Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks
Abstract
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. Ourmore »
- Authors:
-
- Univ. of Tennessee, Knoxville, TN (United States). Bredesen Center for Interdisciplinary Research and Graduate Education; Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Environmental Sciences Division
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Computational Sciences and Engineering; Univ. of Tennessee, Knoxville, TN (United States). Dept. of Civil and Environmental Engineering
- Univ. of Alaska, Fairbanks, AK (United States). International Arctic Research Center
- Publication Date:
- Research Org.:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Biological and Environmental Research (BER)
- OSTI Identifier:
- 1489551
- Grant/Contract Number:
- AC05-00OR22725
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Remote Sensing
- Additional Journal Information:
- Journal Volume: 11; Journal Issue: 1; Journal ID: ISSN 2072-4292
- Publisher:
- MDPI
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 54 ENVIRONMENTAL SCIENCES; 97 MATHEMATICS AND COMPUTING; hyperspectral; field-scale mapping; arctic; vegetation classification; convolutional neural network
Citation Formats
Langford, Zachary, Kumar, Jitendra, Hoffman, Forrest, Breen, Amy, and Iversen, Colleen. Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks. United States: N. p., 2019.
Web. doi:10.3390/rs11010069.
Langford, Zachary, Kumar, Jitendra, Hoffman, Forrest, Breen, Amy, & Iversen, Colleen. Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks. United States. https://doi.org/10.3390/rs11010069
Langford, Zachary, Kumar, Jitendra, Hoffman, Forrest, Breen, Amy, and Iversen, Colleen. Wed .
"Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks". United States. https://doi.org/10.3390/rs11010069. https://www.osti.gov/servlets/purl/1489551.
@article{osti_1489551,
title = {Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks},
author = {Langford, Zachary and Kumar, Jitendra and Hoffman, Forrest and Breen, Amy and Iversen, Colleen},
abstractNote = {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.},
doi = {10.3390/rs11010069},
journal = {Remote Sensing},
number = 1,
volume = 11,
place = {United States},
year = {Wed Jan 02 00:00:00 EST 2019},
month = {Wed Jan 02 00:00:00 EST 2019}
}
Web of Science
Works referenced in this record:
Classification for High Resolution Remote Sensing Imagery Using a Fully Convolutional Network
journal, May 2017
- Fu, Gang; Liu, Changjun; Zhou, Rong
- Remote Sensing, Vol. 9, Issue 5
Road Segmentation of Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields
journal, July 2017
- Panboonyuen, Teerapong; Jitkajornwanich, Kulsawasd; Lawawirojwong, Siam
- Remote Sensing, Vol. 9, Issue 7
Mapping Arctic Tundra Vegetation Communities Using Field Spectroscopy and Multispectral Satellite Data in North Alaska, USA
journal, November 2016
- Davidson, Scott; Santos, Maria; Sloan, Victoria
- Remote Sensing, Vol. 8, Issue 12
Remote Sensing of 2000–2016 Alpine Spring Snowline Elevation in Dall Sheep Mountain Ranges of Alaska and Western Canada
journal, November 2017
- Verbyla, David; Hegel, Troy; Nolin, Anne
- Remote Sensing, Vol. 9, Issue 11
Lateglacial and Holocene climate, disturbance and permafrost peatland dynamics on the Seward Peninsula, western Alaska
journal, March 2013
- Hunt, Stephanie; Yu, Zicheng; Jones, Miriam
- Quaternary Science Reviews, Vol. 63
Parallel k-Means Clustering for Quantitative Ecoregion Delineation Using Large Data Sets
journal, January 2011
- Kumar, Jitendra; Mills, Richard T.; Hoffman, Forrest M.
- Procedia Computer Science, Vol. 4
Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions
journal, January 2011
- Halko, N.; Martinsson, P. G.; Tropp, J. A.
- SIAM Review, Vol. 53, Issue 2
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
Coupling a three-dimensional subsurface flow and transport model with a land surface model to simulate stream–aquifer–land interactions (CP v1.0)
journal, January 2017
- Bisht, Gautam; Huang, Maoyi; Zhou, Tian
- Geoscientific Model Development, Vol. 10, Issue 12
Vegetation and Permafrost Thaw Depth 10 Years after a Tundra Fire in 2002, Seward Peninsula, Alaska
journal, August 2015
- Narita, Kenji; Harada, Koichiro; Saito, Kazuyuki
- Arctic, Antarctic, and Alpine Research, Vol. 47, Issue 3
Mapping Arctic Plant Functional Type Distributions in the Barrow Environmental Observatory Using WorldView-2 and LiDAR Datasets
journal, September 2016
- Langford, Zachary; Kumar, Jitendra; Hoffman, Forrest
- Remote Sensing, Vol. 8, Issue 9
Textural–Spectral Feature-Based Species Classification of Mangroves in Mai Po Nature Reserve from Worldview-3 Imagery
journal, December 2015
- Wang, Ting; Zhang, Hongsheng; Lin, Hui
- Remote Sensing, Vol. 8, Issue 1
Summer Differences among Arctic Ecosystems in Regional Climate Forcing
journal, June 2000
- Chapin, F. Stuart; Eugster, Werner; McFadden, Joseph P.
- Journal of Climate, Vol. 13, Issue 12
Projections of Twenty-First-Century Climate Extremes for Alaska via Dynamical Downscaling and Quantile Mapping
journal, September 2017
- Lader, Rick; Walsh, John E.; Bhatt, Uma S.
- Journal of Applied Meteorology and Climatology, Vol. 56, Issue 9
Hyperspectral and Multispectral Image Fusion via Deep Two-Branches Convolutional Neural Network
journal, May 2018
- Yang, Jingxiang; Zhao, Yong-Qiang; Chan, Jonathan
- Remote Sensing, Vol. 10, Issue 5
The Alaska Arctic Vegetation Archive (AVA-AK)
journal, September 2016
- Walker, Donald A.; Breen, Amy L.; Druckenmiller, Lisa A.
- Phytocoenologia, Vol. 46, Issue 2
Differentiating among Four Arctic Tundra Plant Communities at Ivotuk, Alaska Using Field Spectroscopy
journal, January 2016
- Bratsch, Sara; Epstein, Howard; Buchhorn, Marcel
- Remote Sensing, Vol. 8, Issue 1
Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art
journal, June 2016
- Zhang, Liangpei; Zhang, Lefei; Du, Bo
- IEEE Geoscience and Remote Sensing Magazine, Vol. 4, Issue 2
Regional Quantitative Cover Mapping of Tundra Plant Functional Types in Arctic Alaska
journal, October 2017
- Macander, Matthew; Frost, Gerald; Nelson, Peter
- Remote Sensing, Vol. 9, Issue 10
Addressing numerical challenges in introducing a reactive transport code into a land surface model: a biogeochemical modeling proof-of-concept with CLM–PFLOTRAN 1.0
journal, January 2016
- Tang, Guoping; Yuan, Fengming; Bisht, Gautam
- Geoscientific Model Development, Vol. 9, Issue 3
Convolutional Neural Network Approach for Mapping Arctic Vegetation Using Multi-Sensor Remote Sensing Fusion
conference, November 2017
- Langford, Zachary L.; Kumar, Jitendra; Hoffman, Forrest M.
- 2017 IEEE International Conference on Data Mining Workshops (ICDMW)
Future Arctic climate changes: Adaptation and mitigation time scales
journal, February 2014
- Overland, James E.; Wang, Muyin; Walsh, John E.
- Earth's Future, Vol. 2, Issue 2
Shifts in Arctic vegetation and associated feedbacks under climate change
journal, March 2013
- Pearson, Richard G.; Phillips, Steven J.; Loranty, Michael M.
- Nature Climate Change, Vol. 3, Issue 7
Permafrost response to increasing Arctic shrub abundance depends on the relative influence of shrubs on local soil cooling versus large-scale climate warming
journal, October 2011
- Lawrence, David M.; Swenson, Sean C.
- Environmental Research Letters, Vol. 6, Issue 4
Plant community-level mapping of arctic Alaska based on the Circumpolar Arctic Vegetation Map [Plant community-level mapping of arctic Alaska based on the Circumpolar Arctic Vegetation Map]
journal, December 2005
- Raynolds, Martha K.; Walker, Donald A.; Maier, Hilmar A.
- Phytocoenologia, Vol. 35, Issue 4
Multisource Remote Sensing Data Classification Based on Convolutional Neural Network
journal, February 2018
- Xu, Xiaodong; Li, Wei; Ran, Qiong
- IEEE Transactions on Geoscience and Remote Sensing, Vol. 56, Issue 2
Estimating heterotrophic respiration at large scales: challenges, approaches, and next steps
journal, June 2016
- Bond‐Lamberty, Ben; Epron, Daniel; Harden, Jennifer
- Ecosphere, Vol. 7, Issue 6
Deep Fusion of Remote Sensing Data for Accurate Classification
journal, August 2017
- Chen, Yushi; Li, Chunyang; Ghamisi, Pedram
- IEEE Geoscience and Remote Sensing Letters, Vol. 14, Issue 8
Mapcurves: a quantitative method for comparing categorical maps
journal, May 2006
- Hargrove, William W.; Hoffman, Forrest M.; Hessburg, Paul F.
- Journal of Geographical Systems, Vol. 8, Issue 2
Hyperspectral Imagery Denoising by Deep Learning With Trainable Nonlinearity Function
journal, November 2017
- Xie, Weiying; Li, Yunsong
- IEEE Geoscience and Remote Sensing Letters, Vol. 14, Issue 11
Tundra shrubification and tree-line advance amplify arctic climate warming: results from an individual-based dynamic vegetation model
journal, August 2013
- Zhang, Wenxin; Miller, Paul A.; Smith, Benjamin
- Environmental Research Letters, Vol. 8, Issue 3
Land Cover Change on the Seward Peninsula: The Use of Remote Sensing to Evaluate the Potential Influences of Climate Warming on Historical Vegetation Dynamics
journal, October 2001
- Silapaswan, C. S.; Verbyla, D. L.; McGuire, A. D.
- Canadian Journal of Remote Sensing, Vol. 27, Issue 5
Remote Sensing-Based, 5-m, Vegetation Distributions, Kougarok Study Site, Seward Peninsula, Alaska, ca. 2009 - 2016
dataset, January 2019
- Langford, Zachary; Kumar, Jitendra; Hoffman, Forrest
- Next Generation Ecosystems Experiment - Arctic, Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (US); NGEE Arctic, Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Variability in the sensitivity among model simulations of permafrost and carbon dynamics in the permafrost region between 1960 and 2009: MODELING PERMAFROST CARBON DYNAMICS
journal, July 2016
- McGuire, A. David; Koven, Charles; Lawrence, David M.
- Global Biogeochemical Cycles, Vol. 30, Issue 7
Response of subarctic vegetation to transient climatic change on the Seward Peninsula in north-west Alaska
journal, June 2000
- Rupp, T. Scott; Chapin, F. Stuart; Starfield, Anthony M.
- Global Change Biology, Vol. 6, Issue 5
Deriving Snow Cover Metrics for Alaska from MODIS
journal, September 2015
- Lindsay, Chuck; Zhu, Jiang; Miller, Amy
- Remote Sensing, Vol. 7, Issue 10
Frequent Fires in Ancient Shrub Tundra: Implications of Paleorecords for Arctic Environmental Change
journal, March 2008
- Higuera, Philip E.; Brubaker, Linda B.; Anderson, Patricia M.
- PLoS ONE, Vol. 3, Issue 3
Training deep neural networks on imbalanced data sets
conference, July 2016
- Wang, Shoujin; Liu, Wei; Wu, Jia
- 2016 International Joint Conference on Neural Networks (IJCNN)
Data Fusion and Remote Sensing: An ever-growing relationship
journal, December 2016
- Schmitt, Michael; Zhu, Xiao Xiang
- IEEE Geoscience and Remote Sensing Magazine, Vol. 4, Issue 4
The Alaska Arctic Vegetation Archive (AVA-AK)
text, January 2016
- Jozef, Šibík,; E., Tweedie, Craig; Sandra, Villarreal,
- The University of North Carolina at Chapel Hill University Libraries
Works referencing / citing this record:
Alder Distribution and Expansion Across a Tundra Hillslope: Implications for Local N Cycling
journal, October 2019
- Salmon, Verity G.; Breen, Amy L.; Kumar, Jitendra
- Frontiers in Plant Science, Vol. 10