Convolutional encoder decoder network for the removal of coherent seismic noise

TL;DR

This paper introduces a convolutional encoder-decoder neural network to effectively remove coherent seismic noise from data, preserving essential information for subsurface analysis, offering an alternative to traditional filtering methods.

Contribution

The paper presents a novel deep learning approach using convolutional encoder-decoder architecture for seismic noise removal, improving data quality without losing critical information.

Findings

Effective noise removal demonstrated on seismic data

Preserves important subsurface information

Outperforms traditional notch filtering methods

Abstract

Seismologists often need to gather information about the subsurface structure of a location to determine if it is fit to be drilled for oil. However, there may be electrical noise in seismic data which is often removed by disregarding certain portions of the data with the use of a notch filter. Instead, we use a convolutional encoder decoder network to remove such noise by training the network to take the noisy shot record as input and remove the noise from the shot record as output. In this way, we retain important information about the data collected while still removing coherent noise in seismic data.