Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches
Precise coastal shoreline mapping is essential for monitoring changes in erosion rates, surface hydrology, and ecosystem structure and function. Monitoring water bodies in the Arctic National Wildlife Refuge (ANWR) is of high importance, especially considering the potential for oil and natural gas e...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs13224572 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/13/22/4572/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/13/22/4572/ 2023-08-20T04:03:57+02:00 Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches Bibek Aryal Stephen M. Escarzaga Sergio A. Vargas Zesati Miguel Velez-Reyes Olac Fuentes Craig Tweedie agris 2021-11-14 application/pdf https://doi.org/10.3390/rs13224572 EN eng Multidisciplinary Digital Publishing Institute Remote Sensing Image Processing https://dx.doi.org/10.3390/rs13224572 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 13; Issue 22; Pages: 4572 land water segmentation remote sensing deep learning sparse labels Text 2021 ftmdpi https://doi.org/10.3390/rs13224572 2023-08-01T03:14:52Z Precise coastal shoreline mapping is essential for monitoring changes in erosion rates, surface hydrology, and ecosystem structure and function. Monitoring water bodies in the Arctic National Wildlife Refuge (ANWR) is of high importance, especially considering the potential for oil and natural gas exploration in the region. In this work, we propose a modified variant of the Deep Neural Network based U-Net Architecture for the automated mapping of 4 Band Orthorectified NOAA Airborne Imagery using sparsely labeled training data and compare it to the performance of traditional Machine Learning (ML) based approaches—namely, random forest, xgboost—and spectral water indices—Normalized Difference Water Index (NDWI), and Normalized Difference Surface Water Index (NDSWI)—to support shoreline mapping of Arctic coastlines. We conclude that it is possible to modify the U-Net model to accept sparse labels as input and the results are comparable to other ML methods (an Intersection-over-Union (IoU) of 94.86% using U-Net vs. an IoU of 95.05% using the best performing method). Text Arctic MDPI Open Access Publishing Arctic Remote Sensing 13 22 4572 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
land water segmentation remote sensing deep learning sparse labels |
spellingShingle |
land water segmentation remote sensing deep learning sparse labels Bibek Aryal Stephen M. Escarzaga Sergio A. Vargas Zesati Miguel Velez-Reyes Olac Fuentes Craig Tweedie Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches |
topic_facet |
land water segmentation remote sensing deep learning sparse labels |
description |
Precise coastal shoreline mapping is essential for monitoring changes in erosion rates, surface hydrology, and ecosystem structure and function. Monitoring water bodies in the Arctic National Wildlife Refuge (ANWR) is of high importance, especially considering the potential for oil and natural gas exploration in the region. In this work, we propose a modified variant of the Deep Neural Network based U-Net Architecture for the automated mapping of 4 Band Orthorectified NOAA Airborne Imagery using sparsely labeled training data and compare it to the performance of traditional Machine Learning (ML) based approaches—namely, random forest, xgboost—and spectral water indices—Normalized Difference Water Index (NDWI), and Normalized Difference Surface Water Index (NDSWI)—to support shoreline mapping of Arctic coastlines. We conclude that it is possible to modify the U-Net model to accept sparse labels as input and the results are comparable to other ML methods (an Intersection-over-Union (IoU) of 94.86% using U-Net vs. an IoU of 95.05% using the best performing method). |
format |
Text |
author |
Bibek Aryal Stephen M. Escarzaga Sergio A. Vargas Zesati Miguel Velez-Reyes Olac Fuentes Craig Tweedie |
author_facet |
Bibek Aryal Stephen M. Escarzaga Sergio A. Vargas Zesati Miguel Velez-Reyes Olac Fuentes Craig Tweedie |
author_sort |
Bibek Aryal |
title |
Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches |
title_short |
Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches |
title_full |
Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches |
title_fullStr |
Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches |
title_full_unstemmed |
Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches |
title_sort |
semi-automated semantic segmentation of arctic shorelines using very high-resolution airborne imagery, spectral indices and weakly supervised machine learning approaches |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2021 |
url |
https://doi.org/10.3390/rs13224572 |
op_coverage |
agris |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
Remote Sensing; Volume 13; Issue 22; Pages: 4572 |
op_relation |
Remote Sensing Image Processing https://dx.doi.org/10.3390/rs13224572 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs13224572 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
22 |
container_start_page |
4572 |
_version_ |
1774714391800840192 |