Stratal Zonation using Hierarchical Deep Learning: A method to reduce labelling workload for network training

Training neural networks to detect features on seismic requires care from the interpreter to label all the true positives present on a training image. But often, the interpreter is solely interested in detecting features in a single interval. This narrowed focus arises from either a preference for zones associated with commercial hydrocarbon systems, or because the features in the zone of interest are characteristically different than similar features in overlying or underlying zones. In either case, it would be desirable to create a volumetrically consistent subdivision of stratal layers before feature labeling work begins in earnest.

To achieve these ends, the authors introduce a novel way to perform stratal zonation using a Hierarchical Deep Learning (HDL) network. This approach simultaneously segments the entire seismic image into an arbitrary number of stratal zones using a multi-class network. Each stratal zone can then be further subdivided into a hierarchical arrangement of layers. Once trained, the HDL network’s inference can then be iteratively refined using an increasingly rich set of control points. On each successive iteration, the HDL network returns an inference that more closely approaches the geoscientist’s expert opinion.