Journal cover Journal topic
Earth Surface Dynamics An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 3.928 IF 3.928
  • IF 5-year value: 3.864 IF 5-year
  • CiteScore value: 6.2 CiteScore
  • SNIP value: 1.469 SNIP 1.469
  • IPP value: 4.21 IPP 4.21
  • SJR value: 1.666 SJR 1.666
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 21 Scimago H
    index 21
  • h5-index value: 23 h5-index 23
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

  19 Nov 2020

19 Nov 2020

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

Inverse modeling of turbidity currents using artificial neural network: verification for field application

Hajime Naruse1 and Kento Nakao2 Hajime Naruse and Kento Nakao
  • 1Graduate School of Science, Kyoto University. Kitashirakawa Oiwakecho, Sakyo-ku, Kyoto, 606-8502 Japan
  • 2Baseload Power Japan. SHINTORA-DORI CORE 3F, 4-1-1, Shimbashi, Minato-ku, Tokyo, 105-0004 Japan

Abstract. Although in situ measurements observed on modern frequently occurring turbidity currents have been performed, the flow characteristics of turbidity currents that occur only once every hundreds of years and deposit turbidites over a large area have not yet been elucidated. In this study, we propose a method for estimating the paleo-hydraulic conditions of turbidity currents from ancient turbidites by using machine learning. In this method, we hypothesize that turbidity currents result from suspended sediment clouds that flow down a steep slope in a submarine canyon and into a gently sloping basin plain. Using inverse modeling, we reconstruct seven model input parameters including the initial flow depth, the sediment concentration and the basin slope. Repeated numerical simulation using one-dimensional shallow water equations under various input parameters generates a dataset of the characteristic features of turbidites. This artificial dataset is then used for supervised training of a deep learning neural network (NN) to produce an inverse model capable of estimating paleo-hydraulic conditions from data of the ancient turbidites. Only 3,500 datasets are needed to train this inverse model. The performance of the inverse model is tested using independently generated datasets. Consequently, the NN successfully reconstructs the flow conditions of the test datasets. In addition, the proposed inverse model is quite robust to random errors in the input data. Judging from the results of subsampling tests, inversion of turbidity currents can be conducted if an individual turbidite can be correlated over 10 km at approximately 1 km intervals. These results suggest that the proposed method can sufficiently analyze field-scale turbidity currents.

Hajime Naruse and Kento Nakao

Interactive discussion

Status: open (until 04 Jan 2021)
Status: open (until 04 Jan 2021)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Hajime Naruse and Kento Nakao

Model code and software

nninv1d Hajime Naruse

Hajime Naruse and Kento Nakao


Total article views: 204 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
100 102 2 204 2 3
  • HTML: 100
  • PDF: 102
  • XML: 2
  • Total: 204
  • BibTeX: 2
  • EndNote: 3
Views and downloads (calculated since 19 Nov 2020)
Cumulative views and downloads (calculated since 19 Nov 2020)

Viewed (geographical distribution)

Total article views: 164 (including HTML, PDF, and XML) Thereof 163 with geography defined and 1 with unknown origin.
Country # Views %
  • 1



No saved metrics found.


No discussed metrics found.
Latest update: 29 Nov 2020
Publications Copernicus
Short summary
This paper proposes a method to reconstruct the hydraulic conditions of turbidity currents from turbidites. We investigated validity and problems of this method in application to acutual field datasets using artificial data. Once this method is established, it is expected that the method will elucidate the generation process of turbidity currents and will help to predict the geometry of resultant turbidites in deep sea environemnts.
This paper proposes a method to reconstruct the hydraulic conditions of turbidity currents from...