Semiautomatic Mapping of Permafrost in the Yukon Flats - Alaska

Mats Lundh Gulbrandsen; Burke J. Minsley; Lyndsay B. Ball; Thomas Mejer Hansen

doi:10.1002/2016GL071334

Semiautomatic Mapping of Permafrost in the Yukon Flats - Alaska

Mats Lundh Gulbrandsen, Burke J. Minsley, Lyndsay B. Ball, Thomas Mejer Hansen

Climate and Geophysics

3 Citations (Scopus)

1 Downloads (Pure)

Abstract

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.

Original language	English
Journal	Geophysical Research Letters
Volume	43
Issue number	23
Pages (from-to)	131-137
ISSN	0094-8276
DOIs	https://doi.org/10.1002/2016GL071334
Publication status	Published - 16 Dec 2016

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1002/2016GL071334

grl55266Final published version, 1.76 MB

Cite this

@article{e53eaf643ff54b608976487b24321fa5,

title = "Semiautomatic Mapping of Permafrost in the Yukon Flats - Alaska",

abstract = "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.",

author = "Gulbrandsen, {Mats Lundh} and Minsley, {Burke J.} and Ball, {Lyndsay B.} and Hansen, {Thomas Mejer}",

year = "2016",

month = dec,

day = "16",

doi = "10.1002/2016GL071334",

language = "English",

volume = "43",

pages = "131--137",

journal = "Geophysical Research Letters",

issn = "0094-8276",

publisher = "Wiley-Blackwell",

number = "23",

}

TY - JOUR

T1 - Semiautomatic Mapping of Permafrost in the Yukon Flats - Alaska

AU - Gulbrandsen, Mats Lundh

AU - Minsley, Burke J.

AU - Ball, Lyndsay B.

AU - Hansen, Thomas Mejer

PY - 2016/12/16

Y1 - 2016/12/16

N2 - 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.

AB - 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.

U2 - 10.1002/2016GL071334

DO - 10.1002/2016GL071334

M3 - Journal article

SN - 0094-8276

VL - 43

SP - 131

EP - 137

JO - Geophysical Research Letters

JF - Geophysical Research Letters

IS - 23

ER -

Semiautomatic Mapping of Permafrost in the Yukon Flats - Alaska

Abstract

UN SDGs

Access to Document

Fingerprint

Cite this