Journal
NATURE COMMUNICATIONS
Volume 11, Issue 1, Pages -Publisher
NATURE PORTFOLIO
DOI: 10.1038/s41467-020-17123-6
Keywords
-
Categories
Funding
- Key Research Program of the Institute of Geology & Geophysics, CAS [IGGCAS-201903]
- Original Innovation Program of CAS [ZDBS-LY-DQC003]
- National Key R & D Program of the Ministry of Science and Technology of China [2018YFC0603500, 2018YFC1504203]
Ask authors/readers for more resources
Geoscientists mainly identify subsurface geologic features using exploration-derived seismic data. Classification or segmentation of 2D/3D seismic images commonly relies on conventional deep learning methods for image recognition. However, complex reflections of seismic waves tend to form high-dimensional and multi-scale signals, making traditional convolutional neural networks (CNNs) computationally costly. Here we propose a highly efficient and resource-saving CNN architecture (SeismicPatchNet) with topological modules and multiscale-feature fusion units for classifying seismic data, which was discovered by an automated data-driven search strategy. The storage volume of the architecture parameters (0.73 M) is only similar to 2.7 MB, similar to 0.5% of the well-known VGG-16 architecture. SeismicPatchNet predicts nearly 18 times faster than ResNet-50 and shows an overwhelming advantage in identifying Bottom Simulating Reflection (BSR), an indicator of marine gas-hydrate resources. Saliency mapping demonstrated that our architecture captured key features well. These results suggest the prospect of end-to-end interpretation of multiple seismic datasets at extremely low computational cost.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available