Exemplar-Guided Sedimentary Facies Modeling for Bridging Pattern Controllability Gap

Abstract

Inferring subsurface structure from sparse log data is crucial for geology. Recently, deep-learning-based methods, which provide sufficient prior knowledge from training sets, have been proven to aid in sedimentary facies modeling. However, these methods suffer from suboptimal controllability of the geological model, i.e., the expected geological pattern fails to be specified, resulting in unpredictable generated geological structures. To bridge the gap, we propose a novel Exemplar-Guided Facies Modeling (EGFM) approach, which synthesizes a facies model from log data given a pattern exemplar. The key insight in EGFM is to decouple the content and pattern in the target model, where the content refers to the match with well data, and the pattern is the properties of geological structures, such as fluvial course and shape. On the basis of well data as the hard condition, a pattern exemplar is introduced as the reference model for geological realizations. In addition to preserving the commonalities of the holistic geological pattern (from the geological image set), such as structural connectivity, the pattern details of the geological realization can be tuned through pattern exemplars. Moreover, we introduce an adaptive feature fusion block (AFB) to adaptively fuse the content and pattern features for more natural results. Extensive experimental results on two river data sets demonstrate that our proposed EGFM for conditional facies modeling achieves satisfying visual quality and pattern controllability.