Articles | Volume 13, issue 1
The Cryosphere, 13, 237–245, 2019
https://doi.org/10.5194/tc-13-237-2019
The Cryosphere, 13, 237–245, 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 et al.

Model code and software

CNN-watershed: A machine-learning based tool for delineation and measurement of ice wedge polygons in high-resolution digital elevation models Abolt, CJ; Young, MH; Atchley, AL; Wilson, CJ https://doi.org/10.5821/zenodo.2537167

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.