SparseTFNet: A Physically Informed Autoencoder for Sparse Time-Frequency Analysis of Seismic Data

The time-frequency (TF) analysis is an effective tool in seismic signal processing. The sparsity-based TF transforms have been widely used to obtain high localized TF representations in recent past years. These TF transforms formulate a sparse TF representation as an inverse optimization problem usi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2022, Vol.60, p.1-12
Main Authors: Yang, Yang, Lei, Youbo, Liu, Naihao, Wang, Zhiguo, Gao, Jinghuai, Ding, Jicai
Format: Article
Language:English
Subjects:
Analysis
Analytical models
Artificial neural networks
Autoencoder
Coders
compressed sensing (CS)
Data models
Decoding
Deep learning
deep learning (DL)
Fourier transforms
Frequency analysis
Frequency dependence
Information processing
Mathematical models
Modules
Neural networks
Offshore
Optimization
Representations
Seismic data
Signal processing
sparse time-frequency (TF) representation
Sparsity
Three-dimensional displays
Time-frequency analysis
Training
Transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The time-frequency (TF) analysis is an effective tool in seismic signal processing. The sparsity-based TF transforms have been widely used to obtain high localized TF representations in recent past years. These TF transforms formulate a sparse TF representation as an inverse optimization problem using simple mathematical models, which are typically based on a handcrafted prior knowledge. Unlike the traditional sparsity-based TF transforms, the supervised deep learning (DL)-based sparse TF representations do not require this prior knowledge and instead use a large amount of labeled dataset, which is difficult to label for seismic data. In this study, to bridge the gap between the traditional sparsity-based transforms and the supervised DL-based transforms, we propose a DL-based sparse TF analysis approach based on a physically informed autoencoder model, named the SparseTFNet. The proposed SparseTFNet includes two modules: a convolutional neural networks (CNN)-based encoder and a traditional inverse TF representation-based decoder. The CNN-based encoder is implemented by training the inverse optimization problem in the absence of the "ground-truth" TF representation, which can be trained with only seismic traces. The traditional inverse short-time Fourier transform (STFT) is utilized as the decoder module in this study, which is used as a physical constraint to ensure the high accuracy of the calculated TF representation. Finally, after training and validating the proposed model using the noise-free and noisy synthetic seismic traces, the model is applied to 3-D offshore seismic data. The results show that the proposed SparseTFNet model has good performance in the delineation of the depositional fluvial channels.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2022.3213851