<div><strong>Output Type: </strong>Exploring for the Future Extended Abstract</div><div><br></div><div><strong>Short Abstract: </strong>Airborne electromagnetic surveys are widely used in Australia for mineral exploration, groundwater assessment (i.e. hydro-stratigraphy and water quality) and natural resource management (i.e. salinity assessment). In the last decade, regional surveys have been acquired covering approximately two thirds of the continent and resulting in a large volume of data to interpret. To address this challenge, we have developed a machine learning workflow to assist with the interpretation of AEM conductivity depth sections.</div><div>‘AEM assist’ is an open-source machine learning algorithm that allows the user to interpret AEM sections from drillhole observations and/or interpreted segments along the conductivity depth section. AEM assist finds predictive relationships between the training observations (drillhole and/or interpreted sections) and the conductivity value which also includes the first vertical derivative of the conductivity. Due to the non-uniqueness of the conductivity response, we have also built in a suite of supplementary covariates or features to help improve the model prediction. These features include terrain indices, gamma radiometric, surface weathering intensity, distance proxies (e.g., distance from rocks of a known age), climate indices, gravity, and magnetic derivatives. We have built the AEM assist into a national mapping framework to facilitate model interpretation and training anywhere in Australia. Although local training of sections is recommended the national framework provides an opportunity to train a model in one region and predict into another area given similar geological and landscape histories. The AEM assist has the potential to speed up the interpretation of AEM flightline sections with statistical models of interpretation uncertainty. AEM assist can be used to provide a first pass interpretation of a survey area that can later be revised by the domain expert. A feature of AEM assist is that it systematically integrates many datasets that would otherwise be difficult to do from traditional methods.</div><div><br></div><div><strong>Citation:</strong> Basak S., Wilford J., Wong S.C.T., Ley-Cooper Y. & Ray A., 2024. AEM assist - a national predictive machine learning framework for airborne electromagnetic interpretation and extrapolation. In: Czarnota, K. (ed.) Exploring for the Future: Extended Abstracts. Geoscience Australia, Canberra, https://doi.org/10.26186/149495</div>

<div>Airborne electromagnetics (AEM) is a geophysical technique used for estimating the bulk conductivity profile of the upper 300 m (approximately) of the subsurface. The AEM data acquired as part of the Exploring for the Future program AusAEM Eastern Corridor survey (Ley-Cooper 2021) covers much of the central Kati Thanda - Lake Eyre Basin (KT–LEB). Data for these regional surveys were acquired using the TEMPEST AEM system at a nominal 20 km line spacing.</div><div>&nbsp;</div><div>The prevalence and relative consistency of large sand-rich sediment zones across the Cooper Creek Palaeovalley (Evans et al. 2024) means that AEM data are potentially useful for inferring the distribution of groundwater salinity beneath the floodplain and surrounds. To visualise salinity from AEM data in a map, the thickness weighted average bulk conductivity was calculated for the 15 m depth interval beneath the watertable along the AEM survey lines. Symington et al. (2024) details the rationale and methods to produce the AEM bulk conductivity points. Symington et al. (2024) also included the code embedded in a jupyter notebook written to calculate bulk conductance points from AEM line data and undertake an uncertainty analysis to assess the likelihood of the conductance response to be related to groundwater (note that the link to the code is contained in the Symington et al. 2024 reference).</div><div>&nbsp;</div><div>In conjunction with sparse groundwater salinity and water level data from existing bores, Symington&nbsp;et al. (2024) used the conductance data to provide insights to address the following questions:</div><div>1. What is the regional scale distribution of groundwater salinity within the shallow alluvial aquifer?</div><div>2. Where does the shallow aquifer host fresh water?</div><div>3. What areas are most likely to receive recharge from the flanks of the floodplain?</div><div>4. Is there evidence for the groundwater discharging into the river?</div><div>&nbsp;</div><div>Data from Symington et al. (2024) were used to infer salinity across the Cooper Creek floodplain and Strzelecki Desert, as well as to determine the location of potential fresh groundwater lenses beneath Cooper Creek floodplain in SA and Queensland. The groundwater bore and uncertainty analysis suggests good correlation exists between groundwater bore data and AEM conductance points, where groundwater occurs at shallow depths in areas including the Cooper Creek floodplain, Strzelecki Desert, and Coongie Lakes. Data analysis, interpretation and results are in Symington et al. (2024) and further discussed in Evans et al. (2024), Symington et al. (2023) and Symington et al. (2022).</div><div>&nbsp;</div><div>References</div><div>Evans TJ, Bishop C, Symington NJ, Halas L, Hansen JWH, Norton CJ, Hannaford C and Lewis SJ (2024) Cenozoic geology, hydrogeology, and groundwater systems: Kati Thanda – Lake Eyre Basin, Record 2024/05, Geoscience Australia, Canberra, http://dx.doi.org/10.26186/147422.</div><div>&nbsp;</div><div>Ley-Cooper AY (2021) Exploring for the Future AusAEM Eastern Resources Corridor 2021 Airborne Electromagnetic Survey TEMPEST® airborne electromagnetic data and GALEI inversion conductivity estimates [data set], Geoscience Australia, https://ecat.ga.gov.au/geonetwork/srv/api/records/145744, accessed 14 December 2023.</div><div>&nbsp;</div><div>Symington N, Evans T, McPherson A, Buckerfield S, Rollet N, Ray A and Halas L (2024) Characterising surface water groundwater interaction using airborne electromagnetics: a case study from the Cooper Creek floodplain, Queensland, Australia, workflow release, Geoscience Australia, Canberra, https://dx.doi.org/10.26186/149176.</div><div>&nbsp;</div><div>Symington N, Evans T, Rollet N, Halas L, Vizy J, Buckerfield S, Ray A, LeyCooper Y and Brodie R (2023) Using regional airborne electromagnetic conductivity data to characterise surface water groundwater interaction in the Cooper Creek floodplain in arid central eastern Australia, Geoscience Australia, Canberra, https://pid.geoscience.gov.au/dataset/ga/147716.</div><div>&nbsp;</div><div>Symington N, Halas L, Evans T and Rollet N (2022) Mapping freshwater lenses in the Cooper Creek floodplain using airborne electromagnetics, Geoscience Australia, Canberra, https://pid.geoscience.gov.au/dataset/ga/147039.</div>

<div>In Australia, wide-spread sedimentary basin and regolith cover presents a key challenge to explorers, environmental managers and decision-makers, as it obscures underlying rocks of interest. To address this, a national coverage of airborne electromagnetics (AEM) with a 20&nbsp;km line-spacing is being acquired. This survey is acquired as part of the Exploring for the Future program and in collaboration with state and territory geological surveys. This survey presents an opportunity for regional geological interpretations on the modelled AEM data, helping constrain the characteristics of the near-surface geology beneath the abundant cover, to a depth of up to ~500&nbsp;m.</div><div> The AEM conductivity sections were used to delineate key chronostratigraphic boundaries, e.g. the bases of geological eras, and provide a first-pass interpretation of the subsurface geology. The interpretation was conducted with a high level of data integration with boreholes, potential fields geophysics, seismic, surface geology maps and solid geology maps. This approach led to the construction of well-informed geological interpretations and provided a platform for ongoing quality assurance and quality control of the interpretations and supporting datasets. These interpretations are delivered across various platforms in multidimensional non-proprietary open formats, and have been formatted for direct upload to Geoscience Australia’s (GA) Estimates of Geological and Geophysical Surfaces (EGGS) database, the national repository of multidisciplinary subsurface depth estimates.</div><div> These interpretations have resulted in significant advancements in our understanding of Australia’s near-surface geoscience, by revealing valuable information about the thickness and composition of the extensive cover, as well as the composition, structure and distribution of underlying rocks. Current interpretation coverage is ~110,000 line kilometres of AEM conductivity sections, or an area &gt;2,000,000&nbsp;km2, similar to the area of Greenland or Saudi Arabia. This ongoing work has led to the production of almost 600,000 depth estimate points, each attributed with interpretation-specific metadata. Three-dimensional line work and over 300,000 points are currently available for visualisation, integration and download through the GA Portal, or for download through GA’s eCat electronic catalogue. </div><div> These interpretations demonstrate the benefits of acquiring broadly-spaced AEM surveys. Interpretations derived from these surveys are important in supporting regional environmental management, resource exploration, hazard mapping, and stratigraphic unit certainty quantification. Delivered as precompetitive data, these interpretations provide users in academia, government and industry with a multidisciplinary tool for a wide range of investigations, and as a basis for further geoscientific studies.</div> Abstract submitted and presented at 2023 Australian Earth Science Convention (AESC), Perth WA (https://2023.aegc.com.au/)

<div> A key issue for explorers in Australia is the abundant sedimentary and regolith cover obscuring access to underlying potentially prospective rocks. &nbsp;Multilayered chronostratigraphic interpretation of regional broad line-spaced (~20&nbsp;km) airborne electromagnetic (AEM) conductivity sections have led to breakthroughs in Australia’s near-surface geoscience. &nbsp;A dedicated/systematic workflow has been developed to characterise the thickness of cover and the depth to basement rocks, by delineating contact geometries, and by capturing stratigraphic units, their ages and relationships. &nbsp;Results provide a fundamental geological framework, currently covering 27% of the Australian continent, or approximately 2,085,000&nbsp;km2. &nbsp;Delivery as precompetitive data in various non-proprietary formats and on various platforms ensures that these interpretations represent an enduring and meaningful contribution to academia, government and industry.&nbsp;The outputs support resource exploration, hazard mapping, environmental management, and uncertainty attribution.&nbsp;This work encourages exploration investment, can reduce exploration risks and costs, helps expand search area whilst aiding target identification, and allows users to make well-informed decisions. Presented herein are some key findings from interpretations in potentially prospective, yet in some cases, underexplored regions from around Australia.&nbsp;</div> This abstract was submitted & presented to the 8th International Airborne Electromagnetics Workshop (AEM2023) (https://www.aseg.org.au/news/aem-2023)

<div>A national compilation of airborne electromagnetic (AEM) conductivity–depth models from AusAEM (Ley-Cooper et al. 2020) survey line data and other surveys (see reference list in the attachments) has been used to train a conductivity model prediction for the 0-4 m and 30 m depth intervals. Over 460,000 training points/measurements were used in a 5 K-Fold training and validation split. A further 28,626 points/measurements were used to assess the out of sample performance (OOS; i.e. points not used in the model validation). Modelling of the conductivity values (i.e. measurements along the AEM survey lines) was performed using the gradient boosted (GB) tree algorithm. The GB model is a machine learning (ML) ensemble technique used for both regression and classification tasks (https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html). Samples along the flight-line were thinned to approximately one sample per 300 m. This avoided the situation where we could have more than one sample per pixel (i.e. features or covariates used in the model prediction have a cell or pixel size of 80 m) that could otherwise lead to over fitting. In addition, out of sample set used label clusters or groups to minimise overfitting. Here we use the median of the models as the conductivity prediction and the upper and lower percentiles (95th and 5th respectively) to measure the model uncertainty. Grids show conductivity (S/m) in log 10 units. The methodology used to generate these conductivity grids are overall similar to that described by Wilford, et al. 2022.</div><div>&nbsp;</div><div>Reported out-of-sample r-squares for the 0-4 m and 3 m depths are 0.76 and 0.74, respectively. The ML approach allows estimation of conductivity into areas where we do not have airborne electromagnetic survey coverage. Hence these model have a national extent. Where we do not have AEM survey coverage the model is finding relationships with the covariates and making informed estimates of conductivity in those areas. Where those relationships are not well understood (i.e. where we see a departure in the feature space characteristics from what the model can ‘see’) the model prediction is likely to be less certain. Differences in the features and their corresponding values ‘seen’ and used in the model versus 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.</div><div>&nbsp;</div><div>Datasets in this data package include:</div><div>&nbsp;</div><div>1. 0_4m_conductivity_prediction_median.tif</div><div>2. 0_4m_conductivity_lower_percentile_5th.tif</div><div>3. 0_4m_conductivity_upper_percentile_95th.tif</div><div>4. 30m_conductivity_prediction_median.tif</div><div>5.30m_conductivity_lower_percentile_5th.tif</div><div>6. 30m_conductivity_upper_percentile_95th.tif</div><div>7. National_conductivity_model_shift.tif</div><div>8. Full list of referenced AEM survey datasets used to train the model (word document)</div><div>9. Map showing the distribution of training and out-of-sample sites</div><div><br></div><div>All the Geotiffs (1-6) are in log (10) electrical conductivity siemens per metre (S/m).</div><div>&nbsp;</div><div>This work is part of Geoscience Australia’s Exploring for the Future program which 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.</div><div><br></div><div><br></div><div><strong>Reference:</strong></div><div><br></div><div>Ley-Cooper, A. Y., Brodie, R.C., and Richardson, M. 2020. AusAEM: Australia’s airborne electromagnetic continental-scale acquisition program, Exploration Geophysics, 51:1, 193-202, DOI: 10.1080/08123985.2019.1694393</div><div><br></div><div>Wilford, J., LeyCooper, Y., Basak, S., Czarnota, K. 2022. High resolution conductivity mapping using regional AEM survey and machine learning. Geoscience Australia, Canberra. https://dx.doi.org/10.26186/146380</div>