Skip to main content

IMIS

A new integrated search interface will become available in the next phase of marineinfo.org.
For the time being, please use IMIS to search available data

 

[ report an error in this record ]basket (0): add | show Print this page

Importance of spatial autocorrelation in machine learning modeling of polymetallic nodules, model uncertainty and transferability at local scale
Gazis, I.-Z.; Greinert, J. (2021). Importance of spatial autocorrelation in machine learning modeling of polymetallic nodules, model uncertainty and transferability at local scale. Minerals 11(11): 1172. https://dx.doi.org/10.3390/min11111172
In: Minerals. MDPI: Basel. e-ISSN 2075-163X, more
Peer reviewed article  

Available in  Authors 

Keyword
    Marine/Coastal
Author keywords
    polymetallic nodules; spatial autocorrelation; cross-validation; model transferability

Authors  Top 
  • Gazis, I.-Z.
  • Greinert, J., more

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.

All data in the Integrated Marine Information System (IMIS) is subject to the VLIZ privacy policy Top | Authors