Predictive mapping of the nodule abundance and mineral resource estimation in the clarion-clipperton zone using artificial neural networks and classical geostatistical methods

Abstract

The licence areas for the exploration of manganese nodule fields in the equatorial Pacific Ocean cover 75,000 km2 each. The purpose of this study was to predict the nodule abundance of nodule fields over an entire licence area using artificial neural network statistics. Bathymetry and backscatter information of the seafloor and different derived datasets, as well as sampling point data (box core stations), were used as model input data. Based on the prediction results, mineral resources of manganese nodules at different cut-off grades were calculated and the estimated resources were classified according to international codes. In principle, the estimation of tonnages of metals such as nickel, copper, cobalt, manganese, molybdenum, etc. is also possible based on the prediction results and the average metal contents of the nodules.