Comment on egusphere-2025-5100

Abstract

Abstract. We present curlew, an open-source python package for structural geological modelling using neural fields. This modelling framework incorporates various local constraints (value, gradient, orientation and (in)equalities) and tailored global loss functions to ensure data-consistent and geologically realistic predictions. Random Fourier Feature (RFF) encodings are used to improve model convergence and facilitate stochastic uncertainty quantification, while simultaneously improving the model's ability to learn naturally periodic features such as folds. These advances are integrated into a software framework that allows incremental construction of complex geological models through temporally-linked neural fields, each representing a specific deposition, intrusion or faulting event. Significantly, this framework allows semi-supervised learning to integrate diverse unlabelled datasets (e.g., geochemistry, petrophysics), reducing interpretation bias and potentially improving model robustness. We describe and demonstrate these various capabilities using synthetic examples and real data from a faulted stratigraphic digital outcrop model from Newcastle, Australia.

Authors 8

1. Akshay Kamath

   Helmholtz-Zentrum Dresden-Rossendorf · Helmholtz Institute Freiberg for Resource Technology

   Affiliation as printed

   Helmholtz-Zentrum Dresden-Rossendorf, Helmholtz Institute Freiberg, Chemnitzer Str. 40, 09599 Freiberg, Germany

2. Samuel T. Thiele

   Helmholtz-Zentrum Dresden-Rossendorf · Helmholtz Institute Freiberg for Resource Technology

   Affiliation as printed

   Helmholtz-Zentrum Dresden-Rossendorf, Helmholtz Institute Freiberg, Chemnitzer Str. 40, 09599 Freiberg, Germany

3. Marie Moulard

   Université de Lorraine

   Affiliation as printed

   École Nationale Supérieure de Géologie (ENSG), Université de Lorraine, 54000 Nancy, France

4. Lachlan Grose

   Monash University

   Affiliation as printed

   School of Earth, Atmosphere and Environment, Monash University, Clayton, VIC, Australia

5. Raimon Tolosana-Delgado

   Helmholtz-Zentrum Dresden-Rossendorf · Helmholtz Institute Freiberg for Resource Technology

   Affiliation as printed

   Helmholtz-Zentrum Dresden-Rossendorf, Helmholtz Institute Freiberg, Chemnitzer Str. 40, 09599 Freiberg, Germany

6. M. J. Hillier

   Natural Resources Canada · Geological Survey of Canada

   Affiliation as printed

   Geological Survey of Canada, Natural Resources Canada, 601 Booth Street, Ottawa, ON K1A 0E8, Canada

7. Florian Wellmann Aachen Institute of Computational Geoscience

   Fraunhofer Research Institution for Energy Infrastructures and Geotechnologies IEG · RWTH Aachen University

   Affiliation as printed

   Fraunhofer Research Institution for Energy Infrastructures and Geothermal Systems (IEG), 44801 Bochum, Germany

   Institute of Computational Geoscience, Geothermics and Reservoir Geophysics (CG3), RWTH Aachen University, 52074 Aachen, Germany

8. Richard Gloaguen

   Helmholtz-Zentrum Dresden-Rossendorf · Helmholtz Institute Freiberg for Resource Technology

   Affiliation as printed

   Helmholtz-Zentrum Dresden-Rossendorf, Helmholtz Institute Freiberg, Chemnitzer Str. 40, 09599 Freiberg, Germany