Journal cover Journal topic
Biogeosciences An interactive open-access journal of the European Geosciences Union
Journal topic
Discussion papers
https://doi.org/10.5194/bg-2018-353
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/bg-2018-353
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research article 03 Aug 2018

Research article | 03 Aug 2018

Review status
This discussion paper is a preprint. A revision of this manuscript was accepted for the journal Biogeosciences (BG) and is expected to appear here in due course.

Quantitative mapping and predictive modelling of Mn-nodules' distribution from hydroacoustic and optical AUV data linked by Random Forests machine learning

Iason-Zois Gazis1, Timm Schoening1, Evangelos Alevizos1, and Jens Greinert1,2 Iason-Zois Gazis et al.
  • 1GEOMAR Helmholtz Centre for Ocean Research Kiel, Wischhofstrasse 1–3, 24148 Kiel, Germany
  • 2Christian – Albrechts University Kiel, Institute of Geosciences, Ludewig-Meyn-Str. 10–12, 24098 Kiel, Germany

Abstract. In this study, high-resolution bathymetric multibeam and optical image data, both obtained within the Belgian manganese (Mn) nodule mining license area by the autonomous underwater vehicle (AUV) Abyss, were combined in order to create a predictive Random Forests (RF) machine learning model. AUV bathymetry reveals small-scale terrain variations, allowing slope estimations and calculation of bathymetric derivatives such as slope, curvature, and ruggedness. Optical AUV imagery provides quantitative information regarding the distribution (number and median size) of Mn-nodules. Within the area considered in this study, Mn-nodules show a heterogeneous and spatially clustered pattern and their number per square meter is negatively correlated with their median size. A prediction of the number of Mn-nodules was achieved by combining information derived from the acoustic and optical data using a RF model. This model was tuned by examining the influence of the training set size, the number of growing trees (ntree) and the number of predictor variables to be randomly selected at each RF node (mtry) on the RF prediction accuracy. The use of larger training data sets with higher ntree and mtry values increases the accuracy. To estimate the Mn-nodule abundance, these predictions were linked to ground truth data acquired by box coring. Linking optical and hydro-acoustic data revealed a non-linear relationship between the Mn-nodule distribution and topographic characteristics. This highlights the importance of a detailed terrain reconstruction for a predictive modelling of Mn-nodule abundance. In addition, this study underlines the necessity of a sufficient spatial distribution of the optical data to provide reliable modelling input for the RF.

Iason-Zois Gazis et al.
Interactive discussion
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement
Interactive discussion
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement
Iason-Zois Gazis et al.
Data sets

Swath sonar multibeam EM122 bathymetry during SONNE cruise SO239 with links to raw data files J. Greinert https://doi.pangaea.de/10.1594/PANGAEA.859456

Seafloor images and raw context data along AUV tracks during SONNE cruises SO239 and SO242/1. GEOMAR - Helmholtz Centre for Ocean Research Kiel, PA J. Greinert, T. Schoening, K. Köser, and M. Rothenbeck https://doi.org/10.1594/PANGAEA.882349

Iason-Zois Gazis et al.
Viewed  
Total article views: 392 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
302 89 1 392 2 4
  • HTML: 302
  • PDF: 89
  • XML: 1
  • Total: 392
  • BibTeX: 2
  • EndNote: 4
Views and downloads (calculated since 03 Aug 2018)
Cumulative views and downloads (calculated since 03 Aug 2018)
Viewed (geographical distribution)  
Total article views: 391 (including HTML, PDF, and XML) Thereof 389 with geography defined and 2 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 12 Dec 2018
Publications Copernicus
Special issue
Download
Short summary
The use of high-resolution hydroacoustic and optic data acquired by autonomous underwater vehicle can give us the detailed sea bottom topography and valuable information regarding the manganese nodules' spatial distribution. Moreover, the combined use of these datasets with a Random Forests machine learning model can extend this spatial prediction beyond the areas with available photos, providing the researchers with a new mapping tool for further investigation and link with other data.
The use of high-resolution hydroacoustic and optic data acquired by autonomous underwater...
Citation
Share