Search

Retrogressive thaw slumps (RTS) are considered one of the most dynamic permafrost disturbance features in the Arctic. Sub-meter resolution multispectral imagery acquired by very high spatial resolution (VHSR) commercial satellite sensors offer unique capacities in capturing the morphological dynamics of RTSs. The central goal of this study is to develop a deep learning convolutional neural net (CNN) model (a UNet-based workflow) to automatically detect and characterize RTSs from VHSR imagery. We aimed to understand: (1) the optimal combination of input image tile size (array size) and the CNN network input size (resizing factor/spatial resolution) and (2) the interoperability of the trained UNet models across heterogeneous study sites based on a limited set of training samples. Hand annotation of RTS samples, CNN model training and testing, and interoperability analyses were based on two study areas from high-Arctic Canada: (1) Banks Island and (2) Axel Heiberg Island and Ellesmere Island. Our experimental results revealed the potential impact of image tile size and the resizing factor on the detection accuracies of the UNet model. The results from the model transferability analysis elucidate the effects on the UNet model due the variability (e.g., shape, color, and texture) associated with the RTS training samples. Overall, study findings highlight several key factors that we should consider when operationalizing CNN-based RTS mapping over large geographical extents. [ABSTRACT FROM AUTHOR]

Riverbank erosion in yedoma regions strongly affects landscape evolution, biogeochemical cycling, sediment transport, and organic and nutrient fluxes to the Arctic Ocean. Since 2006, we have studied the 35‐m‐high Itkillik River yedoma bluff in northern Alaska, whose retreat rate during 1995–2010 was up to 19 m/yr, which is among the highest rates worldwide. This study extends our previous observations of bluff evolution and shows that average bluff‐top retreat rates decreased from 8.7–10.0 m/yr during 2011–2014 to 4.5–5.8 m/yr during 2015–2019, and bluff‐base retreat rates for the same time period decreased from 4.7–7.5 m/yr to 1.3–1.7 m/yr, correspondingly. Bluff evolution initially involves rapid fluvio‐thermal erosion at the base and block collapse, following by slowdown in river erosion and continuing thermal denudation of the retreating headwall with formation of baydzherakhs. Eventually, input of sediment and water from the headwall diminishes, vegetation develops, and slope gradually stabilizes. The step change in the fluvial–geomorphic system has resulted in a 60% decline in the volumetric mobilization of sediment and organic carbon between 2011 and 2019. Our findings stress the importance of sustained observations at key permafrost region study sites to elucidate critical information related to past and potential landscape evolution in the Arctic. [ABSTRACT FROM AUTHOR]