Structuring and inspecting 3d anchors for seismic volume into hyperknowledge base in virtual reality

Abstract

Seismic data is a source of information geoscientists use to investigate underground regions to look for resources to explore. Such data are volumetric and noisy, and thus challenging to visualize, which motivated the research of new computational systems to assist the expert, such as visualization methods, signal processing, and machine learning models. We propose a system that aids geologists, geophysicists, and related experts in the domain in interpreting seismic data in virtual reality (VR). The system uses a hyperknowledge base (HKBase), which structures regions of interest (ROIs) as anchors with semantics from the user to the system and vice-versa. For instance, through the HKBase, the user can load and inspect the output from AI systems or give new inputs and feedback in the same way. We ran tests with experts to evaluate the system in their tasks to collect feedback and new insights on how the software could transform their routines. In accordance with our results, we claim we took one step forward for VR in the oil & gas industry by creating a valuable experience in the task of seismic interpretation.