Journal cover Journal topic
Hydrology and Earth System Sciences An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 4.256 IF 4.256
  • IF 5-year value: 4.819 IF 5-year
  • CiteScore value: 4.10 CiteScore
  • SNIP value: 1.412 SNIP 1.412
  • SJR value: 2.023 SJR 2.023
  • IPP value: 3.97 IPP 3.97
  • h5-index value: 58 h5-index 58
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 99 Scimago H
    index 99
Discussion papers
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research article 21 Jan 2019

Research article | 21 Jan 2019

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Hydrology and Earth System Sciences (HESS).

High-resolution palaeovalley classification from airborne electromagnetic imaging and deep neural network training using digital elevation model data

Zhenjiao Jiang1,2, Dirk Mallants2, Luk Peeters3, Lei Gao2, and Gregoire Mariethoz4 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
  • 3CSIRO Mineral Resources, Locked Bag 2, Glen Osmond, SA 5064, Australia
  • 4University of Lausanne, Faculty of Geosciences and Environment, Institute of Earth Surface Dynamics, Lausanne, Switzerland

Abstract. Palaeovalleys are buried ancient river valleys that often form productive aquifers, especially in the semi-arid and arid areas of Australia. Delineating their extent and hydrostratigraphy is however a challenging task in groundwater system characterization. This study developed a methodology based on the deep learning super-resolution convolutional neural network (SRCNN) approach, to convert electrical conductivity (EC) estimates from an airborne electromagnetic (AEM) survey in South Australia to a high-resolution binary palaeovalley map. The SRCNN was trained and tested with a synthetic training dataset, where valleys were generated from readily available digital elevation model (DEM) data from the AEM survey area. Electrical conductivities typical of valley sediments were generated by Archie’s Law, and subsequently blurred by down-sampling and bicubic interpolation to represent noise from the AEM survey, inversion and interpolation. After a model training step, the SRCNN successfully removed such noise, and reclassified the low-resolution, unimodal but skewed EC values into a high-resolution palaeovalley index following a bimodal distribution. The latter allows distinguishing valley from non-valley pixels. Furthermore, a realistic spatial connectivity structure of the palaeovalley was predicted when compared with borehole lithology logs and valley bottom flatness indicator. Overall the methodology permitted to better constrain the three-dimensional palaeovalley geometry from AEM images that are becoming more widely available for groundwater prospecting.

Zhenjiao Jiang et al.
Interactive discussion
Status: open (extended)
Status: open (extended)
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.
Zhenjiao Jiang et al.
Total article views: 332 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
253 76 3 332 5 5
  • HTML: 253
  • PDF: 76
  • XML: 3
  • Total: 332
  • BibTeX: 5
  • EndNote: 5
Views and downloads (calculated since 21 Jan 2019)
Cumulative views and downloads (calculated since 21 Jan 2019)
Viewed (geographical distribution)  
Total article views: 167 (including HTML, PDF, and XML) Thereof 166 with geography defined and 1 with unknown origin.
Country # Views %
  • 1
No saved metrics found.
No discussed metrics found.
Latest update: 23 Apr 2019
Publications Copernicus
Short summary
Palaeovalleys often form productive aquifers in the semi-arid and arid areas. A methodology based on deep learning is introduced to automatically generate high-resolution 3D palaeovalley maps from low-resolution electrical conductivity data derived from airborne geophysical surveys. It is validated by borehole logs and the surface valley indices that the proposed method in this study provides an effective tool for regional-scale palaeovalley mapping and groundwater exploration.
Palaeovalleys often form productive aquifers in the semi-arid and arid areas. A methodology...