We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Identification of Unstable Glacier Flow in the Western Tibetan Plateau and Karakoram Using Machine Learning.
- Authors
Zhu, Q. H.; Ke, C. Q.; Li, H. L.; Yu, X. N.
- Abstract
A novel method was developed for rapidly and accurately identifying unstable glacier flows, including pulse and surge events. The identification method was based on machine learning and high‐frequency glacier velocities derived from short time interval Sentinel‐1 Synthetic Aperture Radar (SAR) data. The method was built and tested using 32 glaciers in the eastern Pamir Plateau and applied it to 13 glaciers in western Karakoram. The test results showed that the success rate of identifying speedup events was more than 90% compared to manual interpretation results derived using velocity change maps and DEM differencing. The application results showed that there were some neglected pulse events, including two pulses on the Kukuar Glacier in 2017 and 2019, one pulse on the Karambar Glacier in 2017, and one pulse on the Ghulkin Glacier in 2016. Moreover, a complete surge event with multiple scattered pulses on the Shispare Glacier in 2018–2019 was also detected. The speedup events of the Shispare Glacier indicated the possibility of mutual transformation between pulse and surge events due to the influence of glacier basal roughness. In all unstable flows occurring within the test and application areas, pulse events could be observed on the nonsurging glaciers during the active phase and quiescent phase of the surge‐type glaciers, which might suggest the randomness of pulse events. Machine learning method made it possible to identify glacier speedup events in large areas with high efficiency and low manpower. Plain Language Summary: The phenomenon that abundant crevassed ice bodies move downstream of glacier surface at a high speed for months to years is called surge, while the unstable flow with smaller temporal and spatial scales than surge is called pulse. The most obvious feature of these unstable glacier flows was the rapid increase of velocity. The unstable glacier flow sometimes could cause serious glacier hazard. Therefore, it is particularly important to identify the unstable flow. Most methods are used to identify the unstable flow by observing glacier surface characteristics from optical satellite images or analyzing changes of glacier velocity and elevation. However, these methods are time‐consuming and only suitable for a small number of glaciers. Here, a machine‐learning algorithm is first used to identify the glacier flow state after calculating time‐series velocities of glaciers in the Western Tibetan Plateau from 127 Synthetic Aperture Radar (SAR) image pairs with 12‐day or 24‐day time interval. The results showed that the identification accuracy was over 90%, and some previously neglected pulses and more detailed surges could be identified due to more stable and shorter time interval of SAR data. The results also indicated that there was a possibility of mutual transformation between pulse and surge. Key Points: A machine learning method was developed to identify unstable glacier flow, providing an accuracy over 90%A complete surge with several pulses on Shispare Glacier and some neglected pulses on other glaciers were detectedPulse events may evolve into surge events under the control of the glacier base roughness
- Subjects
KARAKORAM Range; GLACIOLOGY; GLACIERS; SYNTHETIC aperture radar; MACHINE learning; REMOTE-sensing images
- Publication
Journal of Geophysical Research. Earth Surface, 2022, Vol 127, Issue 5, p1
- ISSN
2169-9003
- Publication type
Article
- DOI
10.1029/2022JF006623