Assessing the Potential to Operationalize Shoreline Sensitivity Mapping: Classifying Multiple Wide Fine Quadrature Polarized RADARSAT-2 and Landsat 5 Scenes with a Single Random Forest Model

Remote Sens. 2015, 7(10), 13528-13563; doi:10.3390/rs71013528

Author

Sarah Banks ^1,* , Koreen Millard ²

, Jon Pasher ¹

, Murray Richardson ²

, Huili Wang ¹

 and Jason Duffe ¹

¹

Environment Canada, National Wildlife Research Centre, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, Canada

²

Department of Geography and Environmental Studies, Carleton University, 1125 Colonel By Drive Ottawa, ON K1S 5B6, Canada

^*

Author to whom correspondence should be addressed. 

Academic Editors: Magaly Koch and Prasad S. Thenkabail

Received: 10 September 2015 / Revised: 30 September 2015 / Accepted: 10 October 2015 / Published: 19 October 2015

View Full-Text   |     Download PDF [1283 KB, uploaded 19 October 2015]   |    

 Browse Figures

 

Abstract 

The Random Forest algorithm was used to classify 86 Wide Fine Quadrature Polarized RADARSAT-2 scenes, five Landsat 5 scenes, and a Digital Elevation Model covering an area approximately 81,000 km² in size, and representing the entirety of Dease Strait, Coronation Gulf and Bathurst Inlet, Nunavut. The focus of this research was to assess the potential to operationalize shoreline sensitivity mapping to inform oil spill response and contingency planning. The impact of varying the training sample size and reducing model data load were evaluated. Results showed that acceptable accuracies could be achieved with relatively few training samples, but that higher accuracies and greater probabilities of correct class assignment were observed with larger sample sizes. Additionally, the number of inputs to the model could be greatly reduced without impacting overall performance. Optimized models reached independent accuracies of 91% for seven land cover types, and classification probabilities between 0.77 and 0.98 (values for latter represent per-class averages generated from independent validation sites). Mixed results were observed when assessing the potential for remote predictive mapping by simulating transferability of the model to scenes without training data. View Full-Text

Keywords: RADARSAT-2;  Landsat 5;  classification;  Random Forest;  Arctic;  shorelines

▼ Figures

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

For further details log on website :
http://www.mdpi.com/2072-4292/7/10/13528