View in EDS

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

Saved in:
Bibliographic Details
Title: Artificial Neural Network Modeling of High Arctic Phytomass Using Synthetic Aperture Radar and Multispectral Data
Authors: Collingwood, Adam (Author), Treitz, Paul (Author), Charbonneau, Francois (Author), Atkinson, David M. (Author)
Source: Remote Sensing, Vol 6, Iss 3, Pp 2134-2153 (2014)
Remote Sensing
Volume 6
Issue 3
Pages: 2134-2153
Publisher Information: Ryerson University Library and Archives, 2014.
Publication Year: 2014
Subject Terms: Vegetation mapping -- Arctic regions -- Computer simulation, Science, 0211 other engineering and technologies, Synthetic aperture radar, 02 engineering and technology, 15. Life on land, 01 natural sciences, Multispectral imaging, Neural networks (Computer science), Arctic, 13. Climate action, phytomass, artificial neural network, synthetic aperture radar, 0105 earth and related environmental sciences
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.
Document Type: Article
Other literature type
File Description: application/pdf
ISSN: 2072-4292
DOI: 10.32920/14637897.v1
DOI: 10.32920/14637897
DOI: 10.3390/rs6032134
Access URL: https://www.mdpi.com/2072-4292/6/3/2134/pdf
https://doaj.org/article/8d815ee7aa9b44f59280d2b6fca7b702
https://dblp.uni-trier.de/db/journals/remotesensing/remotesensing6.html#CollingwoodTCA14
https://core.ac.uk/display/26410403
https://www.mdpi.com/2072-4292/6/3/2134/pdf
https://doi.org/10.3390/rs6032134
https://www.mdpi.com/2072-4292/6/3/2134/htm
Rights: CC BY
Accession Number: edsair.doi.dedup.....ef0b4e6ffb45d26f18caab2f309c2e39
Database: OpenAIRE
Description
Abstract: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.
ISSN:20724292
DOI:10.32920/14637897.v1