Temporal Deep Learning Approach to Bedfast and Floating Thermokarst Lake Ice Mapping using SAR imagery: Old Crow Flats, Yukon, Canada
Lake ice is a fundamental part of the freshwater processes in cold regions and a sensitive indicator of climate change. As such, in light of the recent climate warming, monitoring of lake ice in arctic and sub-arctic regions is becoming increasingly important. Many shallow arctic lakes and ponds of...
Main Author: | |
---|---|
Format: | Master Thesis |
Language: | English |
Published: |
University of Waterloo
2021
|
Subjects: | |
Online Access: | http://hdl.handle.net/10012/17414 |
id |
ftunivwaterloo:oai:uwspace.uwaterloo.ca:10012/17414 |
---|---|
record_format |
openpolar |
spelling |
ftunivwaterloo:oai:uwspace.uwaterloo.ca:10012/17414 2023-05-15T14:58:01+02:00 Temporal Deep Learning Approach to Bedfast and Floating Thermokarst Lake Ice Mapping using SAR imagery: Old Crow Flats, Yukon, Canada Shaposhnikova, Maria 2021-09-14 http://hdl.handle.net/10012/17414 en eng University of Waterloo http://hdl.handle.net/10012/17414 remote sensing lake ice SAR deep learning temporal convolutional neural network bedfast ice floating ice Old Crow Flats microwave remote sensing TempCNN thermokarst permafrost Master Thesis 2021 ftunivwaterloo 2022-06-18T23:03:28Z Lake ice is a fundamental part of the freshwater processes in cold regions and a sensitive indicator of climate change. As such, in light of the recent climate warming, monitoring of lake ice in arctic and sub-arctic regions is becoming increasingly important. Many shallow arctic lakes and ponds of thermokarst origin freeze to bed in the winter months maintaining the underlying permafrost in its frozen state. However, as air temperatures rise and precipitation increases, less lakes are expected to develop bedfast ice. In fact, a consistent decrease in maximum ice thickness has been observed over the past decades. Synthetic aperture radar (SAR) offers a unique opportunity to monitor lake ice regimes remotely. Taking advantage of the growing temporal resolution of microwave remote sensing, we proposed applying a temporal deep learning approach to lake ice regime mapping. We employed a combination of Sentinel 1, ERS 1/2, and RADARSAT 1 SAR imagery for the Old Crow Flats (OCF), Yukon, Canada to create an extensive annotated dataset of SAR time-series labeled as either bedfast ice, foating ice, or land, used to train a temporal convolutional neural network (TempCNN). The trained TempCNN, in turn, allowed to automatically map lake ice regimes over a 29-year period (1993-2021). The classi ed maps aligned well with the available fi eld measurements and Canadian Lake Ice Model (CLIMo) simulated ice thickness. Reaching a mean overall classi cation accuracy of 95.05%, the temporal deep learning approach was found promising for automated lake ice regime classi cation. Change detection tools were utilized to determine lake ice regime changes in the OCF over the past 29 years. In the view of signi cant annual variability, no consistent transition towards more foating lake ice was observed. On the contrary, the overall change indicated an extensive transition to bedfast ice caused by a growing number of catastrophic drainages within the examined time period brought on by climate warming and thermokarst processes. Master Thesis Arctic Climate change Ice Old Crow permafrost Thermokarst Yukon University of Waterloo, Canada: Institutional Repository Arctic Yukon Canada Old Crow Flats ENVELOPE(-139.755,-139.755,68.083,68.083) Monitor Lake ENVELOPE(-129.989,-129.989,56.093,56.093) |
institution |
Open Polar |
collection |
University of Waterloo, Canada: Institutional Repository |
op_collection_id |
ftunivwaterloo |
language |
English |
topic |
remote sensing lake ice SAR deep learning temporal convolutional neural network bedfast ice floating ice Old Crow Flats microwave remote sensing TempCNN thermokarst permafrost |
spellingShingle |
remote sensing lake ice SAR deep learning temporal convolutional neural network bedfast ice floating ice Old Crow Flats microwave remote sensing TempCNN thermokarst permafrost Shaposhnikova, Maria Temporal Deep Learning Approach to Bedfast and Floating Thermokarst Lake Ice Mapping using SAR imagery: Old Crow Flats, Yukon, Canada |
topic_facet |
remote sensing lake ice SAR deep learning temporal convolutional neural network bedfast ice floating ice Old Crow Flats microwave remote sensing TempCNN thermokarst permafrost |
description |
Lake ice is a fundamental part of the freshwater processes in cold regions and a sensitive indicator of climate change. As such, in light of the recent climate warming, monitoring of lake ice in arctic and sub-arctic regions is becoming increasingly important. Many shallow arctic lakes and ponds of thermokarst origin freeze to bed in the winter months maintaining the underlying permafrost in its frozen state. However, as air temperatures rise and precipitation increases, less lakes are expected to develop bedfast ice. In fact, a consistent decrease in maximum ice thickness has been observed over the past decades. Synthetic aperture radar (SAR) offers a unique opportunity to monitor lake ice regimes remotely. Taking advantage of the growing temporal resolution of microwave remote sensing, we proposed applying a temporal deep learning approach to lake ice regime mapping. We employed a combination of Sentinel 1, ERS 1/2, and RADARSAT 1 SAR imagery for the Old Crow Flats (OCF), Yukon, Canada to create an extensive annotated dataset of SAR time-series labeled as either bedfast ice, foating ice, or land, used to train a temporal convolutional neural network (TempCNN). The trained TempCNN, in turn, allowed to automatically map lake ice regimes over a 29-year period (1993-2021). The classi ed maps aligned well with the available fi eld measurements and Canadian Lake Ice Model (CLIMo) simulated ice thickness. Reaching a mean overall classi cation accuracy of 95.05%, the temporal deep learning approach was found promising for automated lake ice regime classi cation. Change detection tools were utilized to determine lake ice regime changes in the OCF over the past 29 years. In the view of signi cant annual variability, no consistent transition towards more foating lake ice was observed. On the contrary, the overall change indicated an extensive transition to bedfast ice caused by a growing number of catastrophic drainages within the examined time period brought on by climate warming and thermokarst processes. |
format |
Master Thesis |
author |
Shaposhnikova, Maria |
author_facet |
Shaposhnikova, Maria |
author_sort |
Shaposhnikova, Maria |
title |
Temporal Deep Learning Approach to Bedfast and Floating Thermokarst Lake Ice Mapping using SAR imagery: Old Crow Flats, Yukon, Canada |
title_short |
Temporal Deep Learning Approach to Bedfast and Floating Thermokarst Lake Ice Mapping using SAR imagery: Old Crow Flats, Yukon, Canada |
title_full |
Temporal Deep Learning Approach to Bedfast and Floating Thermokarst Lake Ice Mapping using SAR imagery: Old Crow Flats, Yukon, Canada |
title_fullStr |
Temporal Deep Learning Approach to Bedfast and Floating Thermokarst Lake Ice Mapping using SAR imagery: Old Crow Flats, Yukon, Canada |
title_full_unstemmed |
Temporal Deep Learning Approach to Bedfast and Floating Thermokarst Lake Ice Mapping using SAR imagery: Old Crow Flats, Yukon, Canada |
title_sort |
temporal deep learning approach to bedfast and floating thermokarst lake ice mapping using sar imagery: old crow flats, yukon, canada |
publisher |
University of Waterloo |
publishDate |
2021 |
url |
http://hdl.handle.net/10012/17414 |
long_lat |
ENVELOPE(-139.755,-139.755,68.083,68.083) ENVELOPE(-129.989,-129.989,56.093,56.093) |
geographic |
Arctic Yukon Canada Old Crow Flats Monitor Lake |
geographic_facet |
Arctic Yukon Canada Old Crow Flats Monitor Lake |
genre |
Arctic Climate change Ice Old Crow permafrost Thermokarst Yukon |
genre_facet |
Arctic Climate change Ice Old Crow permafrost Thermokarst Yukon |
op_relation |
http://hdl.handle.net/10012/17414 |
_version_ |
1766330104821055488 |