Machine Learning System for Multimodal Seismic Search

Summary The current approach for seismic data quality control, which is identifying subsurface geological features and exploration mapping, requires manually scanning large volumes of 3D and 2D data, and displaying seismic slices one by one in seismic interpretation software. This approach is inefficient, subjective, and time consuming, as scanning terabytes of data takes weeks or months of the seismic interpreter’s time. In this paper we introduce a machine-learning (ML) driven approach where domain experts can use semantic, plausible ways to search all seismic data associated with the prompt queries. Our approach is based on advanced generative AI algorithms such as vision language models (VLMs), especially using multimodal contrastive learning, which has the unique capability of understanding and capturing the relationship between the seismic visual representation (image data) and their semantic meaning (textual data).