Accelerating High-Resolution Seismic Imaging by Using Deep Learning
Autor: | Linong Liu, Jianfeng Zhang, Qian Cheng, Yun Wang, Liu Wei |
---|---|
Rok vydání: | 2020 |
Předmět: |
seismic imaging
Computer science Geophysical imaging 02 engineering and technology high-resolution 010502 geochemistry & geophysics lcsh:Technology 01 natural sciences Computational science lcsh:Chemistry Set (abstract data type) Acceleration Dimension (vector space) Convergence (routing) 0202 electrical engineering electronic engineering information engineering General Materials Science lcsh:QH301-705.5 Instrumentation 0105 earth and related environmental sciences Fluid Flow and Transfer Processes Artificial neural network lcsh:T business.industry Process Chemistry and Technology Deep learning General Engineering Volume (computing) deep learning acceleration lcsh:QC1-999 Computer Science Applications lcsh:Biology (General) lcsh:QD1-999 lcsh:TA1-2040 020201 artificial intelligence & image processing Artificial intelligence lcsh:Engineering (General). Civil engineering (General) business lcsh:Physics |
Zdroj: | Applied Sciences Volume 10 Issue 7 Applied Sciences, Vol 10, Iss 2502, p 2502 (2020) |
ISSN: | 2076-3417 |
DOI: | 10.3390/app10072502 |
Popis: | The emerging applications of deep learning in solving geophysical problems have attracted increasing attention. In particular, it is of significance to enhance the computational efficiency of the computationally intensive geophysical algorithms. In this paper, we accelerate deabsorption prestack time migration (QPSTM), which can yield higher-resolution seismic imaging by compensating absorption and correcting dispersion through deep learning. This is implemented by training a neural network with pairs of small-sized patches of the stacked migrated results obtained by conventional PSTM and deabsorption QPSTM and then yielding the high-resolution imaging volume by prediction with the migrated results of conventional PSTM. We use an encoder-decoder network to highlight the features related to high-resolution migrated results in a high-order dimension space. The training data set of small-sized patches not only reduces the required high-resolution migrated result (for instance, only several inline is required) but leads to a fast convergence in training. The proposed deep-learning approach accelerates the high-resolution imaging by more than 100 times. Field data is used to demonstrate the effectiveness of the proposed method. |
Databáze: | OpenAIRE |
Externí odkaz: |