperture radars (SAR) provide near global coverage of the world’s oceans every six days. We curate a data set of co-locations between SAR and altimeter satellites, and investigate the use of deep learning to predict significant wave height from SAR. While previous models for predicting geophysical quantities from SAR rely heavily on feature-engineering, our approach learns directly from low-level image cross-spectra. Training on co-locations from 2015-2017, we demonstrate on test data from 2018 that deep learning reduces the state-of-the-art root mean squared error by 50%, from 0.6 meters to 0.3 meters.  more » « less
Award ID(s):
1920304
PAR ID:
10273998
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
AAAI 2020 Spring Symposium
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium)
    Deploying deep learning on Synthetic Aperture Radar (SAR) data is becoming more common for mapping purposes. One such case is sea ice, which is highly dynamic and rapidly changes as a result of the combined effect of wind, temperature, and ocean currents. Therefore, frequent mapping of sea ice is necessary to ensure safe marine navigation. However, there is a general shortage of expert-labeled data to train deep learning algorithms. Fine-tuning a pre-trained model on SAR imagery is a potential solution. In this paper, we compare the performance of deep learning models trained from scratch using randomly initialized weights against pre-trained models that we fine-tune for this purpose. Our results show that pre-trained models lead to better results, especially on test samples from the melt season. 
    more » « less
  2. ; ; ; ; ; ; (, Journal of Geophysical Research: Solid Earth)
    Abstract Interferometric Synthetic Aperture Radar (InSAR) provides subcentimetric measurements of surface displacements, which are key for characterizing and monitoring magmatic processes in volcanic regions. The abundant measurements of surface displacements in multitemporal InSAR data routinely acquired by SAR satellites can facilitate near real‐time volcano monitoring on a global basis. However, the presence of atmospheric signals in interferograms complicates the interpretation of those InSAR measurements, which can even lead to a misinterpretation of InSAR signals and volcanic unrest. Given the vast quantities of SAR data available, an automatic InSAR data processing and denoising approach is required to separate volcanic signals that are cause of concern from atmospheric signals and noise. In this study, we employ a deep learning strategy that directly removes atmospheric and other noise signals from time‐consecutive unwrapped surface displacements obtained through an InSAR time series approach using an end‐to‐end convolutional neural network (CNN) with an encoder‐decoder architecture, modified U‐net. The CNN is trained with simulated synthetic unwrapped surface displacement maps and is then applied to real InSAR data. Our proposed architecture is capable of detecting dynamic spatio‐temporal patterns of volcanic surface displacements. We find that an ensemble‐average strategy is recommended to stabilize detected results for varying deformation rates and signal‐to‐noise ratios (SNRs). A case study is also presented where this method is applied to InSAR data covering Masaya volcano, Nicaragua and the results are validated using continuous GPS data. The results confirm that our network can indeed efficiently suppress atmospheric and other noise to reveal the noise‐free surface deformation. 
    more » « less
  3. (, US NSF Ocean Observatories Initiative)
    "The Southern Ocean Profiler Mooring is co-located with Southern Ocean Surface Mooring at the Apex site. Two identical Flanking Moorings make up the equidistant sides of a triangle of Moorings (50 km) from the Apex site. The Profiler Mooring is located in 4,800 meters of water in the Southern Ocean, SW of Chile. The triangular configuration moorings provide unique spatial array through which instruments fixed to moorings continuously collect data through time and gliders sample the area between the moorings. The Southern Ocean site is one of four high latitude open ocean locations in the OOI that provide observations to gain better insight into global ocean circulation and climate. The Southern Ocean Profiler Mooring contains two Wire-Following Profilers that house instrumentation. The Wire-Following Profiler moves through the water column along the mooring riser, continuously sampling ocean characteristics at a high vertical resolution over a specified depth interval (310-2,100 meters and 2,100-4,400 meters deep)." 
    more » « less
  4. (, US NSF Ocean Observatories Initiative)
    The Argentine Basin Profiler Mooring is co-located with Argentine Basin Surface Mooring at the Apex site. Two identical Flanking Moorings make up the equidistant sides of a triangle of Moorings (62 km) from the Apex site. The Profiler Mooring is located in 5,200 meters of water along the Brazil Current in the South Atlantic. The triangular configuration moorings provide unique spatial array through which instruments fixed to moorings continuously collect data through time and gliders sample the area between the moorings. The Argentine Basin site is one of four high latitude open ocean locations in the OOI that provide observations to gain better insight into global ocean circulation and climate.\nThe Argentine Basin Profiler Mooring contains two Wire-Following Profilers that house instrumentation. The Wire-Following Profiler moves through the water column along the mooring riser, continuously sampling ocean characteristics at a high vertical resolution over a specified depth interval (310-2,445 meters and 2,470-4605 meters deep). 
    more » « less
  5. (, US NSF Ocean Observatories Initiative)
    The Station Papa Profiler Mooring is co-located with a NOAA Surface Mooring at the Apex site. Two identical Flanking Moorings make up the equidistant sides of a triangle of Moorings (40 km) from the Apex site. The Profiler Mooring is located in 4,250 meters in the Gulf of Alaska in the NE Pacific. The triangular configuration moorings provide unique spatial array through which instruments fixed to moorings continuously collect data through time and gliders sample the area between the moorings. The Station Papa site is one of four high latitude open ocean locations in the OOI that provide observations to gain better insight into global ocean circulation and climate.\nThe Station Papa Profiler Mooring contains two Wire-Following Profilers that house instrumentation. The Wire-Following Profiler moves through the water column along the mooring riser, continuously sampling ocean characteristics at a high vertical resolution over a specified depth interval (156-2090 meters and 2129-4063 meters deep). 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email