Deep learning applied to seismic attribute computation
| Autor: | Antoine Victor Applolinaire Vial-Aussavy, S. Ahmad Zamanian, Francesco Menapace, Jeremy Vila, Donald Paul Griffith, R. David Potter, John Solum |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
010504 meteorology & atmospheric sciences
Artificial neural network Computer science business.industry Computation Deep learning Seismic attribute Geology Pattern recognition 010502 geochemistry & geophysics 01 natural sciences Convolutional neural network Interpretation (model theory) Geophysics Spectral analysis Artificial intelligence business Order of magnitude 0105 earth and related environmental sciences |
| Zdroj: | Interpretation. 7:SE141-SE150 |
| ISSN: | 2324-8866 2324-8858 |
| DOI: | 10.1190/int-2018-0227.1 |
| Popis: | We have trained deep convolutional neural networks (DCNs) to accelerate the computation of seismic attributes by an order of magnitude. These results are enabled by overcoming the prohibitive memory requirements typical of 3D DCNs for segmentation and regression by implementing a novel, memory-efficient 3D-to-2D convolutional architecture and by including tens of thousands of synthetically generated labeled examples to enhance DCN training. Including diverse synthetic labeled seismic in training helps the network generalize enabling it to accurately predict seismic attribute values on field-acquired seismic surveys. Once trained, our DCN tool generates attributes with no input parameters and no additional user guidance. The DCN attribute computations are virtually indistinguishable from conventionally computed attributes while computing up to 100 times faster. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|