Abstract
Machine learning-based seismic processing models are typically trained separately to perform seismic processing tasks (SPTs) and, as a result, require plenty of high-quality training data. However, preparing training data sets is not trivial, especially for supervised learning (SL). Despite the variability in seismic data across different types and regions, some general characteristics are shared, such as their sinusoidal nature and geometric texture. To learn the shared features and thus, quickly adapt to various SPTs, we develop a unified paradigm for neural network-based seismic processing, called Meta-Processing, that uses limited training data for meta learning a common network initialization, which offers universal adaptability features. The proposed Meta-Processing framework consists of two stages: meta-training and meta-testing. In the former, each SPT is treated as a separate task and the training dataset is divided into support and query sets. Unlike conventional SL methods, here, the neural network (NN) parameters are updated by a bilevel gradient descent from the support set to the query set, iterating through all tasks. In the meta-testing stage, we also utilize limited data to fine-tune the optimized NN parameters in an SL fashion to conduct various SPTs, such as denoising, interpolation, ground-roll attenuation, image enhancement, and velocity estimation, aiming to converge quickly to ideal performance. Extensive numerical experiments are conducted to assess the effectiveness of Meta-Processing on both synthetic and real-world data. The findings reveal that our approach leads to a substantial improvement in the convergence speed and predictive performance of the NN.
