eCite Digital Repository
The upside of uncertainty: Identification of lithology contact zones from airborne geophysics and satellite data using random forests and support vector machines
Citation
Cracknell, MJ and Reading, AM, The upside of uncertainty: Identification of lithology contact zones from airborne geophysics and satellite data using random forests and support vector machines, Geophysics, 78, (3) pp. WB113-WB126. ISSN 0016-8033 (2013) [Refereed Article]
![]() | PDF Restricted - Request a copy 5Mb |
Copyright Statement
Copyright 2013 Society of Exploration Geophysicists
DOI: doi:10.1190/GEO2012-0411.1
Abstract
Inductive machine learning algorithms attempt to recognize patterns in, and generalize from empirical data. They provide a practical means of predicting lithology, or other spatially varying physical features, from multidimensional geophysical data sets. It is for this reason machine learning approaches are increasing in popularity for geophysical data inference. A key motivation for their use is the ease with which uncertainty measures can be estimated for nonprobabilistic algorithms. We have compared and evaluated the abilities of two nonprobabilistic machine learning algorithms, random forests (RF) and support vector machines (SVM), to recognize ambiguous supervised classification predictions using uncertainty calculated from estimates of class membership probabilities. We formulated a method to establish optimal uncertainty threshold values to identify and isolate the maximum number of incorrect predictions while preserving most of the correct classifications. This is illustrated using a case example of the supervised classification of surface lithologies in a folded, structurally complex, metamorphic terrain. We found that (1) the use of optimal uncertainty thresholds significantly improves overall classification accuracy of RF predictions, but not those of SVM, by eliminating the maximum number of incorrectly classified samples while preserving the maximum number of correctly classified samples; (2) RF, unlike SVM, was able to exploit dependencies and structures contained within spatially varying input data; and (3) high RF prediction uncertainty is spatially coincident with transitions in lithology and associated contact zones, and regions of intense deformation. Uncertainty has its upside in the identification of areas of key geologic interest and has wide application across the geosciences, where transition zones are important classes in their own right. The techniques used in this study are of practical value in prioritizing subsequent geologic field activities, which, with the aid of this analysis, may be focused on key lithology contacts and problematic localities.
Item Details
Item Type: | Refereed Article |
---|---|
Research Division: | Earth Sciences |
Research Group: | Geophysics |
Research Field: | Geophysics 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: | Reading, AM (Professor Anya Reading) |
ID Code: | 86638 |
Year Published: | 2013 |
Web of Science® Times Cited: | 60 |
Deposited By: | Centre for Ore Deposit Research - CODES CoE |
Deposited On: | 2013-10-07 |
Last Modified: | 2017-11-03 |
Downloads: | 1 View Download Statistics |
Repository Staff Only: item control page