Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion

TL;DR

This paper introduces SESDI, a novel deep learning method that effectively ingests large-scale, irregular seismic data without convolutional networks, significantly reducing processing time and outperforming existing models.

Contribution

SESDI is the first end-to-end learning approach for real seismic data that handles large-scale, irregular data efficiently without relying on convolutions.

Findings

Achieves SSIM over 0.8 on velocity inversion task

Outperforms U-Net on synthetic datasets

Demonstrates effective large-scale seismic data ingestion

Abstract

Traditional seismic processing workflows (SPW) are expensive, requiring over a year of human and computational effort. Deep learning (DL) based data-driven seismic workflows (DSPW) hold the potential to reduce these timelines to a few minutes. Raw seismic data (terabytes) and required subsurface prediction (gigabytes) are enormous. This large-scale, spatially irregular time-series data poses seismic data ingestion (SDI) as an unconventional yet fundamental problem in DSPW. Current DL research is limited to small-scale simplified synthetic datasets as they treat seismic data like images and process them with convolution networks. Real seismic data, however, is at least 5D. Applying 5D convolutions to this scale is computationally prohibitive. Moreover, raw seismic data is highly unstructured and hence inherently non-image like. We propose a fundamental shift to move away from convolutions and introduce SESDI: Set Embedding based SDI approach. SESDI first breaks down the mammoth task of large-scale prediction into an efficient compact auxiliary task. SESDI gracefully incorporates irregularities in data with its novel model architecture. We believe SESDI is the first successful demonstration of end-to-end learning on real seismic data. SESDI achieves SSIM of over 0.8 on velocity inversion task on real proprietary data from the Gulf of Mexico and outperforms the state-of-the-art U-Net model on synthetic datasets.