Self-organizing map modelling and prospectivity mapping of surface geochemical data in Au and multi-metal mineral exploration: example from northern Finland

Abstract

Abstract

Regional till and weathered bedrock geochemical datasets provide a basis for data analysis and modelling in glaciated terrains. These large-scale surface geochemical datasets have great potential in mineral exploration, especially when machine learning and clustering methods are used to reduce the dimensionality of multivariate datasets. Here, self-organizing maps (SOMs) followed by k-means clustering were used to create SOMs of the target areas for initial modelling and prospectivity mapping of gold (Au) prospecting in central Lapland, northern Finland. Because the till and weathered bedrock datasets are legacy data, an effort was made to level the data between the map sheets. The targeting till geochemical dataset did not contain the typical indicator elements for Au. Instead, elements associated with the Au deposits, within the study area, were used. Indicator associations in this study were Ni–Co with possible Cu. Resulting elemental clusters from the SOMs were assigned as interesting clusters according to their distribution of elements. For the till, two potential clusters were identified: Ni–Co–Cr and Cu–V–Co. For the weathered bedrock, three clusters were specified: Ni–Co–Cr, V–Cu and Cu–Co. This study shows the potential of using legacy datasets for early targeting stages of mineral exploration, potentially reducing the footprint of mineral exploration.