Using machine learning classifiers together with discrimination diagrams for validation of rock classification labels

Rock classification based on chemical components is a common task in the geochemical domain. Literature recommends the Total Alkali and Silica (TAS) discrimination diagram for classifying igneous volcanic rocks by the sum of N a 2 O and K 2 O in relation to S i O 2 contents. This paper comparatively applies the TAS diagram and machine learning classification techniques to a collection of volcanic rocks from the GEOROC database. The study demonstrates a mismatch between the rock type labeled by experts in the database and rock types assigned by the TAS diagram. Despite this discrepancy, the experiments show that support vector machines are particularly promising for building decision systems for rock classification. Random forests, multi-layer perceptrons and K nearest neighbors are less suitable as rock classifiers in the study. • Automating the rock classification task is a vital challenge for geochemistry. • Support vector machines are particularly promising for rock classification. • We compared traditional TAS discrimination with machine learning classifiers. • We applied our Method to a subset of the GEOROC database.