eCite Digital Repository

Geological mapping in Western Tasmania using radar and random forests


Radford, DDC and Cracknell, MJ and Roach, MJ and Cumming, GV, Geological mapping in Western Tasmania using radar and random forests, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11, (9) pp. 3075-3087. ISSN 1939-1404 (2018) [Refereed Article]

Copyright Statement

© 2018 IEEE

DOI: doi:10.1109/JSTARS.2018.2855207


Mineral exploration and geological mapping of highly prospective areas in western Tasmania, southern Australia, is challenging due to steep topography, dense vegetation, and limited outcrop. Synthetic aperture radar (SAR) can potentially penetrate vegetation canopies and assist geological mapping in this environment. This study applies manual and automated lithological classification methods to airborne polarimetric TopSAR and geophysical data in the Heazlewood region, western Tasmania. Major discrepancies between classification results and the existing geological map generated fieldwork targets that led to the discovery of previously unmapped rock units. Manual analysis of radar image texture was essential for the identification of lithological boundaries. Automated pixel-based classification of radar data using Random Forests achieved poor results despite the inclusion of textural information derived from gray level co-occurrence matrices. This is because the majority of manually identified features within the radar imagery result from geobotanical and geomorphological relationships, rather than direct imaging of surficial lithological variations. Inconsistent relationships between geology and vegetation or geology and topography limit the reliability of TopSAR interpretations for geological mapping in this environment. However, Random Forest classifications, based on geophysical data and validated against manual interpretations, were accurate (∼90%) even when using limited training data (∼0.15% of total data). These classifications identified a previously unmapped region of mafic–ultramafic rocks, the presence of which was verified through fieldwork. This study validates the application of machine learning for geological mapping in remote and inaccessible localities but also highlights the limitations of SAR data in thickly vegetated terrain.

Item Details

Item Type:Refereed Article
Keywords:airborne geophysics, AirSAR, geological mapping, gray-level co-occurrence matrices (GLCM), Python, radar imaging, Random Forests, remote sensing, scikit-learn, supervised machine learning, synthetic aperture radar (SAR), Tasmania, texture, TopSAR
Research Division:Earth Sciences
Research Group:Geology
Research Field:Geology not elsewhere classified
Objective Division:Mineral Resources (Excl. Energy Resources)
Objective Group:Mineral exploration
Objective Field:Mineral exploration not elsewhere classified
UTAS Author:Cracknell, MJ (Dr Matthew Cracknell)
UTAS Author:Roach, MJ (Dr Michael Roach)
ID Code:128415
Year Published:2018
Web of Science® Times Cited:5
Deposited By:CODES ARC
Deposited On:2018-09-20
Last Modified:2019-03-08

Repository Staff Only: item control page