Brief communication: Rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models
We present a workflow for the rapid delineation and microtopographic characterization of ice wedge polygons within high-resolution digital elevation models. At the core of the workflow is a convolutional neural network used to detect pixels representing polygon boundaries. A watershed transformation...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-13-237-2019 https://tc.copernicus.org/articles/13/237/2019/ |
id |
ftcopernicus:oai:publications.copernicus.org:tc70923 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:tc70923 2023-05-15T15:39:41+02:00 Brief communication: Rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models Abolt, Charles J. Young, Michael H. Atchley, Adam L. Wilson, Cathy J. 2019-01-25 application/pdf https://doi.org/10.5194/tc-13-237-2019 https://tc.copernicus.org/articles/13/237/2019/ eng eng doi:10.5194/tc-13-237-2019 https://tc.copernicus.org/articles/13/237/2019/ eISSN: 1994-0424 Text 2019 ftcopernicus https://doi.org/10.5194/tc-13-237-2019 2020-07-20T16:22:58Z We present a workflow for the rapid delineation and microtopographic characterization of ice wedge polygons within high-resolution digital elevation models. At the core of the workflow is a convolutional neural network used to detect pixels representing polygon boundaries. A watershed transformation is subsequently used to segment imagery into discrete polygons. Fast training times ( <5 min) permit an iterative approach to improving skill as the routine is applied across broad landscapes. Results from study sites near Utqiaġvik (formerly Barrow) and Prudhoe Bay, Alaska, demonstrate robust performance in diverse tundra settings, with manual validations demonstrating 70–96 % accuracy by area at the kilometer scale. The methodology permits precise, spatially extensive measurements of polygonal microtopography and trough network geometry. Text Barrow Prudhoe Bay Tundra Alaska Copernicus Publications: E-Journals The Cryosphere 13 1 237 245 |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
We present a workflow for the rapid delineation and microtopographic characterization of ice wedge polygons within high-resolution digital elevation models. At the core of the workflow is a convolutional neural network used to detect pixels representing polygon boundaries. A watershed transformation is subsequently used to segment imagery into discrete polygons. Fast training times ( <5 min) permit an iterative approach to improving skill as the routine is applied across broad landscapes. Results from study sites near Utqiaġvik (formerly Barrow) and Prudhoe Bay, Alaska, demonstrate robust performance in diverse tundra settings, with manual validations demonstrating 70–96 % accuracy by area at the kilometer scale. The methodology permits precise, spatially extensive measurements of polygonal microtopography and trough network geometry. |
format |
Text |
author |
Abolt, Charles J. Young, Michael H. Atchley, Adam L. Wilson, Cathy J. |
spellingShingle |
Abolt, Charles J. Young, Michael H. Atchley, Adam L. Wilson, Cathy J. Brief communication: Rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models |
author_facet |
Abolt, Charles J. Young, Michael H. Atchley, Adam L. Wilson, Cathy J. |
author_sort |
Abolt, Charles J. |
title |
Brief communication: Rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models |
title_short |
Brief communication: Rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models |
title_full |
Brief communication: Rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models |
title_fullStr |
Brief communication: Rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models |
title_full_unstemmed |
Brief communication: Rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models |
title_sort |
brief communication: rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models |
publishDate |
2019 |
url |
https://doi.org/10.5194/tc-13-237-2019 https://tc.copernicus.org/articles/13/237/2019/ |
genre |
Barrow Prudhoe Bay Tundra Alaska |
genre_facet |
Barrow Prudhoe Bay Tundra Alaska |
op_source |
eISSN: 1994-0424 |
op_relation |
doi:10.5194/tc-13-237-2019 https://tc.copernicus.org/articles/13/237/2019/ |
op_doi |
https://doi.org/10.5194/tc-13-237-2019 |
container_title |
The Cryosphere |
container_volume |
13 |
container_issue |
1 |
container_start_page |
237 |
op_container_end_page |
245 |
_version_ |
1766371716468047872 |