Machine Learning and Interpretation of Sub-Surface Architectures – MaLISSiA

Artificial intelligence and digital twins offer tremendous opportunities for modelling and understanding Earth systems. However, these new developments have mainly been applied to geophysical processes occurring within relatively well-constrained geometries (e.g., on earth surface) and they have yet to make a breakthrough in the characterization of sub-surface architectures, even though they determine the localization of sub-surface Earth processes. The difficulty to access sub-surface causes paramount epistemic uncertainties that result in original scientific locks, e.g., the dependencies to scale, time, and geophysical processes. These limitations are generally counterbalanced by expert interpretations that rely on human learning from outcrops and simulations. The search for more formal and automated solutions is challenging both the formalization of geological knowledge and the development of innovative artificial intelligence methods. The MaLISSiA project draws its inspiration from the geocognitive process developed by human learning and interpretation. It proposes a new paradigm for automatically interpreting and explaining sub-surface architectures. The project proposes to enable the training of machine learning algorithms by developing a corpus of interpreted geological references, based on both natural objects and process-based simulations that reproduce geological history. The concept will be proved for elementary structural objects and, in a more complete example, within the framework of the development of a digital twin of the Vadose Zone Observatory (OZNS).