Predictive grids of major oxide concentrations in surface rock and regolith over the Australian continent

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.

Identification info

Date (Creation): 2023-06-27T16:00:00

Date (Publication): 2023-08-15T03:42:22

Citation identifier: Geoscience Australia Persistent Identifier/https://pid.geoscience.gov.au/dataset/ga/148587

Citation identifier: Digital Object Identifier/https://dx.doi.org/10.26186/148587

Cited responsible party

Role	Organisation / Individual Name	Details
Publisher	Commonwealth of Australia (Geoscience Australia)	Voice
Author	Wilford, J.	Internal Contact
Author	de Caritat, P.	Internal Contact
Principal investigator	Wilford, J.	Internal Contact
Author	Basak, S.	Space Division Internal Contact

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.

Status

Point of contact

Role	Organisation / Individual Name	Details
Resource provider	Minerals, Energy and Groundwater Division	External Contact
Point of contact	Commonwealth of Australia (Geoscience Australia)	Voice
Point of contact	Main, P.	MEG Internal Contact

Spatial representation type

Topic category

Geoscientific information

Extent

Temporal extent

Time period: 2023-06-21 2023-06-22

Maintenance and update frequency: Not planned

Resource format

Title: Product data repository: Various Formats

Website: Data Store directory containing the digital product files

Data Store directory containing one or more files, possibly in a variety of formats, accessible to Geoscience Australia staff only for internal purposes

Project

modelling

Project

machine learning

Project

geochemistry

Project

predictive mapping

Project

Australia’s Resources Framework

Project

EFTF – Exploring for the Future

Keywords

rocks

Keywords

regolith

theme.ANZRC Fields of Research.rdf

Exploration geochemistry
Soil chemistry and soil carbon sequestration (excl. carbon sequestration science)

Keywords

Published_External

Resource constraints

Title: Creative Commons Attribution 4.0 International Licence

Alternate title: CC-BY

Edition: 4.0

Website

https://creativecommons.org/licenses/by/4.0/

Addressee

Role	Organisation / Individual Name	Details
User	Any

Use constraints: License

Use constraints: Other restrictions

Other constraints: © Commonwealth of Australia (Geoscience Australia) 2023

Resource constraints

Title: Australian Government Security Classification System

Edition date: 2018-11-01T00:00:00

Website

https://www.protectivesecurity.gov.au/Pages/default.aspx

Classification: Unclassified

Classification system: Australian Government Security Classification System

Associated resource

Association Type: Operated on by

Title: Machine Learning Models WMS

Citation identifier: 146039

Citation identifier: 958f3685-d7c8-4874-8601-8a4bfd84c676

Website

http://pid.geoscience.gov.au/service/ga/146039

Link to eCat metadata record landing page

Associated resource

Association Type: Operated on by

Title: Machine Learning Models WCS

Citation identifier: 146040

Citation identifier: 26cc9c00-dc16-4b6a-8c37-a624b17cb547

Website

http://pid.geoscience.gov.au/service/ga/146040

Link to eCat metadata record landing page

Language: English

Character encoding: UTF8

Distribution Information

Distributor contact

Role	Organisation / Individual Name	Details
Distributor	Commonwealth of Australia (Geoscience Australia)	Voice facsimile

OnLine resource: Download Silicon oxide (SiO2) Geotiff grids (zip) [10.8 GB]

Download Silicon oxide (SiO2) Geotiff grids (zip) [10.8 GB]

Distribution format

zip geotiff

File decompression technique

unzip

OnLine resource: Download Aluminium oxide (Al2O3) Geotiff grids (zip) [11.5 GB]

Download Aluminium oxide (Al2O3) Geotiff grids (zip) [11.5 GB]

Distribution format

zip

File decompression technique

unzip

OnLine resource: Download Iron oxide (Fe2O3tot) Geotiff grids (zip) [11.9 GB]

Download Iron oxide (Fe2O3tot) Geotiff grids (zip) [11.9 GB]

Distribution format

zip

File decompression technique

unzip

OnLine resource: Download Calcium oxide (CaO) Geotiff grids (zip) [12.0 GB]

Download Calcium oxide (CaO) Geotiff grids (zip) [12.0 GB]

Distribution format

zip

File decompression technique

unzip

OnLine resource: Download Manganese oxide (MnO) Geotiff grids (zip) [11.4 GB]

Download Manganese oxide (MnO) Geotiff grids (zip) [11.4 GB]

Distribution format

zip

File decompression technique

unzip

OnLine resource: Download Magnesium oxide (MgO) Geotiff grids (zip) [12.0 GB]

Download Magnesium oxide (MgO) Geotiff grids (zip) [12.0 GB]

Distribution format

zip

File decompression technique

unzip

OnLine resource: Download Potassium oxide (K2O) Geotiff grids (zip) [12.1 GB]

Download Potassium oxide (K2O) Geotiff grids (zip) [12.1 GB]

Distribution format

zip

File decompression technique

unzip

OnLine resource: Download Sodium oxide (Na2O) Geotiff grids (zip) [12.0 GB]

Download Sodium oxide (Na2O) Geotiff grids (zip) [12.0 GB]

Distribution format

zip

File decompression technique

unzip

OnLine resource: Download Titanium oxide (TiO2) Geotiff grids (zip) [11.9 GB]

Download Titanium oxide (TiO2) Geotiff grids (zip) [11.9 GB]

Distribution format

zip

File decompression technique

unzip

OnLine resource: Download Phosphorus oxide (P2O5) Geotiff grids (zip) [11.4 GB]

Download Phosphorus oxide (P2O5) Geotiff grids (zip) [11.4 GB]

Distribution format

zip

File decompression technique

unzip

OnLine resource: Download National oxide covariate shift (tif) [3.2 GB]

Download National oxide covariate shift (tif) [3.2 GB]

Distribution format

OnLine resource: Download Model approach uncertainties (docx) [669 KB]

Download Model approach uncertainties (docx) [669 KB]

Distribution format

docx

OnLine resource: Machine Learning Models WMS

Machine Learning Models WMS

Distribution format

OGC:WMS

OnLine resource: Machine Learning Models WCS

Machine Learning Models WCS

Distribution format

OGC:WCS

Resource lineage

Statement: <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>

Reference System Information

Reference system identifier: EPSG/GDA94 / geographic 2D (EPSG: 4283)

Metadata constraints

Title: Australian Government Security Classification System

Edition date: 2018-11-01T00:00:00

Website

https://www.protectivesecurity.gov.au/Pages/default.aspx

Classification: Unclassified

Metadata

Metadata identifier

urn:uuid/5ea9a9e9-6253-464f-8aed-0c19124ee910

Title: GeoNetwork UUID

Language: English

Character encoding: UTF8

Contact

Role	Organisation / Individual Name	Details
Point of contact	Commonwealth of Australia (Geoscience Australia)	Voice
Point of contact	Main, P.	MEG Internal Contact

Type of resource

Resource scope: Dataset

Alternative metadata reference

Title

Geoscience Australia - short identifier for metadata record with

uuid

Citation identifier: eCatId/148587

Metadata linkage

https://ecat.ga.gov.au/geonetwork/srv/eng/catalog.search#/metadata/5ea9a9e9-6253-464f-8aed-0c19124ee910

Date info (Creation): 2023-08-14T01:50:17

Date info (Revision): 2023-08-14T01:50:17

Metadata standard

Title: AU/NZS ISO 19115-1:2014

Metadata standard

Title: ISO 19115-1:2014

Metadata standard

Title: ISO 19115-3

Title: Geoscience Australia Community Metadata Profile of ISO 19115-1:2014

Edition: Version 2.0, September 2018

Citation identifier: http://pid.geoscience.gov.au/dataset/ga/122551

Spatial extent

Provided by

Access to the portal

Read here the full details and access to the data.

Associated resources

Not available

Simple

Identification info

Extent

Temporal extent

Resource format

Resource constraints

Resource constraints

Associated resource

Associated resource

Distribution Information

Resource lineage

Reference System Information

Metadata constraints

Metadata

Type of resource

Alternative metadata reference

Metadata standard

Metadata standard

Metadata standard

Spatial extent

Keywords

Provided by

Associated resources