Prediction of true classes of surficial and deep earth materials using multivariate geospatial data is a common challenge for geoscience modellers. Most geological processes leave a footprint that can be explored by geochemical data analysis. These footprints are normally complex statistical and spatial patterns buried deep in the high-dimensional compositional space. This paper proposes a spatial predictive model for classification of surficial and deep earth materials derived from the geochemical composition of surface regolith. The model is based on a combination of geostatistical simulation and machine learning approaches. A random forest predictive model is trained and features are ranked based on their contribution to the predictive model. To generate potential and uncertainty maps, compositional data are simulated at unsampled locations via a chain of transformations (isometric log-ratio transformation followed by flow anamorphosis) and geostatistical simulation. The simulated results are subsequently back-transformed to the original compositional space. The trained predictive model is used to estimate the probability of classes for simulated compositions. The proposed approach is illustrated through two case studies. In the first case study the major crustal blocks of the Australian continent are predicted from the surface regolith geochemistry of the National Geochemical Survey of Australia project. The aim of the second case study is to discover the superficial deposits (peat) from the regional-scale soil geochemical data of the Tellus project. The accuracy of the results in these two case studies confirms the usefulness of the proposed method for geological class prediction and geological process discovery.

This web service contains map layers and coverages for machine learning models, using raster datasets which include radiometric grid infill, cover depths and conductivity. All grids have been converted to cloud-optimised GeoTIFF (COG) format for use and delivery from an cloud-based object store (AWS s3). For potassium (K), thorium (Th) and uranium (U) radiometric infill grids, an equalised histogram was applied to each grid. The radiometric ternary image has no style applied, with from transparency for no-data values. A tile service (WMTS) is also integrated into the WMS to provide a high-performing service for integration into web maps and online mapping portals.

<div><strong>Output Type: </strong>Exploring for the Future Extended Abstract</div><div><br></div><div><strong>Short Abstract: </strong>Most geological mapping either over-estimates the amount of bedrock exposed at the surface or can miss local bedrock exposures in geological units describing cover materials (i.e. alluvium and colluvium). A machine learning, Convolutional Neural Network (CNN) has been applied to detect outcrops (exposed bedrock at the earth’s surface) and areas of very shallow cover over bedrock (i.e. sub-crop) at one meter resolution. We used a multi-feature training dataset consisting of sites associated with urban areas, roads, outcrops, waterbodies, soil (includes bare soil and soil covered by green and dry vegetation), trees, and shadows. Even though we were only interested in mapping outcrop, a multi-criteria label set significantly improved overall accuracy of the model. The explanatory variables or covariates included high-resolution satellite imagery, Sentinel-2 imagery, and terrain derivatives. The modelling approach was tested over an area in central West NSW, Australia. Labels were split into 80% for training and 20% for out-of-sample validation. Spatial K-groups were used in the training set to minimize auto-spatial correlation between neighbouring points and reduce the potential for overfitting. Two CNN model architectures were evaluated: Simple-Net and UNet. The Simple-Net structure consists of 2D Convolution layer and flatten layer, whereas the UNet architecture includes a mixture of 2D convolution layer, max pooling, up sampling and flatten layer. These models were tested with and without the use of high-resolution imagery. The UNet model incorporating high resolution imagery gave the best results (accuracy of 0.841 and an F1 score of 0.814), compared with Simple-Net (accuracy of 0.823 and an F1 score of 0.786). However, the Simple-Net’s model without the incorporation of high-resolution imagery was a slight improvement over the UNet architecture and due to the lack of national coverage for high-resolution imagery, the Simple-Net model offers better scalability. The detection of outcrop/sub-crop has broad application in improving the spatial explicitness of existing geological maps, improving sample detection and interpretation of litho-stratigraphy and geochemistry. High spatial resolution of outcrop/sub-crop also has implications in the agricultural and civil engineering sectors, ecology and in understanding surface and near-surface hydrological systems. After this proof-of-concept phase we plan to up-scale the approach nationally using a more representative labels and national covariates.</div><div><br></div><div><strong>Citation: </strong>Du, Z., Wilford, J. &amp; Roberts, D., 2024. Find a rock or a rock nearby using Convolution Neural Networks. In: Czarnota, K. (ed.) Exploring for the Future: Extended Abstracts. Geoscience Australia, Canberra. https://doi.org/10.26186/149631</div>

The AEM method measures regolith and rocks' bulk subsurface electrical conductivity, typically to a depth of several hundred meters. AEM survey data is widely used in Australia for mineral exploration (i.e. mapping undercover and detection of mineralisation), groundwater assessment (i.e. hydro-stratigraphy and water quality) and natural resource management (i.e. salinity assessment). Geoscience Australia (GA) has flown Large regional AEM surveys over Northern Australia, including Queensland, Northern Territory and Western Australia. The surveys were flown nominally at 20-kilometre line spacing, using the airborne electromagnetic systems that have signed technical deeds of staging with GA to ensure they can be modelled quantitatively. Geoscience Australia commissioned the survey as part of the Exploring for the Future (EFTF) program. The EFTF program is led by Geoscience Australia (GA), in collaboration with the Geological Surveys of the Northern Territory, Queensland, South Australia and Western Australia, and is investigating the potential mineral, energy and groundwater resources in northern Australia and South Australia. We have used a machine learning modelling approach that establishes predictive relationships between the inverted flight-line modelled conductivity with a suite of national environmental and geological covariates. These covariates include terrain derivatives, gamma-ray radiometric, geological maps, climate derived surfaces and satellite imagery. Conductivity-depth values were derived from a single model using GA's deterministic 1D smooth-30-layer layered-earth-inversion algorithm. (Brodie and Richardson 2015). Three conductivity depth interval predictions are generated to interpolate the actual modelled conductivity data, which is 20km apart. These depth slices include a 0-50cm, 9-11m and 22-27m depth prediction. Each depth interval was modelled and individually optimised using the gradient boosted tree algorithm. The training cross-validation step used label clusters or groups to minimise over-fitting. Many hundreds of conductivity models are generated (i.e. ensemble modelling). Here we use the median of the models as the conductivity prediction and the upper and lower percentiles (95th and 5th) to measure model uncertainty. Grids show conductivity (S/m) in log 10 units. Reported out-of-sample r-squares for each interval in order of increasing depth are 0.74, 0.64, and 0.67. A decline in model performance with increasing depth was expected due to the decrease in suitable covariates at greater depths. Modelled conductivities seem to be consistent with the geological, regolith, geomorphological, and climate processes in the study area. The conductivity grids are at the resolution of the covariates, which have a nominal pixel size of 85 meters. Datasets in this data package include; 1. 0-50cm depth interval 0_50cm_median.tif; 0_50_upper.tif; 0_50_lower.tif 2. 9-11m depth interval 9_11m_median.tif; 9_11m_upper.tif; 9_11m_lower.tif 3. 22-27m depth interval 22_27_median.tif; 22_27_upper.tif; 22_27_lower.tif 4. Covariate shift; Cov_shift.tif (higher values = great shift in covariates) Reference: Ross C Brodie & Murray Richardson (2015) Open Source Software for 1D Airborne Electromagnetic Inversion, ASEG Extended Abstracts, 2015:1, 1-3, DOI: 10.1071/ ASEG2015ab197

Improvements in discovery and management of minerals, energy and groundwater resources are spurred along by advancements in surface and subsurface imaging of the Earth. Over the last half decade Australia has led the world in the collection of regionally extensive airborne electromagnetic (AEM) data coverage, which provides new constraints on subsurface conductivity structure. Inferring geology and hydrology from conductivity is non-trivial as the conductivity response of earth materials is non-unique, but careful calibration and interpretation does provide significant insights into the subsurface. To date utility of this new data is limited by its spatial extent. The AusAEM survey provides conductivity constraints every 12.5 m along flight lines with no constraints across vast areas between flight lines spaced 20 km apart. Here we provide a means to infer the conductivity between flight lines as an interim measure before infill surveys can be undertaken. We use a gradient boosted tree machine learning algorithm to discover relationships between AEM conductivity models across northern Australia and other national data coverages for three depth ranges: 0–0.5 m, 9–11 m and 22–27 m. The predictive power of our models decreases with depth but they are nevertheless consistent with our knowledge of geological, landscape evolution and climatic processes and an improvement on standard interpolation methods such as kriging. Our models provide a novel complementary methodology to gridding/interpolating from AEM conductivity alone for use by the mining, energy and natural resource management sectors. <b>Citation: </b>Wilford J., Ley-Cooper Y., Basak S., & Czarnota K., 2022. High resolution conductivity mapping using regional AEM survey and machine learning. In: Czarnota, K. (ed.) Exploring for the Future: Extended Abstracts, Geoscience Australia, Canberra, https://dx.doi.org/10.26186/146380.

This web service contains map layers and coverages for machine learning models, using raster datasets which include radiometric grid infill, cover depths and conductivity. All grids have been converted to cloud-optimised GeoTIFF (COG) format for use and delivery from an cloud-based object store (AWS s3).

Multi-element geochemical surveys of rocks, soils, stream/lake/floodplain sediments, and regolith are typically carried out at continental, regional and local scales. The chemistry of these materials is defined by their primary mineral assemblages and their subsequent modification by comminution and weathering. Modern geochemical datasets represent a multi-dimensional geochemical space that can be studied using multivariate statistical methods from which patterns reflecting geochemical/geological processes are described (process discovery). These patterns form the basis from which probabilistic predictive maps are created (process validation). Processing geochemical survey data requires a systematic approach to effectively interpret the multi-dimensional data in a meaningful way. Problems that are typically associated with geochemical data include closure, missing values, censoring, merging, levelling different datasets, and adequate spatial sample design. Recent developments in advanced multivariate analytics, geospatial analysis and mapping provide an effective framework to analyze and interpret geochemical datasets. Geochemical and geological processes can often be recognized through the use of data discovery procedures such as the application of principal component analysis. Classification and predictive procedures can be used to confirm lithological variability, alteration, and mineralization. Geochemical survey data of lake/till sediments from Canada and of floodplain sediments from Australia show that predictive maps of bedrock and regolith processes can be generated. Upscaling a multivariate statistics-based prospectivity analysis for arc related Cu-Au mineralization from a regional survey in the southern Thomson Orogen in Australia to the continental scale, reveals a number of regions with similar (or stronger) multivariate response and hence potentially similar (or higher) mineral potential throughout Australia. <b>Citation:</b> E. C. Grunsky, P. de Caritat; State-of-the-art analysis of geochemical data for mineral exploration. <i>Geochemistry: Exploration, Environment, Analysis</i> 2019; 20 (2): 217–232. doi: https://doi.org/10.1144/geochem2019-031 This article appears in multiple journals (Lyell Collection & GeoScienceWorld)

In the first half of 2019, a collaborative mineral potential mapping project was undertaken between the Geological Survey of New South Wales (GSNSW) and Kenex to examine the mineral potential in the eastern Lachlan Orogen (ELO; Ford et al., 2019b). This project was part of a broader state-wide study that utilised the high quality publicly available geoscience data provided by the GSNSW to generate data-driven mineral potential maps using the weights of evidence (WofE) technique for different mineral systems in key metallogenic districts within NSW (Ford et al., 2019a). The aim of this collaborative project was to deliver a product that could be used to provide justifiable land use planning advice to key government stakeholders, as well as to highlight the exploration potential for key mineral systems at a regional scale. One key mineral system that was included in the 2019 ELO study was the porphyry Cu-Au mineral system, which was constrained to the Macquarie Arc. The results of the WofE mineral potential mapping for this porphyry model were broadly successful in terms of predicting the location of both the training data used in the WofE model, as well as a separate set of validation porphyry Cu-Au occurrences. However, the model failed to predict the location of one of the training points, Kaiser, in the prospective area. This failure to predict Kaiser led to a re-evaluation of the data using a variety of different machine learning techniques, in particular random forests (RF; Ford, 2020) and neural networks (NN). No additional or updated data was incorporated, and the maps used in the machine learning were the same maps made as part of the initial WofE study in 2019. The results show that the use of input maps that have been pre-classified to determine optimal thresholds outperform input maps that have had no favourability criteria applied when typical benchmarks for exploration targeting are considered. In addition, the NN analysis shows strong evidence of overfitting to the training data when a large number of input maps are used. A moderate degree of success for targeting under cover was achieved when only geophysical maps were included in the models. Abstract presented at the 8th Mines & Wines Conference 2022 (https://www.aig.org.au/events/8th-mines-wines-conference-2022/)

<div>With a higher demand for lithium (Li), a better understanding of its concentration and spatial distribution is important to delineate potential anomalous areas. This study uses a digital soil mapping framework to combine data from recent geochemical surveys and environmental covariates to predict and map Li content across the 7.6 million km2 area of Australia. Soil samples were collected by the National Geochemical Survey of Australia at a total of 1315 sites, with both top (0–10 cm depth) and bottom (on average 60–80 cm depth) catchment outlet sediments sampled. We developed 50 bootstrap models using a Cubist regression tree algorithm for both depths. The spatial prediction models were validated on an independent Northern Australia Geochemical Survey dataset, showing a good prediction with an RMSE of 3.82 mg kg-1 for the top depth. The model for the bottom depth has yet to be validated. The variables of importance for the models indicated that the first three Landsat bands and gamma radiometric dose have a strong impact on Li prediction. The bootstrapped models were then used to generate digital soil Li prediction maps for both depths, which could select and delineate areas with anomalously high Li concentrations in the regolith. The map shows high Li concentration around existing mines and other potentially anomalous Li areas. The same mapping principles can potentially be applied to other elements.&nbsp;</div> <b>Citation:</b> Ng, W., Minasny, B., McBratney, A., de Caritat, P., and Wilford, J.: Digital soil mapping of lithium in Australia, <i>Earth Syst. Sci. Data</i>, 15, 2465–2482, https://doi.org/10.5194/essd-15-2465-2023, <b>2023</b>.

The Proterozoic succession in the NDI Carrara 1 drill hole, Northern Territory, consists predominantly of tight shales, siltstones, and calcareous clastic rocks. As part of Geoscience Australia’s Exploring for the Future program, this study aims to derive porosity, permeability and gas content from both laboratory testing and well log interpretation from machine learning approaches, to improve the Proterozoic shale gas reservoir characterisation. The Proterozoic Lawn Hill Formation was divided into four chemostratigraphic packages. The middle two packages were further divided into seven internal units according to principal component analysis and self-organising map clustering on well logs and inorganic geochemical properties. Artificial neural networks were then applied to interpret the mineral compositions, porosity and permeability from well logs, density and neutron-density crossplot interpretations. Gas content was estimated from the interpreted porosity, gas saturation, total organic carbon and clay contents. Petrophysical interpretation results are summarised for all chemostratigraphic packages and units. Package 2 (1116–1430.1 m) has the highest potential among the four chemostratigraphic packages. P2U1 (1116–1271 m) and P2U3 (1335.5–1430.1 m) units have the most favourable petrophysical properties for organic-rich shales with the average total gas contents of 1.25 cm3/g and 1.30 cm3/g, geometric mean permeability of 4.79 µD and 17.56 µD, and net shale thickness of 54.4 m and 85.3 m, respectively. P3U4 unit (687.9–697.9 m) has high gas content and permeability, with the net shale thickness of 29.1 m. Besides the organic-rich shales, the tight non-organic-rich siltstone and shale reservoirs in package 1 (below 1430.1 m) have average gas saturation of 14% and geometric mean permeability of 1.31 µD, respectively. Published in The APPEA Journal 2023. <b>Citation:</b> Wang Liuqi, Bailey Adam H. E., Grosjean Emmanuelle, Carson Chris, Carr Lidena K., Butcher Grace, Boreham Christopher J., Dewhurst Dave, Esteban Lionel, Southby Chris, Henson Paul A. (2023) Petrophysical interpretation and reservoir characterisation on Proterozoic shales in National Drilling Initiative Carrara 1, Northern Territory. <i>The APPEA Journal</i><b> 63</b>, 230-246. https://doi.org/10.1071/AJ22049