Use of Very High Spatial Resolution Commercial Satellite Imagery and Deep Learning to Automatically Map Ice-Wedge Polygons across Tundra Vegetation Types
We developed a high-throughput mapping workflow, which centers on deep learning (DL) convolutional neural network (CNN) algorithms on high-performance distributed computing resources, to automatically characterize ice-wedge polygons (IWPs) from sub-meter resolution commercial satellite imagery. We a...
Published in: | Journal of Imaging |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2020
|
Subjects: | |
Online Access: | https://doi.org/10.3390/jimaging6120137 https://doaj.org/article/83668c1d94ca4a5f817210c046c01570 |
id |
ftdoajarticles:oai:doaj.org/article:83668c1d94ca4a5f817210c046c01570 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:83668c1d94ca4a5f817210c046c01570 2023-05-15T15:09:59+02:00 Use of Very High Spatial Resolution Commercial Satellite Imagery and Deep Learning to Automatically Map Ice-Wedge Polygons across Tundra Vegetation Types Md Abul Ehsan Bhuiyan Chandi Witharana Anna K. Liljedahl 2020-12-01T00:00:00Z https://doi.org/10.3390/jimaging6120137 https://doaj.org/article/83668c1d94ca4a5f817210c046c01570 EN eng MDPI AG https://www.mdpi.com/2313-433X/6/12/137 https://doaj.org/toc/2313-433X doi:10.3390/jimaging6120137 2313-433X https://doaj.org/article/83668c1d94ca4a5f817210c046c01570 Journal of Imaging, Vol 6, Iss 137, p 137 (2020) permafrost Arctic deep learning tundra ice-wedge polygon Mask R-CNN Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95 article 2020 ftdoajarticles https://doi.org/10.3390/jimaging6120137 2022-12-31T05:27:59Z We developed a high-throughput mapping workflow, which centers on deep learning (DL) convolutional neural network (CNN) algorithms on high-performance distributed computing resources, to automatically characterize ice-wedge polygons (IWPs) from sub-meter resolution commercial satellite imagery. We applied a region-based CNN object instance segmentation algorithm, namely the Mask R-CNN, to automatically detect and classify IWPs in North Slope of Alaska. The central goal of our study was to systematically expound the DLCNN model interoperability across varying tundra types (sedge, tussock sedge, and non-tussock sedge) and image scene complexities to refine the understanding of opportunities and challenges for regional-scale mapping applications. We corroborated quantitative error statistics along with detailed visual inspections to gauge the IWP detection accuracies. We found promising model performances (detection accuracies: 89% to 96% and classification accuracies: 94% to 97%) for all candidate image scenes with varying tundra types. The mapping workflow discerned the IWPs by exhibiting low absolute mean relative error (AMRE) values (0.17–0.23). Results further suggest the importance of increasing the variability of training samples when practicing transfer-learning strategy to map IWPs across heterogeneous tundra cover types. Overall, our findings demonstrate the robust performances of IWPs mapping workflow in multiple tundra landscapes. Article in Journal/Newspaper Arctic Ice north slope permafrost Tundra wedge* Alaska Directory of Open Access Journals: DOAJ Articles Arctic Journal of Imaging 6 12 137 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
permafrost Arctic deep learning tundra ice-wedge polygon Mask R-CNN Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95 |
spellingShingle |
permafrost Arctic deep learning tundra ice-wedge polygon Mask R-CNN Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95 Md Abul Ehsan Bhuiyan Chandi Witharana Anna K. Liljedahl Use of Very High Spatial Resolution Commercial Satellite Imagery and Deep Learning to Automatically Map Ice-Wedge Polygons across Tundra Vegetation Types |
topic_facet |
permafrost Arctic deep learning tundra ice-wedge polygon Mask R-CNN Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95 |
description |
We developed a high-throughput mapping workflow, which centers on deep learning (DL) convolutional neural network (CNN) algorithms on high-performance distributed computing resources, to automatically characterize ice-wedge polygons (IWPs) from sub-meter resolution commercial satellite imagery. We applied a region-based CNN object instance segmentation algorithm, namely the Mask R-CNN, to automatically detect and classify IWPs in North Slope of Alaska. The central goal of our study was to systematically expound the DLCNN model interoperability across varying tundra types (sedge, tussock sedge, and non-tussock sedge) and image scene complexities to refine the understanding of opportunities and challenges for regional-scale mapping applications. We corroborated quantitative error statistics along with detailed visual inspections to gauge the IWP detection accuracies. We found promising model performances (detection accuracies: 89% to 96% and classification accuracies: 94% to 97%) for all candidate image scenes with varying tundra types. The mapping workflow discerned the IWPs by exhibiting low absolute mean relative error (AMRE) values (0.17–0.23). Results further suggest the importance of increasing the variability of training samples when practicing transfer-learning strategy to map IWPs across heterogeneous tundra cover types. Overall, our findings demonstrate the robust performances of IWPs mapping workflow in multiple tundra landscapes. |
format |
Article in Journal/Newspaper |
author |
Md Abul Ehsan Bhuiyan Chandi Witharana Anna K. Liljedahl |
author_facet |
Md Abul Ehsan Bhuiyan Chandi Witharana Anna K. Liljedahl |
author_sort |
Md Abul Ehsan Bhuiyan |
title |
Use of Very High Spatial Resolution Commercial Satellite Imagery and Deep Learning to Automatically Map Ice-Wedge Polygons across Tundra Vegetation Types |
title_short |
Use of Very High Spatial Resolution Commercial Satellite Imagery and Deep Learning to Automatically Map Ice-Wedge Polygons across Tundra Vegetation Types |
title_full |
Use of Very High Spatial Resolution Commercial Satellite Imagery and Deep Learning to Automatically Map Ice-Wedge Polygons across Tundra Vegetation Types |
title_fullStr |
Use of Very High Spatial Resolution Commercial Satellite Imagery and Deep Learning to Automatically Map Ice-Wedge Polygons across Tundra Vegetation Types |
title_full_unstemmed |
Use of Very High Spatial Resolution Commercial Satellite Imagery and Deep Learning to Automatically Map Ice-Wedge Polygons across Tundra Vegetation Types |
title_sort |
use of very high spatial resolution commercial satellite imagery and deep learning to automatically map ice-wedge polygons across tundra vegetation types |
publisher |
MDPI AG |
publishDate |
2020 |
url |
https://doi.org/10.3390/jimaging6120137 https://doaj.org/article/83668c1d94ca4a5f817210c046c01570 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Ice north slope permafrost Tundra wedge* Alaska |
genre_facet |
Arctic Ice north slope permafrost Tundra wedge* Alaska |
op_source |
Journal of Imaging, Vol 6, Iss 137, p 137 (2020) |
op_relation |
https://www.mdpi.com/2313-433X/6/12/137 https://doaj.org/toc/2313-433X doi:10.3390/jimaging6120137 2313-433X https://doaj.org/article/83668c1d94ca4a5f817210c046c01570 |
op_doi |
https://doi.org/10.3390/jimaging6120137 |
container_title |
Journal of Imaging |
container_volume |
6 |
container_issue |
12 |
container_start_page |
137 |
_version_ |
1766341072700571648 |