Enhancing Seismic Feature Quality with Transformer-Based Models for Mud Weight Prediction

This study presents a seismic transformer model designed to enhance the accuracy of mud weight prediction for drilling operations in the overpressured formation. By analysis of seismic data that implicitly characterize formation pressure, the model helps prevent blowouts, well collapses, mud leaks, and expensive managed pressure drilling. A dataset from some oil filed is used to validate this approach, demonstrating the potential for improved subsurface pressure prediction. The workflow processes post-stack time migrated seismic cubes as sequences of seismic traces. Each trace is segmented into samples in the target geological horizon. A Vision Transformer Masked Autoencoder (ViTMAE)-based model extracts robust features by reconstructing masked portions of traces, leveraging seismic data's inherent pressure-related signals. Incremental Principal Component Analysis (IPCA) compresses the extracted features into smaller dimensions. The model ties seismic and spatial characteristics with a mud weight prediction. The seismic transformer model, trained with a 75% masking ratio and mean squared error loss, generated 96 encoded features, which were reduced to 24 principal components using IPCA. This compression retained 90% of the encoded information, preserving crucial seismic characteristic of the formation pressure state while ensuring computational efficiency with batch processing. By better capturing the relationship between seismic data and formation pressure, the model allows for improved mud weight predictions, reducing the risk of operational hazards and unnecessary drilling costs. Statistical tests further confirm the geological significance of the extracted features, demonstrating their ability to represent subsurface pressure conditions accurately. This work introduces a novel adaptation of ViTMAE for seismic data processing in drilling operations, explicitly connecting seismic feature extraction to formation pressure modeling. The study provides a practical framework for engineers to improve mud weight prediction, enhancing safety and cost-efficiency in drilling.