This study proposes a method for generating three-dimensional geological models from text and rock outcrop images. Through multiple experimental cases, it has been proved that by using this method, a three-dimensional geological model corresponding to the geological structure can be generated based on the language descriptions of geologists and the actual rock images. This method enables geologists to directly develop geological structural hypotheses from a three-dimensional perspective.

This study proposes a semi-supervised learning algorithm using pseudo-labels for 3D geological modelling. We establish a 3D geological model using borehole data from a complex real urban local survey area in Shenyang and make an uncertainty analysis of this model. The method effectively expands the sample space, which is suitable for geomodelling and uncertainty analysis from boreholes. The modelling results perform well in terms of spatial morphology and geological semantics.

To robustly train and test automated methods in the geosciences, we need to have access to large numbers of examples where we know the answer. We present a suite of synthetic 3D geological models with their gravity and magnetic responses that allow researchers to test their methods on a whole range of geologically plausible models, thus overcoming one of the fundamental limitations of automation studies.