Speaking: Zoltan Sylvester, University of Texas Austin
A number of meandering rivers in the Arctic, especially in Siberia, have point bars with strikingly structured permafrost polygon patterns. These seem to mimic not just the scroll ‘bar’ lines that are often visible in permafrost-free point bars, but the radial growth lines as well that tend to be perpendicular to the scrolls and have not been observed before. We use a Unet-type convolutional neural network to map the polygons. The network is trained with image tiles derived from manually mapped scroll- and radial lines on nine point bars. Post-processing of the semantic segmentation results allows the identification of individual polygons; a Python ‘networkx’ graph is used to study the relations between the polygons. A simple model of meandering suggests a preliminary explanation of how these beautiful patterns might form.
The Permfrost Discovery Gateway is a NSF and Google.org funded intelligent data management platform created for big data creation and discovery to support knowledge-generation in the Arctic permafrost region. The project is aimed to enable knowledge-generation and community-preparedness by creating big geospatial data products of permafrost thaw features from remote sensing imagery, developing AI tools to identify and track information within the big geospatial data, and building user-friendly online tools to enable scientific discovery, policy, and to empower Arctic communities facing permafrost thaw.