Authors / CoAuthors
Wilford, J. | de Caritat, P. | Wilford, J. | Basak, S.
Abstract
Major oxides provide valuable information about the composition, origin, and properties of rocks and regolith. Analysing major oxides contributes significantly to understanding the nature of geological materials and processes (i.e. physical and chemical weathering) – with potential applications in resource exploration, engineering, environmental assessments, agriculture, and other fields. Traditionally most measurements of oxide concentrations are obtained by laboratory assay, often using X-ray fluorescence, on rock or regolith samples. To expand beyond the point measurements of the geochemical data, we have used a machine learning approach to produce seamless national scale grids for each of the major oxides. This approach builds predictive models by learning relationships between the site measurements of an oxide concentration (sourced from Geoscience Australia’s OZCHEM database and selected sites from state survey databases) and a comprehensive library of covariates (features). These covariates include: terrain derivatives; climate surfaces; geological maps; gamma-ray radiometric, magnetic, and gravity grids; and satellite imagery. This approach is used to derive national predictions for 10 major oxide concentrations at the resolution of the covariates (nominally 80 m). The models include the oxides of silicon (SiO2), aluminium (Al2O3), iron (Fe2O3tot), calcium (CaO), magnesium (MgO), manganese (MnO), potassium (K2O), sodium (Na2O), titanium (TiO2), and phosphorus (P2O5). The grids of oxide concentrations provided include the median of multiple models run as the prediction, and lower and upper (5th and 95th) percentiles as measures of the prediction’s uncertainty. Higher uncertainties correlate with greater spreads of model values. Differences in the features used in the model compared with the full feature space covering the entire continent are captured in the ‘covariate shift’ map. High values in the shift model can indicate higher potential uncertainty or unreliability of the model prediction. Users therefore need to be mindful, when interpreting this dataset, of the uncertainties shown by the 5th-95th percentiles, and high values in the covariate shift map. Details of the modelling approach, model uncertainties and datasets are describe in an attached word document “Model approach uncertainties”. This work is part of Geoscience Australia’s Exploring for the Future program that provides precompetitive information to inform decision-making by government, community and industry on the sustainable development of Australia's mineral, energy and groundwater resources. By gathering, analysing and interpreting new and existing precompetitive geoscience data and knowledge, we are building a national picture of Australia’s geology and resource potential. This leads to a strong economy, resilient society and sustainable environment for the benefit of all Australians. This includes supporting Australia’s transition to net zero emissions, strong, sustainable resources and agriculture sectors, and economic opportunities and social benefits for Australia’s regional and remote communities. The Exploring for the Future program, which commenced in 2016, is an eight year, $225m investment by the Australian Government. These data are published with the permission of the CEO, Geoscience Australia.
Product Type
dataset
eCat Id
148587
Contact for the resource
Resource provider
Point of contact
Cnr Jerrabomberra Ave and Hindmarsh Dr GPO Box 378
Canberra
ACT
2601
Australia
Point of contact
- Contact instructions
- MEG
Digital Object Identifier
Keywords
- ( Project )
-
- modelling
- ( Project )
-
- machine learning
- ( Project )
-
- geochemistry
- ( Project )
-
- predictive mapping
- ( Project )
-
- Australia’s Resources Framework
- ( Project )
-
- EFTF – Exploring for the Future
-
- rocks
-
- regolith
- theme.ANZRC Fields of Research.rdf
-
- Exploration geochemistrySoil chemistry and soil carbon sequestration (excl. carbon sequestration science)
-
- Published_External
Publication Date
2023-08-15T03:42:22
Creation Date
2023-06-27T16:00:00
Security Constraints
Legal Constraints
Status
Purpose
Improve our understanding of the surface geochemistry of rock and regolith for the Australian continent. These maps of oxide concentration have broad applications in mineral exploration, natural resource management, and in understanding geological systems and weathering processes.
Maintenance Information
notPlanned
Topic Category
geoscientificInformation
Series Information
Lineage
<div>The major oxide grids are derived from a covariate machine learning approach that establishes predictive correlations between site measurements of oxide concentration in exposed rock and surface soil/sediment with a suite of environmental and geological covariates or proxies (in machine learning they are also called features). Site concentrations of the major oxides have been extracted from;</div><div> </div><div>Geoscience Australia’s OZCHEM database (https://ecat.ga.gov.au/geonetwork/srv/api/records/a05f7892-d0ec-7506-e044-00144fdd4fa6)</div><div> </div><div>Western Australian geochemical database (https://www.dmp.wa.gov.au/GeoChem-Extract-Geochemistry-1559.aspx)</div><div> </div><div>NSW -https://minview.geoscience.nsw.gov.au/#/?lon=148.5&lat=-32.5&z=7&l=</div><div> </div><div>NT - https://geoscience.nt.gov.au/gemis/ntgsjspui/handle/1/81743</div><div> </div><div>QLD-https://www.business.qld.gov.au/industries/mining-energy-water/resources/geoscience-information/maps-datasets/digital-data/exploration-geochemistry</div><div> </div><div>SA - https://map.sarig.sa.gov.au/</div><div> </div><div>The environmental/geological covariates include: terrain attributes; gamma radiometric; satellite imagery (barest earth: Wilford and Roberts, 2020); gravity and magnetic derivatives; geological units (1:1 million surface geology map); and climate surfaces. The gradient boosted LightGBM machine-learning algorithm embedded into GA Uncover-ML (Wilford et al. 2020) workflow is used to generate the prediction model. All prediction grids display concentrations in log base 10 scale.</div><div><br></div><div><br></div><div>Wilford J., et al., 2020. Uncover-ML: a machine-learning pipeline for geoscience data analysis. In: Czarnota K., et al. (eds.), <em>Exploring for the Future: extended abstracts</em>, Geoscience Australia, Canberra, 1–4</div><div> </div><div>Wilford J. & Roberts D., 2020. Enhanced bare earth Landsat imagery for soil and lithological modelling. In: Czarnota K., et al. (eds.), Exploring for the Future: extended abstracts, Geoscience Australia, Canberra, http://dx.doi.org/10.11636/134472</div><div><br></div>
Parent Information
Extents
[-44, -9, 112, 154]
Reference System
GDA94 / geographic 2D (EPSG: 4283)
Spatial Resolution
Service Information
Associations
Downloads and Links
Download Silicon oxide (SiO2) Geotiff grids (zip) [10.8 GB]
Download Aluminium oxide (Al2O3) Geotiff grids (zip) [11.5 GB]
Download Iron oxide (Fe2O3tot) Geotiff grids (zip) [11.9 GB]
Download Calcium oxide (CaO) Geotiff grids (zip) [12.0 GB]
Download Manganese oxide (MnO) Geotiff grids (zip) [11.4 GB]
Download Magnesium oxide (MgO) Geotiff grids (zip) [12.0 GB]
Download Potassium oxide (K2O) Geotiff grids (zip) [12.1 GB]
Download Sodium oxide (Na2O) Geotiff grids (zip) [12.0 GB]
Download Titanium oxide (TiO2) Geotiff grids (zip) [11.9 GB]
Download Phosphorus oxide (P2O5) Geotiff grids (zip) [11.4 GB]
Download National oxide covariate shift (tif) [3.2 GB]
Source Information