Australian Soil Classification Map
We used Digital Soil Mapping (DSM) technologies combined with the real-time collations of soil attribute data from TERN's recently developed Soil Data Federation System, to produce a map of Australian Soil Classification Soil Order classes with quantified estimates of mapping reliability at a 90 m resolution.
Simple
Identification info
- Date (Creation)
- 2021-08-10
- Date (Publication)
- 2021-08-12
- Date (Revision)
- 2025-12-10
- Edition
- 1
Identifier
Publisher
Author
CSIRO Agriculture and Food - Searle, Ross (Senior Experimental Scientist)
Waite Road, Waite, South Australia, 5064, Australia
Waite
South Australia
5064
Australia
Collaborator
Commonwealth Scientific and Industrial Research Organisation
147 Underwood Avenue, Floreat, 6014, Western Australia, Australia
Floreat
Western Australia
6014
Australia
Collaborator
Terrestrial Ecosystem Research Network
80 Meiers Road, Indooroopilly, Queensland, 4068, Australia
Indooroopilly
Queensland
4068
Australia
Collaborator
University of Sydney
City Road, Camperdown, New South Wales, 2050, Australia
Camperdown
New South Wales
2050
Australia
Collaborator
Geoscience Australia
101 Jerrabomberra Avenue, Symonston, 2609, Australian Capital Territory, Australia
Symonston
Australian Capital Territory
2609
Australia
Collaborator
Department of Land Resource Management (2012-2016), Northern Territory Government
25 Chung Wah Terrace, Palmerston, Northern Territory, 0830, Australia
Palmerston
Northern Territory
0830
Australia
Collaborator
Office of Environment and Heritage (2011-2019), New South Wales
4 Parramatta Square, 12 Darcy Street, Parramatta, 2150, New South Wales, Australia
Parramatta
New South Wales
2150
Australia
Collaborator
Department of Science, Information Technology, Innovation and the Arts (2012-2015), Queensland Government
400 George Street, Brisbane, Queensland, 4000, Australia
Brisbane
Queensland
4000
Australia
Collaborator
Department of Environment, Water and Natural Resources (2012-2018), South Australian Government
81-95 Waymouth Street, Adelaide, South Australia, 5000, Australia
Adelaide
South Australia
5000
Australia
Collaborator
Department of Primary Industries, Parks, Water and Environment, Tasmanian Government
59 Liverpool Street, Hobart, Tasmania, 7000, Australia
Hobart
Tasmania
7000
Australia
Collaborator
Department of Environment and Primary Industries (2013-2015), Victorian Government
8 Nicholson Street, Melbourne, Victoria, 3000, Australia
Melbourne
Victoria
3000
Australia
Collaborator
Department of Agriculture and Food (2006-2017), Western Australian Government
3 Baron-Hay Court South Perth Western Australia 6151, Australia
South Perth
Western Australia
6151
Australia
- Website
- https://www.tern.org.au/
- Purpose
- The map gives an estimate of the spatial distribution of soil types across Australia.
- Credit
- We at TERN acknowledge the Traditional Owners and Custodians throughout Australia, New Zealand and all nations. We honour their profound connections to land, water, biodiversity and culture and pay our respects to their Elders past, present and emerging.
- Credit
- <p></p>This work was jointly funded by CSIRO, Terrestrial Ecosystem Research Network (TERN) and the Australian Government through the National Collaborative Research Infrastructure Strategy (NCRIS).<br><br> We are grateful to the custodians of the soil site data in each state and territory for providing access to the soil site data, and all of the organisations listed as collaborating agencies for their significant contributions to the project and its outcomes.<br> CSIRO maintains and makes the data through the Australian Soil Resource Information System.
- Status
- Completed
Point of contact
CSIRO Agriculture and Food - Searle, Ross (Senior Experimental Scientist)
Waite Road, Waite, South Australia, 5064, Australia
Waite Road
Waite
South Australia
5064
Australia
- Topic category
-
- Environment
- Geoscientific information
Extent
N
S
E
W
))
Temporal extent
- Time period
- 1950-01-01 2021-08-10
- Maintenance and update frequency
- Not planned
- GCMD Science Keywords
- ANZSRC Fields of Research
- TERN Parameter Vocabulary
- QUDT Units of Measure
- GCMD Horizontal Resolution Ranges
- GCMD Temporal Resolution Ranges
- Keywords (Discipline)
-
- Australian Soil Types
Resource constraints
- Use limitation
- The Creative Commons Attribution 4.0 International (CC BY 4.0) license allows others to copy, distribute, display, and create derivative works provided that they credit the original source and any other nominated parties. Details are provided at https://creativecommons.org/licenses/by/4.0/
- File name
- 88x31.png
- File description
- CCBy Logo from creativecommons.org
- File type
- png
- Title
- Creative Commons Attribution 4.0 International Licence
- Alternate title
- CC-BY
- Edition
- 4.0
- Access constraints
- License
- Use constraints
- Other restrictions
- Other constraints
- TERN services are provided on an "as-is" and "as available" basis. Users use any TERN services at their discretion and risk. They will be solely responsible for any damage or loss whatsoever that results from such use including use of any data obtained through TERN and any analysis performed using the TERN infrastructure. <br />Web links to and from external, third party websites should not be construed as implying any relationships with and/or endorsement of the external site or its content by TERN. <br /><br />Please advise any work or publications that use this data via the online form at https://www.tern.org.au/research-publications/#reporting
- Other constraints
- Please cite this dataset as {Author} ({PublicationYear}). {Title}. {Version, as appropriate}. Terrestrial Ecosystem Research Network. Dataset. {Identifier}.
Resource constraints
- Classification
- Unclassified
Distribution Information
Distribution Information
- Distribution format
-
Distributor
Distributor
Terrestrial Ecosystem Research Network
80 Meiers Road, Indooroopilly, Queensland, 4068, Australia
Indooroopilly
Queensland
4068
Australia
- OnLine resource
-
ASC
Australian Soil Classification Map
- OnLine resource
- Cloud Optimised GeoTIFFs - Australian Soil Classification Map
- OnLine resource
- Landscape Data Visualiser - Australian Soil Classification Map
- OnLine resource
- ro-crate-metadata.json
Data quality info
- Hierarchy level
- Dataset
Report
Result
- Statement
- The overall map accuracy is 61%. Each pixel also has an estimate of the Random Forest model structural uncertainty represented as a confusion index. The confusion index is available from the same location as this dataset.
Resource lineage
- Statement
- The map was produced as per methods described at - https://aussoilsdsm.esoil.io/slga-version-2-products/australian-soil-classification-map<br><br> Soil classification data was extracted from the SoilDataFederator (SDF) - https://esoil.io/TERNLandscapes/Public/Pages/SoilDataFederator/SoilDataFederator.html<br><br> A total of 195,383 observations with either an Australian Soil Classification (ASC) or a Principal Profile Form (PPF) classification or a Great Soil Group (GSG) classification were extracted. Of these observations 130,570 of them had an ASC directly assigned by a pedologist. The remaining 64,813 observations either had a PPF or an ASC assigned to them by pedologists. The PPF and GSG classification where then transformed to an ASC.<br><br> The 90 m raster covariate data was obtained from TERNs publicly available raster covariate stack - https://esoil.io/TERNLandscapes/Public/Products/TERN/Covariates/Mosaics. A parsimonious set of these covariates was used in the modelling.<br><br> We used the R "Ranger" Random Forest package to implement a machine learning model as per standard Digital Soil Mapping (DSM) methodologies.<br><br> The observed geographic locations in the ASC data set were used to extract cell values from the raster covariate stack using the R "raster" package. This data set was then divided into a 90/10% split of training and external validation sets. The training data was then bootstrapped sampled 50 times to create 50 bootstrap training sets. These training sets were then used to generate 50 Random Forest model realisations.<br><br> Using the CSIRO Pearcey High Performance Compute (HPC) cluster the Random Forest models were evaluated against the input covariate raster data stack. This was done for each 90m raster cell across the nation for each of the 50 bootstrapped model realisations. The modal ASC value across the 50 realisations for each cell was determined and assigned as the most probable soil type for that cell in the output raster. The ratio of the second most probable soil to the most probable soil was also calculated to generate a model confusion index, an estimate of the structural uncertainty in the Random Forest model.<br><br> The Australian Soil Resource Information System (ASRIS) contains a product that is a compilation of all existing polygon mapping conducted by state and federal soil survey agencies across all of Australia. This product is made up of a diverse range of field mapping products at a range of mapping scales. From this product we extracted all polygons that were mapped at a scale of 1:100,000 or finer, as defined in the Guidelines For Surveying Soil And Land Resources (Blue Book). Polygons mapped at this scale are high quality spatial estimates of the distribution of soil attributes. We then rasterised these polygon ASC values and merged these values into our final estimates of ASC, i.e., where an ASRIS 100,000 scale polygon exists it will replace the modelled ASC value.<br><br> All processing for the generation of these products was undertaken using the R programming language. R Core Team (2020).<br><br> <ul style="list-style-type: disc;"><li>Code - https://github.com/AusSoilsDSM/SLGA</li> <li>Observation data - https://esoil.io/TERNLandscapes/Public/Pages/SoilDataFederator/SoilDataFederator.html</li> <li>Covariate rasters - https://esoil.io/TERNLandscapes/Public/Pages/SLGA/GetData-COGSDataStore.html</li></ul>
- Hierarchy level
- Dataset
- Title
- Methods Summary - Australian Soil Classification Map
- Website
-
https://aussoilsdsm.esoil.io/slga-version-2-products/australian-soil-classification-map
Method documentation
- Title
- R Core Team (2020). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria.
- Website
-
https://www.R-project.org/
Method documentation
Reference System Information
- Reference system identifier
- EPSG/EPSG:4326
- Reference system type
- Geodetic Geographic 2D
Metadata
- Metadata identifier
-
urn:uuid/15728dba-b49c-4da5-9073-13d8abe67d7c
- Title
- TERN GeoNetwork UUID
- Language
- English
- Character encoding
- UTF8
Point of contact
Type of resource
- Resource scope
- Dataset
- Metadata linkage
-
https://geonetwork.tern.org.au/geonetwork/srv/eng/catalog.search#/metadata/15728dba-b49c-4da5-9073-13d8abe67d7c
Point-of-truth metadata URL
- Date info (Creation)
- 2021-08-10T00:00:00.000000+00:00
- Date info (Revision)
- 2025-12-10T10:11:44.999100+00:00
Metadata standard
- Title
- ISO 19115-1:2014/AMD 1:2018 Geographic information - Metadata - Fundamentals
- Edition
- 1
Metadata standard
- Title
- ISO/TS 19115-3:2016
- Edition
- 1.0
Metadata standard
- Title
- ISO/TS 19157-2:2016
- Edition
- 1.0
- Title
- Terrestrial Ecosystem Research Network (TERN) Metadata Profile of ISO 19115-3:2016 and ISO 19157-2:2016
- Date (published)
- 2021
- Edition
- 1.0
Identifier
Overviews
Spatial extent
N
S
E
W
Provided by
Associated resources
Not available