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
  • Combining “Deep Learning” and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern High-Resolution Satellite Imagery: Application of the GEOCLASS-Image System to Create VarioCNN for Glacier Surges
Title: Combining “Deep Learning” and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern High-Resolution Satellite Imagery: Application of the GEOCLASS-Image System to Create VarioCNN for Glacier Surges
The objectives of this paper are to investigate the trade-offs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach (“VarioCNN”). Our solution is provided in the framework of a cyberinfrastructure that includes a newly designed ML software, GEOCLASS-image (v1.0), modern high-resolution satellite image data sets (Maxar WorldView data), and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100–200 times its normal velocity. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in six simplified classes.  more » « less
Award ID(s):
1942356 1835256
PAR ID:
10563362
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
MDPI
Date Published:
Journal Name:
Remote Sensing
Volume:
16
Issue:
11
ISSN:
2072-4292
Page Range / eLocation ID:
1854
Subject(s) / Keyword(s):
neural networks convolutional neural networks geostatistics glaciology surge glaciers image classification satellite remote sensing spatial classification connectionist-geostatistical classification
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Remote Sensing)
    The topic of this paper is the airborne evaluation of ICESat-2 Advanced Topographic Laser Altimeter System (ATLAS) measurement capabilities and surface-height-determination over crevassed glacial terrain, with a focus on the geodetical accuracy of geophysical data collected from a helicopter. To obtain surface heights over crevassed and otherwise complex ice surface, ICESat-2 data are analyzed using the density-dimension algorithm for ice surfaces (DDA-ice), which yields surface heights at the nominal 0.7 m along-track spacing of ATLAS data. As the result of an ongoing surge, Negribreen, Svalbard, provided an ideal situation for the validation objectives in 2018 and 2019, because many different crevasse types and morphologically complex ice surfaces existed in close proximity. Airborne geophysical data, including laser altimeter data (profilometer data at 905 nm frequency), differential Global Positioning System (GPS), Inertial Measurement Unit (IMU) data, on-board-time-lapse imagery and photographs, were collected during two campaigns in summers of 2018 and 2019. Airborne experiment setup, geodetical correction and data processing steps are described here. To date, there is relatively little knowledge of the geodetical accuracy that can be obtained from kinematic data collection from a helicopter. Our study finds that (1) Kinematic GPS data collection with correction in post-processing yields higher accuracies than Real-Time-Kinematic (RTK) data collection. (2) Processing of only the rover data using the Natural Resources Canada Spatial Reference System Precise Point Positioning (CSRS-PPP) software is sufficiently accurate for the sub-satellite validation purpose. (3) Distances between ICESat-2 ground tracks and airborne ground tracks were generally better than 25 m, while distance between predicted and actual ICESat-2 ground track was on the order of 9 m, which allows direct comparison of ice-surface heights and spatial statistical characteristics of crevasses from the satellite and airborne measurements. (4) The Lasertech Universal Laser System (ULS), operated at up to 300 m above ground level, yields full return frequency (400 Hz) and 0.06–0.08 m on-ice along-track spacing of height measurements. (5) Cross-over differences of airborne laser altimeter data are −0.172 ± 2.564 m along straight paths, which implies a precision of approximately 2.6 m for ICESat-2 validation experiments in crevassed terrain. (6) In summary, the comparatively light-weight experiment setup of a suite of small survey equipment mounted on a Eurocopter (Helicopter AS-350) and kinematic GPS data analyzed in post-processing using CSRS-PPP leads to high accuracy repeats of the ICESat-2 tracks. The technical results (1)–(6) indicate that direct comparison of ice-surface heights and crevasse depths from the ICESat-2 and airborne laser altimeter data is warranted. Numerical evaluation of height comparisons utilizes spatial surface roughness measures. The final result of the validation is that ICESat-2 ATLAS data, analyzed with the DDA-ice, facilitate surface-height determination over crevassed terrain, in good agreement with airborne data, including spatial characteristics, such as surface roughness, crevasse spacing and depth, which are key informants on the deformation and dynamics of a glacier during surge. 
    more » « less
  2. ; ; ; (, Artificial Intelligence for the Earth Systems)
    Abstract Superresolution is the general task of artificially increasing the spatial resolution of an image. The recent surge in machine learning (ML) research has yielded many promising ML-based approaches for performing single-image superresolution including applications to satellite remote sensing. We develop a convolutional neural network (CNN) to superresolve the 1- and 2-km bands on the GOES-R series Advanced Baseline Imager (ABI) to a common high resolution of 0.5 km. Access to 0.5-km imagery from ABI band 2 enables the CNN to realistically sharpen lower-resolution bands without significant blurring. We first train the CNN on a proxy task, which allows us to only use ABI imagery, namely, degrading the resolution of ABI bands and training the CNN to restore the original imagery. Comparisons at reduced resolution and at full resolution withLandsat-8/Landsat-9observations illustrate that the CNN produces images with realistic high-frequency detail that is not present in a bicubic interpolation baseline. Estimating all ABI bands at 0.5-km resolution allows for more easily combining information across bands without reconciling differences in spatial resolution. However, more analysis is needed to determine impacts on derived products or multispectral imagery that use superresolved bands. This approach is extensible to other remote sensing instruments that have bands with different spatial resolutions and requires only a small amount of data and knowledge of each channel’s modulation transfer function. Significance StatementSatellite remote sensing instruments often have bands with different spatial resolutions. This work shows that we can artificially increase the resolution of some lower-resolution bands by taking advantage of the texture of higher-resolution bands on theGOES-16ABI instrument using a convolutional neural network. This may help reconcile differences in spatial resolution when combining information across bands, but future analysis is needed to precisely determine impacts on derived products that might use superresolved bands. 
    more » « less
  3. ; (, Earth ArXiv)
    The unique measurement capabilities of ICESat-2 allow high spatiotemporal resolution of complex ice-dynamic processes that occur during a surge. Detailed and precise mapping of height changes on surge glaciers has previously escaped observations from space due to limited resolution of space-borne altimeter data and the surface characteristics of glaciers during surge such as heavy crevassing. This makes geophysical interpretation of deformation and assessment of mass transfer difficult. In this paper, we present an approach that facilitates analysis of the evolution of geophysical processes during a surge, including height changes, crevassing, mass transfer and roughness evolution. We utilize all data from 2 years of ICESat-2 observations collected during the mature phase of the Negribreen Glacier System (NGS) surge in 2019 and 2020. The progression of the NGS surge has resulted in large-scale elevation changes and wide-spread crevassing making it an ideal case study to demonstrate ICESat-2 measurement capabilities, which are maximized when coupled with the Density Dimension Algorithm for Ice (DDA-ice). Results show the expansion of the surge in upper Negribreen which demonstrates the unique ability of ICESat-2/DDA-ice to measure a rapidly changing surge glacier and provide the best estimates for cryospheric changes and their contributions to sea-level rise. 
    more » « less
  4. ; ; ; (, The Cryosphere)
    Abstract. En masse application of feature tracking algorithms to satellite image pairs has produced records of glacier surface velocities with global coverage, revolutionizing the understanding of global glacier change. However, glacier velocity records are sometimes incomplete due to gaps in the cloud-free satellite image record (for optical images) and failure of standard feature tracking parameters, e.g., search range, chip size, or estimated displacement, to capture rapid changes in glacier velocity. Here, we present a pipeline for pre-processing commercial high-resolution daily PlanetScope surface reflectance images and for generating georeferenced glacier velocity maps using NASA's autonomous Repeat Image Feature Tracking (autoRIFT) algorithm with customized parameters. We compare our velocity time series to the NASA Inter-Mission Time Series of Land Ice Velocity and Elevation (ITS_LIVE) global glacier velocity dataset, which is produced using autoRIFT, with regional-scale feature tracking parameters. Using five surge-type glaciers as test sites, we demonstrate that the use of customized feature tracking parameters for each glacier improves upon the velocity record provided by ITS_LIVE during periods of rapid glacier acceleration (i.e., changes greater than several meters per day over 2–3 months). We show that ITS_LIVE can fail to capture velocities during glacier surges but that both the use of custom autoRIFT parameters and the inclusion of PlanetScope imagery can capture the progression of order-of-magnitude changes in flow speed with median uncertainties of <0.5 m d−1. Additionally, the PlanetScope image record approximately doubles the amount of optical cloud-free imagery available for each glacier and the number of velocity maps produced outside of the months affected by darkness (i.e., polar night), augmenting the ITS_LIVE record. We demonstrate that these pipelines provide additional insights into speedup behavior for the test glaciers and recommend that they are used for studies that aim to capture glacier velocity change at sub-monthly timescales and with greater spatial detail. 
    more » « less
  5. ; ; ; ; ; (, ACM)
    With the rise of tiny IoT devices powered by machine learning (ML), many researchers have directed their focus toward compressing models to fit on tiny edge devices. Recent works have achieved remarkable success in compressing ML models for object detection and image classification on microcontrollers with small memory, e.g., 512kB SRAM. However, there remain many challenges prohibiting the deployment of ML systems that require high-resolution images. Due to fundamental limits in memory capacity for tiny IoT devices, it may be physically impossible to store large images without external hardware. To this end, we propose a high-resolution image scaling system for edge ML, called HiRISE, which is equipped with selective region-of-interest (ROI) capability leveraging analog in-sensor image scaling. Our methodology not only significantly reduces the peak memory requirements, but also achieves up to 17.7× reduction in data transfer and energy consumption. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email