Artificial Neural Network Modeling of High Arctic Phytomass Using Synthetic Aperture Radar and Multispectral Data

Vegetation in the Arctic is often sparse, spatially heterogeneous, and difficult to model. Synthetic Aperture Radar (SAR) has shown some promise in above-ground phytomass estimation at sub-arctic latitudes, but the utility of this type of data is not known in the context of the unique environments o...

Full description

Bibliographic Details
Published in:Remote Sensing
Main Authors: Collingwood, Adam (Author), Treitz, Paul (Author), Charbonneau, Francois (Author), Atkinson, David M. (Author)
Format: Article in Journal/Newspaper
Language:English
Published: 2014
Subjects:
Online Access:https://doi.org/10.3390/rs6032134
https://digital.library.ryerson.ca/islandora/object/RULA%3A4529
id ftryersonuniv:oai:digital.library.ryerson.ca:RULA_4529
record_format openpolar
spelling ftryersonuniv:oai:digital.library.ryerson.ca:RULA_4529 2023-05-15T14:41:21+02:00 Artificial Neural Network Modeling of High Arctic Phytomass Using Synthetic Aperture Radar and Multispectral Data Collingwood, Adam (Author) Treitz, Paul (Author) Charbonneau, Francois (Author) Atkinson, David M. (Author) 2014-03-07 https://doi.org/10.3390/rs6032134 https://digital.library.ryerson.ca/islandora/object/RULA%3A4529 eng eng Creative Commons Attribution 4.0 International Public License; https://creativecommons.org/licenses/by/4.0/ CC-BY Vegetation mapping -- Arctic regions -- Computer simulation Synthetic aperture radar Multispectral imaging Neural networks (Computer science) Text article 2014 ftryersonuniv https://doi.org/10.3390/rs6032134 2020-07-17T13:01:09Z Vegetation in the Arctic is often sparse, spatially heterogeneous, and difficult to model. Synthetic Aperture Radar (SAR) has shown some promise in above-ground phytomass estimation at sub-arctic latitudes, but the utility of this type of data is not known in the context of the unique environments of the Canadian High Arctic. In this paper, Artificial Neural Networks (ANNs) were created to model the relationship between variables derived from high resolution multi-incidence angle RADARSAT-2 SAR data and optically-derived (GeoEye-1) Soil Adjusted Vegetation Index (SAVI) values. The modeled SAVI values (i.e., from SAR variables) were then used to create maps of above-ground phytomass across the study area. SAVI model results for individual ecological classes of polar semi-desert, mesic heath, wet sedge, and felsenmeer were reasonable, with r2 values of 0.43, 0.43, 0.30, and 0.59, respectively. When the outputs of these models were combined to analyze the relationship between the model output and SAVI as a group, the r2 value was 0.60, with an 8% normalized root mean square error (% of the total range of phytomass values), a positive indicator of a relationship. The above-ground phytomass model also resulted in a very strong relationship (r2 = 0.87) between SAR-modeled and field-measured phytomass. A positive relationship was also found between optically derived SAVI values and field measured phytomass (r2 = 0.79). These relationships demonstrate the utility of SAR data, compared to using optical data alone, for modeling above-ground phytomass in a high arctic environment possessing relatively low levels of vegetation. Collingwood, A., Treitz, P., Charbonneau, F., & Atkinson, D. M. (2014). Artificial neural network modeling of high arctic phytomass using synthetic aperture radar and multispectral data. Remote Sensing, 6(3), 2134-2153. doi:10.3390/rs6032134 Article in Journal/Newspaper Arctic Ryerson University: RULA Digital Repository Arctic Atkinson ENVELOPE(-85.483,-85.483,-78.650,-78.650) Remote Sensing 6 3 2134 2153
institution Open Polar
collection Ryerson University: RULA Digital Repository
op_collection_id ftryersonuniv
language English
topic Vegetation mapping -- Arctic regions -- Computer simulation
Synthetic aperture radar
Multispectral imaging
Neural networks (Computer science)
spellingShingle Vegetation mapping -- Arctic regions -- Computer simulation
Synthetic aperture radar
Multispectral imaging
Neural networks (Computer science)
Collingwood, Adam (Author)
Treitz, Paul (Author)
Charbonneau, Francois (Author)
Atkinson, David M. (Author)
Artificial Neural Network Modeling of High Arctic Phytomass Using Synthetic Aperture Radar and Multispectral Data
topic_facet Vegetation mapping -- Arctic regions -- Computer simulation
Synthetic aperture radar
Multispectral imaging
Neural networks (Computer science)
description Vegetation in the Arctic is often sparse, spatially heterogeneous, and difficult to model. Synthetic Aperture Radar (SAR) has shown some promise in above-ground phytomass estimation at sub-arctic latitudes, but the utility of this type of data is not known in the context of the unique environments of the Canadian High Arctic. In this paper, Artificial Neural Networks (ANNs) were created to model the relationship between variables derived from high resolution multi-incidence angle RADARSAT-2 SAR data and optically-derived (GeoEye-1) Soil Adjusted Vegetation Index (SAVI) values. The modeled SAVI values (i.e., from SAR variables) were then used to create maps of above-ground phytomass across the study area. SAVI model results for individual ecological classes of polar semi-desert, mesic heath, wet sedge, and felsenmeer were reasonable, with r2 values of 0.43, 0.43, 0.30, and 0.59, respectively. When the outputs of these models were combined to analyze the relationship between the model output and SAVI as a group, the r2 value was 0.60, with an 8% normalized root mean square error (% of the total range of phytomass values), a positive indicator of a relationship. The above-ground phytomass model also resulted in a very strong relationship (r2 = 0.87) between SAR-modeled and field-measured phytomass. A positive relationship was also found between optically derived SAVI values and field measured phytomass (r2 = 0.79). These relationships demonstrate the utility of SAR data, compared to using optical data alone, for modeling above-ground phytomass in a high arctic environment possessing relatively low levels of vegetation. Collingwood, A., Treitz, P., Charbonneau, F., & Atkinson, D. M. (2014). Artificial neural network modeling of high arctic phytomass using synthetic aperture radar and multispectral data. Remote Sensing, 6(3), 2134-2153. doi:10.3390/rs6032134
format Article in Journal/Newspaper
author Collingwood, Adam (Author)
Treitz, Paul (Author)
Charbonneau, Francois (Author)
Atkinson, David M. (Author)
author_facet Collingwood, Adam (Author)
Treitz, Paul (Author)
Charbonneau, Francois (Author)
Atkinson, David M. (Author)
author_sort Collingwood, Adam (Author)
title Artificial Neural Network Modeling of High Arctic Phytomass Using Synthetic Aperture Radar and Multispectral Data
title_short Artificial Neural Network Modeling of High Arctic Phytomass Using Synthetic Aperture Radar and Multispectral Data
title_full Artificial Neural Network Modeling of High Arctic Phytomass Using Synthetic Aperture Radar and Multispectral Data
title_fullStr Artificial Neural Network Modeling of High Arctic Phytomass Using Synthetic Aperture Radar and Multispectral Data
title_full_unstemmed Artificial Neural Network Modeling of High Arctic Phytomass Using Synthetic Aperture Radar and Multispectral Data
title_sort artificial neural network modeling of high arctic phytomass using synthetic aperture radar and multispectral data
publishDate 2014
url https://doi.org/10.3390/rs6032134
https://digital.library.ryerson.ca/islandora/object/RULA%3A4529
long_lat ENVELOPE(-85.483,-85.483,-78.650,-78.650)
geographic Arctic
Atkinson
geographic_facet Arctic
Atkinson
genre Arctic
genre_facet Arctic
op_rights Creative Commons Attribution 4.0 International Public License; https://creativecommons.org/licenses/by/4.0/
op_rightsnorm CC-BY
op_doi https://doi.org/10.3390/rs6032134
container_title Remote Sensing
container_volume 6
container_issue 3
container_start_page 2134
op_container_end_page 2153
_version_ 1766313136213721088