Articles | Volume 13, issue 1
https://doi.org/10.5194/tc-13-237-2019
https://doi.org/10.5194/tc-13-237-2019
Brief communication
 | 
25 Jan 2019
Brief communication |  | 25 Jan 2019

Brief communication: Rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models

Charles J. Abolt, Michael H. Young, Adam L. Atchley, and Cathy J. Wilson

Download

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by Charles Abolt on behalf of the Authors (17 Dec 2018)  Author's response   Manuscript 
ED: Publish as is (04 Jan 2019) by Moritz Langer
AR by Charles Abolt on behalf of the Authors (10 Jan 2019)  Manuscript 
Download
Short summary
We present a workflow that uses a machine-learning algorithm known as a convolutional neural network (CNN) to rapidly delineate ice wedge polygons in high-resolution topographic datasets. Our workflow permits thorough assessments of polygonal microtopography at the kilometer scale or greater, which can improve understanding of landscape hydrology and carbon budgets. We demonstrate that a single CNN can be trained to delineate polygons with high accuracy in diverse tundra settings.