Localized Smart Interpretation - a data driven semi-automatic geological modelling method

Abstract

Localised Smart interpretation (LSI) is a method that infers a statistical model, which describes a relation between the knowledge of a geologist (as quantified by geological interpretation) and the available information (such as geophysical data, well log data, etc.) that a geologist uses when he/she interprets. This model is then used to perform semi-automatic geological interpretation wherever the same kinds of attributes, as used for the initial interpretation, are available. The statistical model is inferred using a combination of a regularized least squares method and cross validation. In this study, we demonstrate the applicability of the method to predict the depth to a low resistivity subsurface layer, based on interpretations from a geological expert, using a 19- layered resistivity model obtained from inversion of airborne electromagnetic (SkyTEM) data. This study shows that LSI is capable of making prediction with great accuracy. The method is fast and is able to handle large amounts of data of different origin, which suggest that the method may become a very useful approach to assist in geological modelling, based on increasingly large amounts of data of different nature.