Multi-level frameworks are increasingly used in knowledge representation to model scenarios involving not only types and their individuals, but also types of types, e.g. Species, Human, and me. Central to prominent approaches are powertypes and basetypes, which have not yet been analyzed for dependency. In this paper we analyze and formalize the dependence relations between these entities using Fine’s theory and logic of essence, derived notions for dependence, specialization, and rigidity, the Multi-Level Theory, and a geological use-case. Results reveal a web of dependencies that enhance understanding of these entities.

Three-dimensional geological modelling algorithms can generate multiple models that fit various mathematical and geometrical constraints. The results, however, are often meaningless to geological experts if the models do not respect accepted geological principles. This is problematic as use of the models is expected for various downstream purposes, such as hazard risk assessment, flow characterization, reservoir estimation, geological storage, or mineral and energy exploration. Verification of the geological reasonableness of such models is therefore important. If implausible models can be identified and eliminated, it will save countless hours and computational and human resources.To begin assessing geological reasonableness, we develop a framework for checking model consistency with geological knowledge and test it with a proof-of-concept tool. The framework consists of a space of consistent and inconsistent geological situations that can hold between a pair of geological objects, and the tool assesses a model's geological relations against the space to identify (in)consistent situations. The tool is successfully applied to several case studies as a first promising step toward automated assessment of geological reasonableness.

Abstract. With their growing volumes and uses, it is increasingly important to understand the interpretative and representational aspects of three-dimensional (3D) geosciences models. Such understanding will not only clarify key premises, inferences, and conclusions, but also enable more informed applications. Yet the epistemic foundations are often opaque. Critical information about assumptions, reasoning steps, and uncertainties typically remains tacit in the mind of the geomodeller. This lack of transparency hampers explainability, reproducibility, and broader utility. Current practices therefore 15 limit trust, knowledge transfer, and automation in geomodelling workflows. To address these limitations, we develop the POKIMON ontology, designed to make explicit the expert knowledge, interpretative choices, and conceptual structures underlying 3D geosciences models. POKIMON provides a formalized framework to represent how geological and geomdelling concepts are applied during model construction. Motivating use-cases, the ontological structure, and its application to the use[1]cases are presented to demonstrate utility and to advance automated knowledge-driven 3D geomodelling.

Abstract. 3D geological modelling algorithms can generate multiple models that fit various mathematical and geometrical constraints. The results, however, are often meaningless to geological experts if the models do not respect accepted geological principles. This is problematic given the expected use of the models for various downstream purposes, such as hazard risk assessment, flow characterization, reservoir estimation, natural storage, or mineral and energy exploration. Verification of the geological reasonableness of such models is therefore important: if implausible models can be identified and eliminated, it will save countless hours, computational and human resources, as well as minimize user problems. To begin assessing geological reasonableness, we develop a framework for consistency-checking and test it with a proof-of-concept tool. The framework consists of a space of consistent and inconsistent geological situations that can be held between a pair of geological objects, and the tool assesses a model against the space to identify (in)consistent situations. Both the framework and tool are successfully applied to several case studies as a promising first step toward automated assessment of geological reasonableness.

Implicit neural representation (INR) networks are emerging as a powerful framework for learning three-dimensional shape representations of complex objects. These networks can be used effectively to model three-dimensional geological structures from scattered point data, sampling geological interfaces, units, and structural orientations. The flexibility and scalability of these networks provide a potential framework for integrating many forms of geological data and knowledge that classical implicit methods cannot easily incorporate. We present an implicit three-dimensional geological modelling approach using an efficient INR network architecture, called GeoINR, consisting of multilayer perceptrons (MLPs). The approach expands on the modelling capabilities of existing methods using these networks by (1) including unconformities into the modelling; (2) introducing constraints on stratigraphic relations and global smoothness, as well as associated loss functions; and (3) improving training dynamics through the geometrical initialization of learnable network variables. These three enhancements enable the modelling of more complex geology, improved data fitting characteristics, and reduction of modelling artifacts in these settings, as compared to an existing INR approach to structural geological modelling. Two diverse case studies also are presented, including a sedimentary basin modelled using well data and a deformed metamorphic setting modelled using outcrop data. Modelling results demonstrate the method's capacity to fit noisy datasets, use outcrop data, represent unconformities, and efficiently model large geographic areas with relatively large datasets, confirming the benefits of the GeoINR approach.

Application of 3D technologies to the wide range of Geosciences knowledge domains is well underway. These have been operationalized in workflows of the hydrocarbon sector for a half-century, and now in mining for over two decades. In Geosciences, algorithms, structured workflows and data integration strategies can support compelling Earth models, however challenges remain to meet the standards of geological plausibility required for most geoscientific studies. There is also missing links in the institutional information infrastructure supporting operational multi-scale 3D data and model development. Canada in 3D (C3D) is a vision and road map for transforming the Geological Survey of Canada's (GSC) work practice by leveraging emerging 3D technologies. Primarily the transformation from 2D geological mapping, to a well-structured 3D modelling practice that is both data-driven and knowledge-driven. It is tempting to imagine that advanced 3D computational methods, coupled with Artificial Intelligence and Big Data tools will automate the bulk of this process. To effectively apply these methods there is a need, however, for data to be in a well-organized, classified, georeferenced (3D) format embedded with key information, such as spatial-temporal relations, and earth process knowledge. Another key challenge for C3D is the relative infancy of 3D geoscience technologies for geological inference and 3D modelling using sparse and heterogeneous regional geoscience information, while preserving the insights and expertise of geoscientists maintaining scientific integrity of digital products. In most geological surveys, there remains considerable educational and operational challenges to achieve this balance of digital automation and expert knowledge. Emerging from the last two decades of research are more efficient workflows, transitioning from cumbersome, explicit (manual) to reproducible implicit semi-automated methods. They are characterized by integrated and iterative, forward and reverse geophysical modelling, coupled with stratigraphic and structural approaches. The full impact of research and development with these 3D tools, geophysical-geological integration and simulation approaches is perhaps unpredictable, but the expectation is that they will produce predictive, instructive models of Canada's geology that will be used to educate, prioritize and influence sustainable policy for stewarding our natural resources. On the horizon are 3D geological modelling methods spanning the gulf between local and frontier or green-fields, as well as deep crustal characterization. These are key components of mineral systems understanding, integrated and coupled hydrological modelling and energy transition applications, e.g. carbon sequestration, in-situ hydrogen mining, and geothermal exploration. Presented are some case study examples at a range of scales from our efforts in C3D.

Three-dimensional structural geomodels are increasingly being used for a wide variety of scientific and societal purposes. Most advanced methods for generating these models are implicit approaches, but they suffer limitations in the types of interpolation constraints permitted, which can lead to poor modeling in structurally complex settings. A geometric deep learning approach, using graph neural networks, is presented in this paper as an alternative to classical implicit interpolation that is driven by a learning through training paradigm. The graph neural network approach consists of a developed architecture utilizing unstructured meshes as graphs on which coupled implicit and discrete geological unit modeling is performed, with the latter treated as a classification problem. The architecture generates three-dimensional structural models constrained by scattered point data, sampling geological units and interfaces as well as planar and linear orientations. The modeling capacity of the architecture for representing geological structures is demonstrated from its application on two diverse case studies. The benefits of the approach are (1) its ability to provide an expressive framework for incorporating interpolation constraints using loss functions and (2) its capacity to deal with both continuous and discrete properties simultaneously. Furthermore, a framework is established for future research for which additional geological constraints can be integrated into the modeling process.

Groundwater Information Network. Fed-prov-terr-int'l collaboration to share groundwater data online, using international standards; aligned with FGP, GOC Open Data Portal and Open Science, Google Dataset Search. Third program cycle, since 2010. https://gw-info.net

A new approach for constrained 3-D structural geological modelling using Graph Neural Networks (GNN) has been developed that is driven by a learning through training paradigm. Graph neural networks are an emerging deep learning model for graph structured data which can produce vector embeddings of graph elements including nodes, edges, and graphs themselves, useful for various learning objectives. In this work our graphs represent unstructured volumetric meshes. Our developed GNN architecture can generate spatially interpolated implicit scalar fields and discrete geological unit predictions on graph nodes (e.g. mesh vertices) to construct 3-D structural models. Interpolations are constrained by scattered point data sampling geological units, interfaces, as well as linear and planar orientation measurements. Interpolation constraints are incorporated into the neural architecture using loss functions associated with each constraint type that measure the error between the network’s predictions and data observations. This presentation will describe key concepts involved within this approach including vector embeddings, spatial-based convolutions on graphs, and loss functions for structural geological features. In addition, several modelling results will be given that demonstrate the capabilities and potential of GNNs for representing geological structures.