MTL-FaultNet: Seismic Data Reconstruction Assisted Multitask Deep Learning 3-D Fault Interpretation

Seismic fault interpretation is of extraordinary significant for hydrocarbon reservoir characterization and drilling hazard mitigation. In recent years, deep learning-based seismic fault detection methods have been conducted actively. Considering efficiency and fault prediction consistency, the most appealing way is to train a 3-D segmentation network using synthetic seismic data with ground-truth fault structure. However, the differences in signal-to-noise ratio, resolution, and fault strike distribution between synthetic and real data can lead to inconsistent and unreliable prediction results. In this article, we propose a multitask deep learning-based seismic fault detection method, which takes seismic fault detection as the main task and 3-D seismic data reconstruction as the auxiliary task, named MTL-FaultNet. The auxiliary branch can provide suggestive information to the main branch, thus improving its performance. We also design two levels of multiscale modules and embedded attention mechanisms in the network, so as to improve the network's ability to focus on multiscale fault features and learn stable fault structures. Different weights are assigned to the loss for different tasks, with large and small weights on the main and auxiliary branches, respectively. We apply the proposed method to Netherlands offshore F3 seismic data and a land field seismic data collected from Tarim Basin with mainly strike-slip faults, and Poseidon 3-D seismic data. The proposed fault detection method is experimentally demonstrated on the improved network generalization and achieves reliable fault interpretation on field seismic data.