Support vector machine for 3D modelling from sparse geological information of various origins

Three-dimensional (3D) geological models are a powerful way of visualization, analysis and interpretation of geological information. However, manual modelling with available GIS tools is a challenging and time-consuming task. Here we propose the use of the support vector machine (SVM) in order to automate the creation of such models. We experiment with various input data and hyperparameters in order to demonstrate that the SVM can be efficiently applied in 3D geological reconstructions overcoming some limitations of previously used methods.