Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks
Land cover datasets are essential for modeling and analysis of Arctic ecosystem structure and function and for understanding land–atmosphere interactions at high spatial resolutions. However, most Arctic land cover products are generated at a coarse resolution, often limited due to cloud cover, pola...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2019
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs11010069 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/11/1/69/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/11/1/69/ 2023-08-20T04:03:48+02:00 Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks Zachary L. Langford Jitendra Kumar Forrest M. Hoffman Amy L. Breen Colleen M. Iversen agris 2019-01-02 application/pdf https://doi.org/10.3390/rs11010069 EN eng Multidisciplinary Digital Publishing Institute https://dx.doi.org/10.3390/rs11010069 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 11; Issue 1; Pages: 69 hyperspectral field-scale mapping arctic vegetation classification convolutional neural network Text 2019 ftmdpi https://doi.org/10.3390/rs11010069 2023-07-31T21:56:33Z Land cover datasets are essential for modeling and analysis of Arctic ecosystem structure and function and for understanding land–atmosphere interactions at high spatial resolutions. However, most Arctic land cover products are generated at a coarse resolution, often limited due to cloud cover, polar darkness, and poor availability of high-resolution imagery. A multi-sensor remote sensing-based deep learning approach was developed for generating high-resolution (5 m) vegetation maps for the western Alaskan Arctic on the Seward Peninsula, Alaska. The fusion of hyperspectral, multispectral, and terrain datasets was performed using unsupervised and supervised classification techniques over a ∼343 km2 area, and a high-resolution (5 m) vegetation classification map was generated. An unsupervised technique was developed to classify high-dimensional remote sensing datasets into cohesive clusters. We employed a quantitative method to add supervision to the unlabeled clusters, producing a fully labeled vegetation map. We then developed convolutional neural networks (CNNs) using the multi-sensor fusion datasets to map vegetation distributions using the original classes and the classes produced by the unsupervised classification method. To validate the resulting CNN maps, vegetation observations were collected at 30 field plots during the summer of 2016, and the resulting vegetation products developed were evaluated against them for accuracy. Our analysis indicates the CNN models based on the labels produced by the unsupervised classification method provided the most accurate mapping of vegetation types, increasing the validation score (i.e., precision) from 0.53 to 0.83 when evaluated against field vegetation observations. Text Arctic Seward Peninsula Alaska MDPI Open Access Publishing Arctic Remote Sensing 11 1 69 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
hyperspectral field-scale mapping arctic vegetation classification convolutional neural network |
spellingShingle |
hyperspectral field-scale mapping arctic vegetation classification convolutional neural network Zachary L. Langford Jitendra Kumar Forrest M. Hoffman Amy L. Breen Colleen M. Iversen Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks |
topic_facet |
hyperspectral field-scale mapping arctic vegetation classification convolutional neural network |
description |
Land cover datasets are essential for modeling and analysis of Arctic ecosystem structure and function and for understanding land–atmosphere interactions at high spatial resolutions. However, most Arctic land cover products are generated at a coarse resolution, often limited due to cloud cover, polar darkness, and poor availability of high-resolution imagery. A multi-sensor remote sensing-based deep learning approach was developed for generating high-resolution (5 m) vegetation maps for the western Alaskan Arctic on the Seward Peninsula, Alaska. The fusion of hyperspectral, multispectral, and terrain datasets was performed using unsupervised and supervised classification techniques over a ∼343 km2 area, and a high-resolution (5 m) vegetation classification map was generated. An unsupervised technique was developed to classify high-dimensional remote sensing datasets into cohesive clusters. We employed a quantitative method to add supervision to the unlabeled clusters, producing a fully labeled vegetation map. We then developed convolutional neural networks (CNNs) using the multi-sensor fusion datasets to map vegetation distributions using the original classes and the classes produced by the unsupervised classification method. To validate the resulting CNN maps, vegetation observations were collected at 30 field plots during the summer of 2016, and the resulting vegetation products developed were evaluated against them for accuracy. Our analysis indicates the CNN models based on the labels produced by the unsupervised classification method provided the most accurate mapping of vegetation types, increasing the validation score (i.e., precision) from 0.53 to 0.83 when evaluated against field vegetation observations. |
format |
Text |
author |
Zachary L. Langford Jitendra Kumar Forrest M. Hoffman Amy L. Breen Colleen M. Iversen |
author_facet |
Zachary L. Langford Jitendra Kumar Forrest M. Hoffman Amy L. Breen Colleen M. Iversen |
author_sort |
Zachary L. Langford |
title |
Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks |
title_short |
Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks |
title_full |
Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks |
title_fullStr |
Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks |
title_full_unstemmed |
Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks |
title_sort |
arctic vegetation mapping using unsupervised training datasets and convolutional neural networks |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2019 |
url |
https://doi.org/10.3390/rs11010069 |
op_coverage |
agris |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Seward Peninsula Alaska |
genre_facet |
Arctic Seward Peninsula Alaska |
op_source |
Remote Sensing; Volume 11; Issue 1; Pages: 69 |
op_relation |
https://dx.doi.org/10.3390/rs11010069 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs11010069 |
container_title |
Remote Sensing |
container_volume |
11 |
container_issue |
1 |
container_start_page |
69 |
_version_ |
1774714225909825536 |