Search

Permafrost coasts are experiencing accelerated erosion in response to above average warming in the Arctic resulting in local, regional, and global consequences. However, Arctic coasts are expansive in scale, constituting 30–34% of Earth's coastline, and represent a particular challenge for wide-scale, high temporal measurement and monitoring. This study addresses the potential strengths and limitations of an object-based approach to integrate with an automated workflow by assessing the accuracy of coastal classifications and subsequent feature extraction of coastal indicator features. We tested three object-based classifications; thresholding, supervised, and a deep learning model using convolutional neural networks, focusing on a Pleaides satellite scene in the Western Canadian Arctic. Multiple spatial resolutions (0.6, 1, 2.5, 5, 10, and 30 m/pixel) and segmentation scales (100, 200, 300, 400, 500, 600, 700, and 800) were tested to understand the wider applicability across imaging platforms. We achieved classification accuracies greater than 85% for the higher image resolution scenarios using all classification methods. Coastal features, waterline and tundra, or vegetation, line, generated from image classifications were found to be within the image uncertainty 60% of the time when compared to reference features. Further, for very high resolution scenarios, segmentation scale did not affect classification accuracy; however, a smaller segmentation scale (i.e., smaller image objects) led to improved feature extraction. Similar results were generated across classification approaches with a slight improvement observed when using deep learning CNN, which we also suggest has wider applicability. Overall, our study provides a promising contribution towards broad scale monitoring of Arctic coastal erosion. [ABSTRACT FROM AUTHOR]

The warming of high latitudes climate is enhancing the degradation of ground-ice and inducing important landscape changes across the Arctic. This new Arctic state affects geomorphological dynamics, hydrology, and ecosystems, and poses challenges to the stability of infrastructure and livelihoods of Arctic communities. This study focuses on the hamlet of Paulatuk within the Inuvialuit Settlement Region of the Amundsen Gulf, south Darnley Bay, in northern Canada. In the summer of 2019, an ultra-high resolution aerial survey with a fixed-wing Unmanned Aerial Vehicle (UAV) was conducted, generating a 5 cm spatial resolution orthomosaic and Digital Surface Model (DSM). These, together with field observations were used to produce a very-high resolution geomorphological map of the settlement and surrounding coastal areas. Landscape changes were analyzed using historical aerial imagery of 1975 and 1993, the 2019 UAV survey and a very-high resolution Pléiades satellite scene from 2020. The area is a tundra terrace made up of sandy fluvioglacial sediments affected by a dense network of ice-wedge polygons, mostly high-centered, but also low-centered, showing signs of permafrost degradation. Air and ground temperatures have increased respectively by 0.8 and 1.9 °C over last two decades at Paulatuk, and inter-polygon ponds surface increased by 23,000 m2 since 1975 due to ice-wedge thawing. The airstrip enhanced thaw pond formation on its margins, especially after 1993. The DSM reveals a depression south of the airstrip, which can be potentially flooded due to its proximity to the coastal waters. • Air and ground temperatures increased significantly over the two last decades leading to permafrost degradation. • Infrastructures participate in increasing surficial water retention at their margin, disrupting ground-thermal regime. • High-centered ice-wedges polygons and inter-polygon ponds revealed advanced signs of degradation due to ground-ice thawing. • A low depression basin is subject to marine submersion associated with relative sea level rise scenarios by 2100. [ABSTRACT FROM AUTHOR]