Skip to main content
U.S. flag

An official website of the United States government

Semiautomatic mapping of permafrost in the Yukon Flats, Alaska

December 1, 2016

Thawing of permafrost due to global warming can have major impacts on hydrogeological processes, climate feedback, arctic ecology, and local environments. To understand these effects and processes, it is crucial to know the distribution of permafrost. In this study we exploit the fact that airborne electromagnetic (AEM) data are sensitive to the distribution of permafrost and demonstrate how the distribution of permafrost in the Yukon Flats, Alaska, is mapped in an efficient (semiautomatic) way, using a combination of supervised and unsupervised (machine) learning algorithms, i.e., Smart Interpretation and K-means clustering. Clustering is used to sort unfrozen and frozen regions, and Smart Interpretation is used to predict the depth of permafrost based on expert interpretations. This workflow allows, for the first time, a quantitative and objective approach to efficiently map permafrost based on large amounts of AEM data.

Citation Information

Publication Year 2016
Title Semiautomatic mapping of permafrost in the Yukon Flats, Alaska
DOI 10.1002/2016GL071334
Authors Mats Lundh Gulbrandsen, Burke J. Minsley, Lyndsay B. Ball, Thomas Mejer Hansen
Publication Type Article
Publication Subtype Journal Article
Series Title Geophysical Research Letters
Index ID 70193685
Record Source USGS Publications Warehouse
USGS Organization Crustal Geophysics and Geochemistry Science Center