SeismiQB -- a novel framework for deep learning with seismic data
This addresses data processing bottlenecks for researchers in geophysics using deep learning, but it is incremental as it builds on existing methods for data handling.
The paper tackles the slow loading speed and lack of widely-used formats for seismic data, which hampers deep learning experimentation, by developing an open-source Python framework that provides tools for fast data loading, conversion, cropping, augmentation, and pairing with labels.
In recent years, Deep Neural Networks were successfully adopted in numerous domains to solve various image-related tasks, ranging from simple classification to fine borders annotation. Naturally, many researches proposed to use it to solve geological problems. Unfortunately, many of the seismic processing tools were developed years before the era of machine learning, including the most popular SEG-Y data format for storing seismic cubes. Its slow loading speed heavily hampers experimentation speed, which is essential for getting acceptable results. Worse yet, there is no widely-used format for storing surfaces inside the volume (for example, seismic horizons). To address these problems, we've developed an open-sourced Python framework with emphasis on working with neural networks, that provides convenient tools for (i) fast loading seismic cubes in multiple data formats and converting between them, (ii) generating crops of desired shape and augmenting them with various transformations, and (iii) pairing cube data with labeled horizons or other types of geobodies.