Data

Machine-learning infilled radiometric grids of Australia - potassium (K), thorium (Th), and uranium (U), 2026

Geoscience Australia

Du, Z. ; Sanchez, G. ; Mahani, M. ; Carr, L.

Viewed: [[ro.stat.viewed]] Cited: [[ro.stat.cited]] Accessed: [[ro.stat.accessed]]

ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rfr_id=info%3Asid%2FANDS&rft_id=info:doi10.26186/150893&rft.title=Machine-learning infilled radiometric grids of Australia - potassium (K), thorium (Th), and uranium (U), 2026&rft.identifier=10.26186/150893&rft.publisher=Commonwealth of Australia (Geoscience Australia)&rft.description=This dataset provides spatially continuous national grids of potassium (K), thorium (Th), and uranium (U) across Australia at a nominal 100 m cell size in the GDA2020 / Australian Albers projected coordinate system (EPSG:9473). The grids are derived from airborne radiometric survey data combined with modelled infill in areas where observations are absent.Measured airborne radiometric data were compiled from Geoscience Australia’s Radiometric Map of Australia (radmap v4) and associated survey datasets, with additional recent survey coverage incorporated for Tasmania. Where observations are available, the grids retain measured values. In areas without coverage, values were estimated using a machine-learning approach based on a convolutional neural network (CNN) combined with residual correction, producing spatially consistent predictions.The final products are provided on a 100 m grid to enable consistent national coverage; however, the spatial density and effective resolution of the underlying airborne survey data vary across regions. As a result, the grids represent a combination of measured and modelled values and should be interpreted accordingly. In infilled areas, values are derived from statistical relationships with environmental predictor variables (e.g. geology, terrain, and vegetation) and may therefore introduce dependencies if used in analyses involving similar inputs.Maintenance and Update Frequency: asNeededStatement: Measured airborne radiometric observations were sourced from Geoscience Australia’s Geophysical Archive Data Delivery System (GADDS), including Australia‑wide flight‑line datasets and survey‑level estimates underpinning the Radiometric Map of Australia (radmap v4). This update incorporates airborne radiometric surveys over Tasmania acquired during 2021–2022 by Mineral Resources Tasmania and flown by Magnetic and Spectrometric Surveys (MAGSPEC), including the Tasmanian Tiers (P5003) and East Tasmania (P5020) airborne magnetic, radiometric and elevation surveys. All newly incorporated data were levelled and harmonised to ensure consistency with national radiometric datasets.Primary reference datasets include Radmap v4 potassium (K), thorium (Th) and uranium (U) grids from the Australian National Radiometric Data Collection (2022), AWAGS radiometric flight‑line datasets accessed via GADDS, and Tasmania airborne radiometric surveys (Mineral Resources Tasmania, 2023).A harmonised national suite of predictor layers representing geological, terrain and vegetation or landscape controls was assembled to support machine‑learning prediction of K, Th and U. Covariates were resampled to the modelling grid. Further methodological details are documented in Du et al. (2025).Final products are provided as national GeoTIFF raster layers on a 100 m grid, referenced to the GDA2020 / Australian Albers projected coordinate system (EPSG:9473), and distributed as ZIP archives. Deliverables include filtered grids of potassium (K, %), equivalent thorium (eTh, ppm) and equivalent uranium (eU, ppm), along with supporting files comprising the prediction covariate list, the Tasmania radiometric mosaic (MRT) and major gap regions.Equivalent thorium (eTh) and uranium (eU) represent concentrations derived from gamma‑ray spectrometry and are reported as equivalent values because abundances are inferred from gamma emissions of daughter radionuclides, consistent with standard airborne radiometric processing conventions.References1. Australian National Radiometric Data Collection. 2022. Geoscience Australia, Canberra. https://pid.geoscience.gov.au/dataset/ga/1446362. Du, Zheyuan, John Wilford, MarieAude Bonnardot, Eloise Beyer, and Guillaume Sanchez. 2025. Advancing Radiometric Mapping in Australia: Bridging Gaps and Enhancing Mineral Exploration. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2025. Brisbane, Australia. DOI. 10.1109/IGARSS55030.2025.11243104.3. Mineral Resources Tasmania, Tasmania Radiometric Map, 2023. https://www.mrt.tas.gov.au/products/geoscience_maps/1500,000_statewide_maps/maps/geophysics_-_radiometric_map4. Wilford, J., and A Kroll. 2019. Complete radiometric grid of Australia (Radmap) v4 2019 with modelled infill. Geoscience Australia, Canberra.. https://pid.geoscience.gov.au/dataset/ga/144413&rft.creator=Du, Z. &rft.creator=Sanchez, G. &rft.creator=Mahani, M. &rft.creator=Carr, L. &rft.date=2026&rft.coverage=westlimit=154.00; southlimit=-9.00; eastlimit=112.00; northlimit=-44.00; projection=GDA2020 / geographic 2D (EPSG: 7844)&rft.coverage=westlimit=154.00; southlimit=-9.00; eastlimit=112.00; northlimit=-44.00; projection=GDA2020 / geographic 2D (EPSG: 7844)&rft_rights=Creative Commons Attribution 4.0 International Licence https://creativecommons.org/licenses/by/4.0/&rft_rights=© Commonwealth of Australia (Geoscience Australia) 2026&rft_rights=Australian Government Security Classification System https://www.protectivesecurity.gov.au/pspf-annual-release&rft_subject=geoscientificInformation&rft_subject=airborne digital data&rft_subject=Radiometrics&rft_subject=uranium&rft_subject=Earth sciences&rft_subject=potassium&rft_subject=thorium&rft_subject=GDA2020&rft_subject=radmap&rft_subject=machine learning&rft_subject=Resourcing Australia’s Prosperity&rft_subject=Onshore National Geology&rft_subject=Australia-wide geoscience data&rft_subject=Geology not elsewhere classified&rft_subject=Published_External&rft.type=dataset&rft.language=English Access the data

Access data via landing page
https://ecat.ga.gov.au...

Cite Saved to MyRDA Save to MyRDA

Licence & Rights:

Open Licence view details

Creative Commons Attribution 4.0 International Licence
https://creativecommons.org/licenses/by/4.0/

Australian Government Security Classification System
https://www.protectivesecurity.gov.au/pspf-annual-release

Access:

Open

Full description

This dataset provides spatially continuous national grids of potassium (K), thorium (Th), and uranium (U) across Australia at a nominal 100 m cell size in the GDA2020 / Australian Albers projected coordinate system (EPSG:9473). The grids are derived from airborne radiometric survey data combined with modelled infill in areas where observations are absent.

Measured airborne radiometric data were compiled from Geoscience Australia’s Radiometric Map of Australia (radmap v4) and associated survey datasets, with additional recent survey coverage incorporated for Tasmania. Where observations are available, the grids retain measured values. In areas without coverage, values were estimated using a machine-learning approach based on a convolutional neural network (CNN) combined with residual correction, producing spatially consistent predictions.

The final products are provided on a 100 m grid to enable consistent national coverage; however, the spatial density and effective resolution of the underlying airborne survey data vary across regions. As a result, the grids represent a combination of measured and modelled values and should be interpreted accordingly. In infilled areas, values are derived from statistical relationships with environmental predictor variables (e.g. geology, terrain, and vegetation) and may therefore introduce dependencies if used in analyses involving similar inputs.

Lineage

Maintenance and Update Frequency: asNeeded

Statement:

Measured airborne radiometric observations were sourced from Geoscience Australia’s Geophysical Archive Data Delivery System (GADDS), including Australia‑wide flight‑line datasets and survey‑level estimates underpinning the Radiometric Map of Australia (radmap v4). This update incorporates airborne radiometric surveys over Tasmania acquired during 2021–2022 by Mineral Resources Tasmania and flown by Magnetic and Spectrometric Surveys (MAGSPEC), including the Tasmanian Tiers (P5003) and East Tasmania (P5020) airborne magnetic, radiometric and elevation surveys. All newly incorporated data were levelled and harmonised to ensure consistency with national radiometric datasets.

Primary reference datasets include Radmap v4 potassium (K), thorium (Th) and uranium (U) grids from the Australian National Radiometric Data Collection (2022), AWAGS radiometric flight‑line datasets accessed via GADDS, and Tasmania airborne radiometric surveys (Mineral Resources Tasmania, 2023).

A harmonised national suite of predictor layers representing geological, terrain and vegetation or landscape controls was assembled to support machine‑learning prediction of K, Th and U. Covariates were resampled to the modelling grid. Further methodological details are documented in Du et al. (2025).

Final products are provided as national GeoTIFF raster layers on a 100 m grid, referenced to the GDA2020 / Australian Albers projected coordinate system (EPSG:9473), and distributed as ZIP archives. Deliverables include filtered grids of potassium (K, %), equivalent thorium (eTh, ppm) and equivalent uranium (eU, ppm), along with supporting files comprising the prediction covariate list, the Tasmania radiometric mosaic (MRT) and major gap regions.

Equivalent thorium (eTh) and uranium (eU) represent concentrations derived from gamma‑ray spectrometry and are reported as equivalent values because abundances are inferred from gamma emissions of daughter radionuclides, consistent with standard airborne radiometric processing conventions.

References

1. Australian National Radiometric Data Collection. 2022. Geoscience Australia, Canberra. https://pid.geoscience.gov.au/dataset/ga/144636

2. Du, Zheyuan, John Wilford, MarieAude Bonnardot, Eloise Beyer, and Guillaume Sanchez. 2025. "Advancing Radiometric Mapping in Australia: Bridging Gaps and Enhancing Mineral Exploration." In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2025. Brisbane, Australia. DOI. 10.1109/IGARSS55030.2025.11243104.

3. Mineral Resources Tasmania, Tasmania Radiometric Map, 2023. https://www.mrt.tas.gov.au/products/geoscience_maps/1500,000_statewide_maps/maps/geophysics_-_radiometric_map

4. Wilford, J., and A Kroll. 2019. "Complete radiometric grid of Australia (Radmap) v4 2019 with modelled infill. Geoscience Australia, Canberra.". https://pid.geoscience.gov.au/dataset/ga/144413

Notes

Purpose
The purpose of this dataset is to provide spatially continuous national radiometric grids for K, Th, and U by combining measured airborne radiometric observations with machine-learning-based infill in areas where data are sparse or absent. Unlike traditional radiometric datasets based solely on measured observations, this product includes modelled infill to provide complete spatial coverage. Measured observations are retained in areas of survey coverage, while modelled values are used only to infill gaps where no data are available. The modelling is therefore intended to improve spatial completeness rather than to replace measured data. These datasets are designed to support regional to national scale geoscientific analysis, mineral exploration, and environmental modelling where complete spatial coverage is required.

Issued: 14 05 2026

This dataset is part of a larger collection

Click to explore relationships graph

text: westlimit=154.00; southlimit=-9.00; eastlimit=112.00; northlimit=-44.00; projection=GDA2020 / geographic 2D (EPSG: 7844)

Subjects

User Contributed Tags

Other Information

Download the dataset (zip) [11.5 GB]

url : https://d28rz98at9flks.cloudfront.net/150893/150893_00_0.zip External Link

Complete Radiometric Grid of Australia (Radmap) v4 2019 with modelled infill

local : 144413

Australian National Radiometric Data Collection

local : 144636

Identifiers

DOI : 10.26186/150893
URL : pid.geoscience.gov.au/dataset/ga/150893
global : fbf3327c-1b47-4690-b3c8-ed81072ba639