Dropout-Based Robust Self-Supervised Deep Learning for Seismic Data Denoising

Gui Chen

doi:10.1109/LGRS.2022.3167999

Dropout-Based Robust Self-Supervised Deep Learning for Seismic Data Denoising

2022-01-01

9

PRE

AI

DOI：10.1109/LGRS.2022.3167999

Original

Original request for help

Save

Abstract

En 中文

Incoherent noise suppression is an indispensable step in seismic data processing. Recently, deep learning (DL) methods have gained commendable success in seismic data denoising, one of which is the supervised DL denoising method using clean data as the training label, whereas the cost of obtaining clean data is high. We investigate a robust self-supervised DL denoising method without using clean data. Bernoulli-sampled training pairs of the raw noisy data produced by the dropout layer are served to train the NN, and a Monte Carlo (MC) self-integrated technique results in further improving the denoising quality of the trained NN during the testing. Compared with the f-x deconvolution (FXDECON), deep image prior (DIP), and sparse autoencoder (SAE) methods via synthetic and real data examples, the proposed method outperforms these methods for enhancing the signal-to-noise ratio (SNR) and reducing the signal loss.

Keywords:

Training

Noise reduction

Noise measurement

Electronics packaging

Artificial neural networks

Signal to noise ratio

Testing

Denoising

dropout

Monte Carlo (MC) self-ensemble

seismic

self-supervised deep learning (DL)

Dropout-Based Robust Self-Supervised Deep Learning for Seismic Data Denoising

Abstract

Journal

Organization