Journal cover Journal topic
Geoscientific Model Development An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 5.240 IF 5.240
  • IF 5-year value: 5.768 IF 5-year
    5.768
  • CiteScore value: 8.9 CiteScore
    8.9
  • SNIP value: 1.713 SNIP 1.713
  • IPP value: 5.53 IPP 5.53
  • SJR value: 3.18 SJR 3.18
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 71 Scimago H
    index 71
  • h5-index value: 51 h5-index 51
Preprints
https://doi.org/10.5194/gmd-2020-106
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-2020-106
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: model description paper 19 Jun 2020

Submitted as: model description paper | 19 Jun 2020

Review status
This preprint is currently under review for the journal GMD.

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

Zhenjiao Jiang1,2, Dirk Mallants2, Lei Gao2, Gregoire Mariethoz3, and Luk Peeters4 Zhenjiao Jiang et al.
  • 1Key Laboratory of Groundwater Resources and Environment, Ministry of Education, College of Environment and Resources, Jilin University, Changchun, 130021, China
  • 2CSIRO Land & Water, Locked Bag 2, Glen Osmond, SA 5064, Australia
  • 3University of Lausanne, Faculty of Geosciences and Environment, Institute of Earth Surface Dynamics, Lausanne, Switzerland
  • 4CSIRO Mineral Resources, Locked Bag 2, Glen Osmond, SA 5064, Australia

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 < 0.10 and produces a square error < 0.10 across 93 % of the validation areas, demonstrating that it is reliable in reconstructing 3D palaeovalley 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 (ore bodies, aquifer) from 2D land surface observations.

Zhenjiao Jiang et al.

Interactive discussion

Status: open (until 14 Aug 2020)
Status: open (until 14 Aug 2020)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Zhenjiao Jiang et al.

Model code and software

A deep learning model for regional-scale 3D subsurface structure mapping J. et al. 2020 https://doi.org/10.7910/DVN/DDEIUV

Zhenjiao Jiang et al.

Viewed

Total article views: 181 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
129 44 8 181 18 9 13
  • HTML: 129
  • PDF: 44
  • XML: 8
  • Total: 181
  • Supplement: 18
  • BibTeX: 9
  • EndNote: 13
Views and downloads (calculated since 19 Jun 2020)
Cumulative views and downloads (calculated since 19 Jun 2020)

Viewed (geographical distribution)

Total article views: 119 (including HTML, PDF, and XML) Thereof 119 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Saved

No saved metrics found.

Discussed

No discussed metrics found.
Latest update: 10 Jul 2020
Publications Copernicus
Download
Short summary
Fast and reliable tools are required to extract hidden information from big geophysical and remote sensing data. Deep learning model in 3D image construction from 2D single image is here developed for palaeovalley 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.
Fast and reliable tools are required to extract hidden information from big geophysical and...
Citation