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 c...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/11/1/69 |
| _version_ | 1798018482970820608 |
|---|---|
| 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 |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-04-11T16:23:35Z |
| format | Article |
| id | doaj.art-a12523a44bda470ebdd6dd8c00086698 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T16:23:35Z |
| publishDate | 2019-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a12523a44bda470ebdd6dd8c000866982022-12-22T04:14:14ZengMDPI AGRemote Sensing2072-42922019-01-011116910.3390/rs11010069rs11010069Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural NetworksZachary L. Langford0Jitendra Kumar1Forrest M. Hoffman2Amy L. Breen3Colleen M. Iversen4Bredesen Center for Interdisciplinary Research and Graduate Education, University of Tennessee, Knoxville, TN 37996, USABredesen Center for Interdisciplinary Research and Graduate Education, University of Tennessee, Knoxville, TN 37996, USAComputational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USAInternational Arctic Research Center, University of Alaska, Fairbanks, AK 99775, USABredesen Center for Interdisciplinary Research and Graduate Education, University of Tennessee, Knoxville, TN 37996, USALand 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.http://www.mdpi.com/2072-4292/11/1/69hyperspectralfield-scale mappingarcticvegetation classificationconvolutional neural network |
| spellingShingle | 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 Remote Sensing hyperspectral field-scale mapping arctic vegetation classification convolutional neural network |
| title | 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_short | Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks |
| title_sort | arctic vegetation mapping using unsupervised training datasets and convolutional neural networks |
| topic | hyperspectral field-scale mapping arctic vegetation classification convolutional neural network |
| url | http://www.mdpi.com/2072-4292/11/1/69 |
| work_keys_str_mv | AT zacharyllangford arcticvegetationmappingusingunsupervisedtrainingdatasetsandconvolutionalneuralnetworks AT jitendrakumar arcticvegetationmappingusingunsupervisedtrainingdatasetsandconvolutionalneuralnetworks AT forrestmhoffman arcticvegetationmappingusingunsupervisedtrainingdatasetsandconvolutionalneuralnetworks AT amylbreen arcticvegetationmappingusingunsupervisedtrainingdatasetsandconvolutionalneuralnetworks AT colleenmiversen arcticvegetationmappingusingunsupervisedtrainingdatasetsandconvolutionalneuralnetworks |