This is a review paper which provides an understanding of advanced approaches in geological modelling for the geoscience community currently used in modelling subsurface resources and for solving similar challenges in heterogeneous pattern modelling in computer science.
Modern geoscience has become a data-rich field where many problems are related to identifying/generate realistic patterns from data to predict nature. Machine learning among many other modelling approaches is not an ideal remedy but is probably the most promising one. Although it has its own drawbacks and limitations. Recent rapid advances in the newly developed generation of learning-based algorithms open more opportunities for geoscience modelling to overcome some limitations of the spatial statistics to tackle the challenge of model calibration and prediction when large volumes of data and domain knowledge to account for.
We are going to focus on the four specific questions inherent to geological modelling:
- how to represent geological realism of the modelled patterns;
- how to identify and preserve explicit and implicit dependencies between geological properties;
- what are the principle model controls that driving the geological system performance and how to parameterise them;
- how to establish the right level of model diversity to provide the necessary predictive power in the forecast of the geological system behaviour.