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

Gazis, Iason-Zois, Schoening, Timm, Alevizos, Evangelos and Greinert, Jens (2018) Quantitative mapping and predictive modelling of Mn-nodules' distribution from hydroacoustic and optical AUV data linked by Random Forests machine learning. Open Access Biogeosciences Discussions . DOI 10.5194/bg-2018-353.

[img]
Preview
Text
bg-2018-353.pdf - Published Version
Available under License Creative Commons: Attribution 4.0.

Download (2807Kb) | Preview

Supplementary data:

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.

Document Type: Article
Additional Information: Special issue statement: This article is part of the special issue “Assessing environmental impacts of deep-sea mining – revisiting decade-old benthic disturbances in Pacific nodule areas”.
Keywords: AUV, Mn-nodules, Random Forests
Research affiliation: OceanRep > GEOMAR > FB2 Marine Biogeochemistry > FB2-MG Marine Geosystems
OceanRep > GEOMAR > FB2 Marine Biogeochemistry > FB2-MG Marine Geosystems > DeepSea Monitoring
Refereed: No
Open Access Journal?: Yes
DOI etc.: 10.5194/bg-2018-353
ISSN: 1810-6285
Related URLs:
Projects: JPIO-MiningImpact
Contribution Number:
ProjectNumber
DSM35
Expeditions/Models/Experiments:
Date Deposited: 05 Sep 2018 09:25
Last Modified: 11 Sep 2018 13:50
URI: http://oceanrep.geomar.de/id/eprint/44142

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...