Learning to Decouple and Generate Seismic Random Noise via Invertible Neural Network

• Published in: IEEE transactions on geoscience and remote sensing Vol. 61; p. 1
• Main Authors: Meng, Chuangji, Gao, Jinghuai, Tian, Yajun, Li, Zhen
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Attenuation; Bias; Couplings; Data analysis; Data Augmentation; Data models; Data processing; Datasets; Decoupling; Deep learning; Invertible Neural Network; Neural networks; Noise; Noise Decoupling; Noise Generation; Random noise; Random Noise Attenuation; Sample Generation; Seismic data; Seismic data processing; Task analysis; Training; Wavelet transforms

Recovering the useful signal from seismic field data is critical in seismic data processing. Seismic field data are usually coupled by a useful signal and field noise (random noise with unknown distribution), making them difficult to decouple. Unfortunately, subject to the assumption biases of data...