A Deep Convolutional Network for Seismic Shot-Gather Image Quality Classification

TL;DR

This paper presents a CNN-based method for classifying seismic shot-gather image quality, achieving high accuracy on a new manually labeled dataset to improve seismic data processing.

Contribution

Introduces a new labeled dataset and a CNN model for seismic shot-gather quality classification, advancing automated seismic data quality assurance.

Findings

F1-score of 93.56% on test set

Effective CNN model for seismic quality prediction

New dataset with 6,613 labeled examples

Abstract

Deep Learning-based models such as Convolutional Neural Networks, have led to significant advancements in several areas of computing applications. Seismogram quality assurance is a relevant Geophysics task, since in the early stages of seismic processing, we are required to identify and fix noisy sail lines. In this work, we introduce a real-world seismogram quality classification dataset based on 6,613 examples, manually labeled by human experts as good, bad or ugly, according to their noise intensity. This dataset is used to train a CNN classifier for seismic shot-gathers quality prediction. In our empirical evaluation, we observe an F1-score of 93.56% in the test set.