Preprints
https://doi.org/10.5194/gmd-2022-290
https://doi.org/10.5194/gmd-2022-290
Submitted as: development and technical paper
 | 
08 Mar 2023
Submitted as: development and technical paper |  | 08 Mar 2023
Status: a revised version of this preprint is currently under review for the journal GMD.

GeoINR 1.0: an implicit neural representation network for three-dimensional geological modelling

Michael Hillier, Florian Wellmann, Eric de Kemp, Ernst Schetselaar, Boyan Brodaric, and Karine Bédard

Abstract. 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 implicitly model three-dimensional geological structures from scattered point data, sampling geological interfaces, units, and orientations of structural features, provided appropriate loss functions associated with data and model constraints are employed during training. The flexibility and scalability of these networks provide a potential framework for integrating new forms of related geological data and knowledge that classical implicit methods cannot easily incorporate. We present a methodology using an efficient INR network architecture, called GeoINR, consisting of multilayer perceptrons (MLP) that advance existing implicit methods for structural geological modelling. The developed methodology expands on the modelling capabilities of existing methods using these networks by: (1) including unconformities into the modelling, (2) introducing constraints on stratigraphic relations as well as global smoothness along with their 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 existing INR frameworks for structural geological modelling. A provincial scale case study for the Lower Paleozoic portion of the Western Canadian Sedimentary Basin (WCSB) in Saskatchewan, Canada is presented to demonstrate the modelling capacity of the MLP architecture using the developed methodology. Modelling results illustrate the method’s capacity to fit noisy datasets, represent unconformities, and implicitly model large regional scale three-dimensional geological structures.

Michael Hillier et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on gmd-2022-290', Anonymous Referee #1, 24 May 2023
  • RC2: 'Comment on gmd-2022-290', Anonymous Referee #2, 06 Aug 2023
  • AC1: 'Response to both referees comments on gmd-2022-290', Michael Hillier, 17 Sep 2023

Michael Hillier et al.

Michael Hillier et al.

Viewed

Total article views: 737 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
538 183 16 737 5 4
  • HTML: 538
  • PDF: 183
  • XML: 16
  • Total: 737
  • BibTeX: 5
  • EndNote: 4
Views and downloads (calculated since 08 Mar 2023)
Cumulative views and downloads (calculated since 08 Mar 2023)

Viewed (geographical distribution)

Total article views: 708 (including HTML, PDF, and XML) Thereof 708 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 18 Sep 2023
Download
Short summary
Neural networks can be used effectively to model three-dimensional geological structures from point data, sampling geological interfaces, units, and orientations of structural features. Existing neural network approaches for this type of modelling are advanced by the efficient incorporation of unconformities, new knowledge inputs, and new techniques to improve data fitting. These advances permit the modelling of large scale geological structures with low fitting error using noisy datasets.