| Title | Three-dimensional structural geological modeling using graph neural networks |
| |
| Author | Hillier, M ;
Wellmann, F; Brodaric, B; de Kemp, E; Schetselaar, E |
| Source | Mathematical Geosciences 2021 p. 1-25, https://doi.org/10.1007/s11004-021-09945-x  Open Access |
| Image |  |
| Year | 2021 |
| Alt Series | Natural Resources Canada, Contribution Series 20200743 |
| Publisher | Springer |
| Document | serial |
| Lang. | English |
| Media | paper; digital; on-line |
| File format | pdf; html |
| Subjects | structural geology; Science and Technology; Nature and Environment; bedrock geology; structural features; models; modelling; geometric analyses; Methodology; Classification |
| Illustrations | schematic representations; 3-D diagrams; 3-D models; tables; models |
| Program | Open Geoscience |
| Released | 2021 06 30 |
| Abstract | 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. |
| Summary | (Plain Language Summary, not published)
A new 3D geological modelling framework using a geometric deep learning approach has been developed. Compared with existing geological modelling
approaches the presented approach permits new forms of data and knowledge to be incorporated into generating 3D geological models, does not impose modelling assumptions that can compromise modelling, and produces reasonable models from noisy
datasets. A Graph Neural Network (GNN) is developed and applied to two diverse geological datasets to demonstrate its modelling performance. |
| GEOSCAN ID | 328099 |
|
|