WirMAE: Learning Well-Logging Interval Representations via Masked Autoencoders for Gas Hydrate Reservoir Characterization

Reservoir characterization (identification and parameter estimation) is critical for gas hydrate exploration and development. While machine learning (ML) techniques excel at capturing complex relationships in well-logging reservoir characterization, existing research mainly focuses on end-to-end supervised learning approaches relying on costly labeled data and lacking multitask learning capabilities. In this article, we introduce a self-supervised learning (SSL) framework to learn general representations of large-scale unlabeled Well-Logging Interval Representations via Masked Autoencoders (WirMAE). By incorporating channel-based attention mechanisms and a masked reconstruction pretraining strategy for variable tokens, WirMAE effectively extracts intrinsic multivariate correlations within logging data, enabling the generation of various missing log curves. The model is validated on data from globally distributed hydrate with diverse accumulation patterns. Compared to supervised deep learning methods and classical ML models, fine-turned WirMAE achieves superior reservoir identification accuracy (average $F1$ -score: 0.864) using only 1% labeled data in complex geological settings. Combined with domain expertise, WirMAE yields precise estimation of key reservoir parameters such as hydrate saturation and permeability, outperforming conventional petrophysical methods. Additionally, embedding visualizations and attention analyses reveal the inner workings of the model and its consistency with expert-driven geological interpretations. Our findings highlight the potential of SSL for advancing more accurate and transparent intelligent reservoir characterization using well-log data, indicating that the application of WirMAE could be extended to broader hydrocarbon reservoirs in the future.