Objective classification of high‐resolution geophysical data: Empowering the next generation of mineral exploration in Sierra Leone

Abstract In 2019, a nationwide airborne geophysical survey of Sierra Leone was flown at 150 m nominal line spacing and 50 m nominal terrain clearance. Contractual deliverables included magnetic, radiometric and supporting data streams. The primary aim of the geophysical survey was to provide a national geoscientific benchmark for resource management by the National Minerals Agency and to encourage foreign investment in the rich mining potential of Sierra Leone. Geophysical interpretation is often highly subjective. This can be helpful when an interpreter is skilled in the project area and exploration targets being sought but can be constraining and even dangerous when exploring new areas, and for new commodities. Objective classification tools can challenge interpretive bias and enhance geological understanding, both locally and regionally. We present self‐organizing maps and neural network products generated from the Sierra Leone geophysical dataset which both confirm and challenge the validity of conventional, subjective interpretation workflows. We demonstrate the usefulness of self‐organizing maps as a tool for inferring complementary geological information and show some initial results of convolution neural network classification of a reduced‐to‐equator grid to locate magnetic lineaments in plan and in depth. Moreover, we show initial results of self‐organizing map clustering as a tool for joint analysis of multiphysics datasets and construction of a pseudolithological cluster map.