Importance of Spatial Autocorrelation in Machine Learning Modeling of Polymetallic Nodules, Model Uncertainty and Transferability at Local Scale.

Gazis, Iason-Zois and Greinert, Jens (2021) Importance of Spatial Autocorrelation in Machine Learning Modeling of Polymetallic Nodules, Model Uncertainty and Transferability at Local Scale. Open Access Minerals, 11 . Art.Nr. 1172. DOI 10.3390/min11111172.

[thumbnail of minerals-11-01172.pdf]
Preview
Text
minerals-11-01172.pdf - Published Version
Available under License Creative Commons: Attribution 4.0.

Download (10MB) | Preview

Supplementary data:

Abstract

Machine learning spatial modeling is used for mapping the distribution of deep-sea polymetallic nodules (PMN). However, the presence and influence of spatial autocorrelation (SAC) have not been extensively studied. SAC can provide information regarding the variable selection before modeling, and it results in erroneous validation performance when ignored. ML models are also problematic when applied in areas far away from the initial training locations, especially if the (new) area to be predicted covers another feature space. Here, we study the spatial distribution of PMN in a geomorphologically heterogeneous area of the Peru Basin, where SAC of PMN exists. The local Moran’s I analysis showed that there are areas with a significantly higher or lower number of PMN, associated with different backscatter values, aspect orientation, and seafloor geomorphological characteristics. A quantile regression forests (QRF) model is used using three cross-validation (CV) techniques (random-, spatial-, and cluster-blocking). We used the recently proposed “Area of Applicability” method to quantify the geographical areas where feature space extrapolation occurs. The results show that QRF predicts well in morphologically similar areas, with spatial block cross-validation being the least unbiased method. Conversely, random-CV overestimates the prediction performance. Under new conditions, the model transferability is reduced even on local scales, highlighting the need for spatial model-based dissimilarity analysis and transferability assessment in new areas.

Document Type: Article
Funder compliance: BMBF:03F0707A ; BMWi:03SX466B
Additional Information: This article belongs to the Special Issue "Exploration of Polymetallic Nodules".
Keywords: polymetallic nodules, spatial autocorrelation, cross-validation, model transferability
Research affiliation: OceanRep > GEOMAR > FB2 Marine Biogeochemistry > FB2-MG Marine Geosystems > DeepSea Monitoring
OceanRep > GEOMAR > FB2 Marine Biogeochemistry > FB2-MG Marine Geosystems
Main POF Topic: PT6: Marine Life
Refereed: Yes
Open Access Journal?: Yes
Publisher: MDPI
Related URLs:
Projects: JPIO-MiningImpact, MarTERA
Contribution Number:
Project
Number
DSM
49
Expeditions/Models/Experiments:
Date Deposited: 27 Oct 2021 13:18
Last Modified: 07 Feb 2024 15:48
URI: https://oceanrep.geomar.de/id/eprint/54296

Actions (login required)

View Item View Item