Matthew Cracknell

Dr. Matthew Cracknell

orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2014 in Computers & Geosciences
Verified
Journal Article
Open access
MCMatthew Cracknell
Matthew Cracknell
ARAnya M. Reading
Anya M. Reading
Machine learning algorithms (MLAs) are a powerful group of data-driven inference tools that offer an automated means of recognizing patterns in high-dimensional data. Hence, there is much scope for the application of MLAs to the rapidly increasing volumes of remotely sensed geophysical data for geological mapping problems. We carry out a rigorous comparison of five MLAs: Naive Bayes, k-Nearest Neighbors, Random Forests, Support Vector Machines, and Artificial Neural Networks, in the context of a supervised lithology classification task using widely available and spatially constrained remotely sensed geophysical data. We make a further comparison of MLAs based on their sensitivity to variations in the degree of spatial clustering of training data, and their response to the inclusion of explicit spatial information (spatial coordinates). Our work identifies Random Forests as a good first choice algorithm for the supervised classification of lithology using remotely sensed geophysical data. Random Forests is straightforward to train, computationally efficient, highly stable with respect to variations in classification model parameter values, and as accurate as, or substantially more accurate than the other MLAs trialed. The results of our study indicate that as training data becomes increasingly dispersed across the region under investigation, MLA predictive accuracy improves dramatically. The use of explicit spatial information generates accurate lithology predictions but should be used in conjunction with geophysical data in order to generate geologically plausible predictions. MLAs, such as Random Forests, are valuable tools for generating reliable first-pass predictions for practical geological mapping applications that combine widely available geophysical data

31 May 2018 in Geophysics
Verified
Journal Article
Open access
SKStephen Kuhn
Stephen Kuhn
MCMatthew Cracknell
Matthew Cracknell
ARAnya M. Reading
Anya M. Reading
The Eastern Goldfields of Western Australia is one of the world’s premier gold-producing regions; however, large areas of prospective bedrock are under cover and lack detailed lithologic mapping. Away from the near-mine environment, exploration for new gold prospects requires mapping geology using the limited data available with robust estimates of uncertainty. We used the machine learning algorithm Random Forests (RF) to classify the lithology of an underexplored area adjacent to the historically significant Junction gold mine, using geophysical and remote-sensing data, with no geochemical sampling available at this reconnaissance stage. Using a sparse training sample, 1.6% of the total ground area, we produce a refined lithologic map. The classification is stable, despite including parts of the study area with later intrusions and variable cover depth, and it preserves the stratigraphic units defined in the training data. We assess the uncertainty associated with this new RF classification using information entropy, identifying those areas of the refined map that are most likely to be incorrectly classified. We find that information entropy correlates well with inaccuracy, providing a mechanism for explorers to direct future expenditure toward areas most likely to be incorrectly mapped or geologically complex. We conclude that the method can be an effective additional tool available to geoscientists in a greenfield, orogenic gold setting when confronted with limited data. We determine that the method could be used either to substantially improve an existing map, or produce a new map, taking sparse observations as a starting point. It can be implemented in similar situations (with limited outcrop information and no geochemical data) as an objective, data-driven alternative to conventional interpretation with the additional value of quantifying uncertainty.

1 May 2013 in Geophysics
Verified
Journal Article
Closed access
MCMatthew Cracknell
Matthew Cracknell
ARAnya M. Reading
Anya M. Reading
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.

26 November 2013 in Australian Journal of Earth Sciences
Verified
Journal Article
Closed access
MCMatthew Cracknell
Matthew Cracknell
ARA. M. Reading
A. M. Reading
AMA. W. McNeill
A. W. McNeill
The Hellyer–Mt Charter region of western Tasmania includes three known and economically significant volcanic-hosted massive sulfide (VHMS) deposits. Thick vegetation and poor outcrop present a considerable challenge to ongoing detailed geological field mapping in this area. Numerous geophysical and soil geochemical datasets covering the Hellyer–Mt Charter region have been collected in recent years. These data provide a rich source of geological information that can assist in defining the spatial distribution of lithologies. The integration and analysis of many layers of data in order to derive meaningful geological interpretations is a non-trivial task; however, machine learning algorithms such as Random Forests and Self-Organising Maps offer geologists methods for indentifying patterns in high-dimensional (many layered) data. In this study, we validate an interpreted geological map of the Hellyer–Mt Charter region by employing Random Forests™ to classify geophysical and geochemical data into 21 discrete lithological units. Our comparison of Random Forests supervised classification predictions to the interpreted geological map highlights the efficacy of this algorithm to map complex geological terranes. Furthermore, Random Forests identifies new geological details regarding the spatial distributions of key lithologies within the economically important Que-Hellyer Volcanics (QHV). We then infer distinct but spatially contiguous sub-classes within footwall and hangingwall, basalts and andesites of the QHV using Self-Organising Maps, an unsupervised clustering algorithm. Insight into compositional variability within volcanic units is gained by visualising the spatial distributions of sub-classes and associated statistical distributions of key geochemical data. Compositional differences in volcanic units are interpreted to reflect contrasting primary composition and VHMS alteration styles. We conclude that combining supervised and unsupervised machine-learning algorithms provides a widely applicable, robust means, of analysing complex and disparate data for machine-assisted geological mapping in challenging terranes.

1 June 2021 in Ore Geology Reviews
Verified
Journal Article
Closed access
RZRichen Zhong
Richen Zhong
YDYi Deng
Yi Deng
WLWenbo Li
Wenbo Li
LDLeonid V. Danyushevsky
Leonid V. Danyushevsky
MCMatthew Cracknell
Matthew Cracknell
LLLamei Li
Lamei Li

27 July 2018 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Closed access
DRDeclan D. G. Radford
Declan D. G. Radford
MCMatthew Cracknell
Matthew Cracknell
MRMichael J. Roach
Michael J. Roach
GCGrace V. Cumming
Grace V. Cumming
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.