Backing up the AEM – unravelling a palaeovalley fill for groundwater exploration in the APY Lands

Krapf, Carmen; Costar, Adrian; Keppel, Mark; Inverarity, Kent; Love, Andrew J.; Stoian, Liliana; Gordon, Georgina; Soerensen, Camilla; Munday, Tim

doi:10.1080/22020586.2019.12073103

Cited by 2 publications

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

Sub3DNet1.0: a deep-learning model for regional-scale 3D subsurface structure mapping

et al. 2021

Self Cite

View full text Add to dashboard Cite

Abstract. This study introduces an efficient deep-learning model based on convolutional neural networks with joint autoencoder and adversarial structures for 3D subsurface mapping from 2D surface observations. The method was applied to delineate paleovalleys in an Australian desert landscape. The neural network was trained on a 6400 km2 domain by using a land surface topography as 2D input and an airborne electromagnetic (AEM)-derived probability map of paleovalley presence as 3D output. The trained neural network has a squared error <0.10 across 99 % of the training domain and produces a squared error <0.10 across 93 % of the validation domain, demonstrating that it is reliable in reconstructing 3D paleovalley patterns beyond the training area. Due to its generic structure, the neural network structure designed in this study and the training algorithm have broad application potential to construct 3D geological features (e.g., ore bodies, aquifer) from 2D land surface observations.

show abstract

Sub3DNet1.0: a deep-learning model for regional-scale 3D subsurface structure mapping

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

Surf3DNet1.0: A deep learning model for regional-scale 3D subsurface structure mapping

Jiang

Mallants

Gao

et al. 2020

Preprint

View full text Add to dashboard Cite

Abstract. This study introduces an efficient deep learning approach based on convolutional neural networks with joint autoencoder and adversarial structures for 3D subsurface mapping from surface observations. The method was applied to delineate palaeovalleys in an Australian desert landscape. The neural network was trained on a 6,400 km2 domain by using a land surface tomography as 2D input and an airborne electromagnetic (AEM)-derived probability map of palaeovalley presence as 3D output. The trained neural network has a maximum square error

show abstract

Backing up the AEM – unravelling a palaeovalley fill for groundwater exploration in the APY Lands

Cited by 2 publications

References 1 publication

Sub3DNet1.0: a deep-learning model for regional-scale 3D subsurface structure mapping

Sub3DNet1.0: a deep-learning model for regional-scale 3D subsurface structure mapping

Surf3DNet1.0: A deep learning model for regional-scale 3D subsurface structure mapping

Contact Info

Product

Resources

About