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.
Highlights
The spatial distribution of deep-sea polymetallic nodules (PMN) is currently of high interest due to their high metal content of Mn, Fe, Ni, Co, Cu, or Li
This paper addresses the presence of spatial autocorrelation (SAC) in the PMN distribution of a specific site and how this could influence the results in the various modelling steps of the machine learning (ML) workflow by studying: (a) The use of SAC as source information for the feature selection before modeling
Similar to the backscatter entropy (BSE), the aspect of the seafloor surface plays a role in H-H clustering, as areas with higher numbers of PMN tend to be north-faced oriented
Summary
The spatial distribution of deep-sea polymetallic nodules (PMN) is currently of high interest due to their high metal content of Mn, Fe, Ni, Co, Cu, or Li. The European Union alone will need 60 times more lithium and 15 times more cobalt by 2050 than today [3] for this transition. Deep-sea resources such as PMN could support this transition, with predictive spatial mapping having a key role in mining-block prioritization. PMN spatial mapping advanced by using autonomous underwater vehicles (AUVs) to acquire large volumes of hydroacoustic and image data allows for high-resolution seafloor reconstruction at meter and even down to centimeter scales. The quantitative analysis of images enlightens the PMN distribution, narrowing the spatial gap that arises from the sparse ground-truth box-corer samples (usually > 1.8 km) with very limited sampling area (0.25 m2) [4,5,6,7,8,9]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
