eCite Digital Repository

Object-based random forest classification of Landsat ETM+ and WorldView-2 satellite imagery for mapping lowland native grassland communities in Tasmania, Australia

Citation

Melville, B and Lucieer, A and Aryal, J, Object-based random forest classification of Landsat ETM+ and WorldView-2 satellite imagery for mapping lowland native grassland communities in Tasmania, Australia, International Journal of Applied Earth Observation and Geoinformation, 66 pp. 46-55. ISSN 1569-8432 (2018) [Refereed Article]

Copyright Statement

2017 Elsevier B.V. All rights reserved.

DOI: doi:10.1016/j.jag.2017.11.006

Abstract

This paper presents a random forest classification approach for identifying and mapping three types of lowland native grassland communities found in the Tasmanian Midlands region. Due to the high conservation priority assigned to these communities, there has been an increasing need to identify appropriate datasets that can be used to derive accurate and frequently updateable maps of community extent. Therefore, this paper proposes a method employing repeat classification and statistical significance testing as a means of identifying the most appropriate dataset for mapping these communities. Two datasets were acquired and analysed; a Landsat ETM+ scene, and a WorldView-2 scene, both from 2010. Training and validation data were randomly subset using a k-fold (k=50) approach from a pre-existing field dataset. Poa labillardierei, Themeda triandra and lowland native grassland complex communities were identified in addition to dry woodland and agriculture. For each subset of randomly allocated points, a random forest model was trained based on each dataset, and then used to classify the corresponding imagery. Validation was performed using the reciprocal points from the independent subset that had not been used to train the model. Final training and classification accuracies were reported as per class means for each satellite dataset. Analysis of Variance (ANOVA) was undertaken to determine whether classification accuracy differed between the two datasets, as well as between classifications. Results showed mean class accuracies between 54% and 87%. Class accuracy only differed significantly between datasets for the dry woodland and Themeda grassland classes, with the WorldView-2 dataset showing higher mean classification accuracies. The results of this study indicate that remote sensing is a viable method for the identification of lowland native grassland communities in the Tasmanian Midlands, and that repeat classification and statistical significant testing can be used to identify optimal datasets for vegetation community mapping.

Item Details

Item Type:Refereed Article
Keywords:native grasslands, random forest, k-fold cross-validation, object-based image analysis
Research Division:Engineering
Research Group:Geomatic Engineering
Research Field:Photogrammetry and Remote Sensing
Objective Division:Environment
Objective Group:Ecosystem Assessment and Management
Objective Field:Ecosystem Assessment and Management of Sparseland, Permanent Grassland and Arid Zone Environments
UTAS Author:Melville, B (Ms Bethany Melville)
UTAS Author:Lucieer, A (Professor Arko Lucieer)
UTAS Author:Aryal, J (Dr Jagannath Aryal)
ID Code:124563
Year Published:2018
Web of Science® Times Cited:8
Deposited By:Geography and Spatial Science
Deposited On:2018-02-27
Last Modified:2019-03-14
Downloads:0

Repository Staff Only: item control page