A machine learning approach to the potential-field method for implicit modeling of geological structures

• Published in: Computers & geosciences Vol. 103; pp. 173 - 182
• Main Authors: Gonçalves, Ítalo Gomes, Kumaira, Sissa, Guadagnin, Felipe
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.06.2017
• Subjects: 3D geological modeling; Compositional data analysis; Implicit modeling; Kriging; Machine learning; Potential field; 3D geological modeling; Potential field; Implicit modeling; Kriging; Machine learning; Compositional data analysis
• DOI: 10.1016/j.cageo.2017.03.015
• ISSN: 0098-3004

Implicit modeling has experienced a rise in popularity over the last decade due to its advantages in terms of speed and reproducibility in comparison with manual digitization of geological structures. The potential-field method consists in interpolating a scalar function that indicates to which side of a geological boundary a given point belongs to, based on cokriging of point data and structural orientations. This work proposes a vector potential-field solution from a machine learning perspective, recasting the problem as multi-class classification, which alleviates some of the original method's assumptions. The potentials related to each geological class are interpreted in a compositional data framework. Variogram modeling is avoided through the use of maximum likelihood to train the model, and an uncertainty measure is introduced. The methodology was applied to the modeling of a sample dataset provided with the software Move™. The calculations were implemented in the R language and 3D visualizations were prepared with the rgl package. •Machine learning technique for implicit geological modeling.•Potential field model recast as multi-class classification.•Probabilistic interpretation of the potential field.•Variogram modeling avoided through maximization of log-likelihood.