The performance of random forests in an operational setting for large area sclerophyll forest classification

Mellor, Andrew, Haywood, Andrew, Stone, Christine and Jones, Simon (2013) The performance of random forests in an operational setting for large area sclerophyll forest classification. Remote Sensing, 5 6: 2838-2856. doi:10.3390/rs5062838

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Mellor, Andrew
Haywood, Andrew
Stone, Christine
Jones, Simon
Title The performance of random forests in an operational setting for large area sclerophyll forest classification
Journal name Remote Sensing   Check publisher's open access policy
ISSN 2072-4292
Publication date 2013-06
Year available 2013
Sub-type Article (original research)
DOI 10.3390/rs5062838
Open Access Status DOI
Volume 5
Issue 6
Start page 2838
End page 2856
Total pages 19
Place of publication Postfach, Basel, Switzerland
Publisher M D P I AG
Collection year 2014
Language eng
Abstract Mapping and monitoring forest extent is a common requirement of regional forest inventories and public land natural resource management, including in Australia. The state of Victoria, Australia, has approximately 7.2 million hectares of mostly forested public land, comprising ecosystems that present a diverse range of forest structures, composition and condition. In this paper, we evaluate the performance of the Random Forest (RF) classifier, an ensemble learning algorithm that has recently shown promise using multi-spectral satellite sensor imagery for large area feature classification. The RF algorithm was applied using selected Landsat Thematic Mapper (TM) imagery metrics and auxiliary terrain and climatic variables, while the reference data was manually extracted from systematically distributed plots of sample aerial photography and used for training (75%) and accuracy (25%) assessment. The RF algorithm yielded an overall accuracy of 96% and a Kappa statistic of 0.91 (confidence interval (CI) 0.909–0.919) for the forest/non-forest classification model, given a Kappa maximised binary threshold value of 0.5. The area under the receiver operating characteristic plot produced a score of 0.91, also indicating high model performance. The framework described in this study contributes to the operational deployment of a robust, but affordable, program, able to collate and process large volumes of multi-sourced data using open-source software for the production of consistent and accurate forest cover maps across the full spectrum of Victorian sclerophyll forest types.
Keyword Large area monitoring
Forest extent
Random forests
Landsat TM
Q-Index Code C1
Q-Index Status Confirmed Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: School of Geography, Planning and Environmental Management Publications
Official 2014 Collection
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 22 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 23 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Sun, 11 Aug 2013, 00:10:50 EST by System User on behalf of School of Geography, Planning & Env Management