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

Jiang, Zhenjiao; Mallants, Dirk; Gao, Lei; Munday, Tim; Mariethoz, Gregoire; Peeters, Luk

doi:https://doi.org/10.5194/gmd-14-3421-2021

Articles | Volume 14, issue 6

https://doi.org/10.5194/gmd-14-3421-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-14-3421-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 14, issue 6

Model description paper

|

08 Jun 2021

Model description paper |

| 08 Jun 2021

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

Zhenjiao Jiang, Dirk Mallants, Lei Gao, Tim Munday, Gregoire Mariethoz, and Luk Peeters

Supplement

https://doi.org/10.5194/gmd-14-3421-2021-supplement

Data sets

Multi-resolution Valley Bottom Flatness (MrVBF) J. Gallant, T. Dowling, and J. Austin https://doi.org/10.4225/08/5701C885AB4FE

Musgrave Province Airborne Electromagnetic Conductivity Grids T. Munday https://doi.org/10.25919/5d0868d48591e

Model code and software

Sub3DNet: A deep learning model for regional-scale 3D subsurface structure mapping Zhenjiao Jiang https://doi.org/10.7910/DVN/DDEIUV

Short summary

Fast and reliable tools are required to extract hidden information from big geophysical and remote sensing data. A deep-learning model in 3D image construction from 2D image(s) is here developed for paleovalley mapping from globally available digital elevation data. The outstanding performance for 3D subsurface imaging gives confidence that this generic novel tool will make better use of existing geophysical and remote sensing data for improved management of limited earth resources.