Uncertainty assessment in unsupervised machine-learning methods for deepwater channel seismic facies using outcrop-derived 3D models and synthetic seismic data

Abstract

Unsupervised machine-learning (ML) techniques have been widely applied to analyze seismic reflection data, including the identification of seismic facies and structural features. However, interpreting the resulting clusters often relies on geoscientists’ expertise, necessitating a robustness assessment of these methods. To evaluate their reliability, synthetic data generated from an actual outcrop model are used to demonstrate how two unsupervised methods, self-organizing maps (SOMs) and generative topographic maps (GTMs), cluster deepwater channel-related seismic facies and then measure the associated error. Six seismic attributes, comprising root-mean-square amplitude, instantaneous envelope, peak magnitude, and spectral decomposition frequencies at 20, 40, and 55 Hz, served as input variables. Geobodies are assigned to each cluster formed, and the error in facies clustering is quantified by comparing the actual 3D model with the facies grouped by ML methods on a voxel-by-voxel basis. This allowed for error quantification and the computation of metrics such as F1 score and accuracy through correlation matrices. Key findings reveal that (1) GTM and SOM exhibit similar performance, with a clustering configuration of 81 for GTM slightly outperforming others. (2) Error rates are approximately 2% for the predominant facies (background shale) but significantly higher for individual channel-related facies, suggesting that channel clusters might represent multiple facies. (3) Resolution and imbalanced data distribution impact seismic facies predictability, resulting in nonuniqueness in cluster generation. (4) Using synthetic seismic data proved valuable for experimenting with different unsupervised MLs, highlighting the need for assessing uncertainty in these methods, given their implications for crucial economic decisions reliant on reservoir interpretation, modeling, and volumetric estimations.