20 Jun 2022
20 Jun 2022
Status: this preprint is open for discussion.

Bedfast and Floating Ice Dynamics of Thermokarst Lakes Using a Temporal Deep Learning Mapping Approach: Case Study of the Old Crow Flats, Yukon, Canada

Maria Shaposhnikova1, Claude R. Duguay1,2, and Pascale Roy-Léveillée3 Maria Shaposhnikova et al.
  • 1Department of Geography and Environmental Management, University of Waterloo, Waterloo, Ontario, Canada
  • 2H2O Geomatics Inc., Waterloo, Ontario, Canada
  • 3Département de géographie et Centre d’études nordiques, Université Laval, Québec, Québec, Canada

Abstract. 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 this work, we propose a novel temporal deep learning approach to lake ice regime mapping from synthetic aperture radar (SAR) and employ it to study lake ice dynamics in the Old Crow Flats (OCF), Yukon, Canada over the 1993 to 2021 period. We utilized a combination of Sentinel-1, ERS-1 and 2, and RADARSAT-1 to create an extensive annotated dataset of SAR time-series labeled as either bedfast ice, floating ice, or land, used to train a temporal convolutional neural network (TempCNN). The trained TempCNN, in turn, allowed to automatically map lake ice regimes. The classified maps aligned well with the available field measurements and ice thickness simulations obtained with a thermodynamic lake ice model. Reaching a mean overall classification accuracy of 95 %, the TempCNN was determined to be suitable for automated lake ice regime classification. The fraction of bedfast ice in the OCF increased by 11 % over the 29-year period of analysis. Findings suggest that the OCF lake ice dynamics is dominated by lake drainage events, brought on by thermokarst processes accelerated by climate warming, as well as fluctuations in water level and winter snowfall. Catastrophic drainage, and lowered water levels cause surface water area and lake depth to decrease and lake ice to often transition from floating to bedfast ice, while a reduction in snowfall allows for the growth of thicker ice.

Maria Shaposhnikova et al.

Status: open (until 15 Aug 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Maria Shaposhnikova et al.

Maria Shaposhnikova et al.


Total article views: 117 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
80 34 3 117 2 0
  • HTML: 80
  • PDF: 34
  • XML: 3
  • Total: 117
  • BibTeX: 2
  • EndNote: 0
Views and downloads (calculated since 20 Jun 2022)
Cumulative views and downloads (calculated since 20 Jun 2022)

Viewed (geographical distribution)

Total article views: 99 (including HTML, PDF, and XML) Thereof 99 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 02 Jul 2022
Short summary
This paper explores lake ice in the Old Crow Flats, Yukon, Canada using a novel approach that employs radar imagery and deep learning. Results indicate an 11 % increase in fraction of lake ice that grounds between 1993 and 2021. We believe this to be caused by widespread lake drainage, and fluctuations in water level and snow depth. This transition is likely to have implications for permafrost beneath the lakes, with potential impact on methane ebullition and the regional carbon budget.