Controlled-source electromagnetic noise attenuation via deep convolutional neural network and high-quality sounding curve screening mechanism

Abstract

Strong noise is one of the biggest challenges in controlled-source electromagnetic (CSEM) exploration, which severely affects the quality of recorded signal. We have developed a novel and effective CSEM noise attenuation method that integrates deep convolutional neural network (DCNN) with a high-quality sounding curve screening mechanism. This method first employs DCNN to learn the large-scale noise characteristics of CSEM measured data and build a DCNN denoising model for attenuating the noise. Since some impulse noise remains after DCNN denoising, the high-quality sounding curve screening mechanism is innovatively applied to optimize the DCNN denoised data. The core of this method is the smoothness value (SV), which quantitatively evaluates the smoothness of the sounding curve (apparent resistivity curve). In effect, the mechanism segments the overall DCNN denoised data, and calculates the corresponding sounding curve and its smoothness value (SV) for each segment. The highest-quality sounding curve can be screened out by comparing the SV values of all curves, as well as obtaining the highest-quality data segment present in the overall DCNN denoised data. Finally, the proposed method is validated with both synthetic and field data, demonstrating its feasibility and effectiveness in attenuating large-scale CSEM noise. The quality of CSEM data, which is heavily affected by noise, is significantly improved after processing by the proposed method.