Machine learning strategies for lithostratigraphic classification based on geochemical sampling data: A case study in area of Chahanwusu River, Qinghai Province, China

Based on the complex correlation between the geochemical element distribution patterns at the surface and the types of bedrock and the powerful capabilities in capturing subtle of machine learning algorithms, four machine learning algorithms, namely, decision tree (DT), random forest (RF), XGBoost (XGB), and LightGBM (LGBM), were implemented for the lithostratigraphic classification and lithostratigraphic prediction of a quaternary coverage area based on stream sediment geochemical sampling data in the Chahanwusu River of Dulan County, Qinghai Province, China. The local Moran's I to represent the features of spatial autocorrelations, and terrain factors to represent the features of surface geological processes, were calculated as additional features. The accuracy, precision, recall, and F1 scores were chosen as the evaluation indices and Voronoi diagrams were applied for visualization. The results indicate that XGB and LGBM models both performed well. They not only obtained relatively satisfactory classification performance but also predicted lithostratigraphic types of the Quaternary coverage area that are essentially consistent with their neighborhoods which have the known types. It is feasible to classify the lithostratigraphic types through the concentrations of geochemical elements in the sediments, and the XGB and LGBM algorithms are recommended for lithostratigraphic classification.