Automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classification

Automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classification

The authors present an automated design approach to propose a new neural network architecture for seismic data analysis. The new architecture classifies multiple seismic reflection datasets at extremely low computational cost compared with conventional architectures for image classification.

Bibliographic Details
Main Authors: Zhi Geng, Yanfei Wang
Format: Article
Language:English
Published: Nature Publishing Group 2020-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-020-17123-6
id doaj-47df02517dab422f98ad99c5a7c03762
record_format Article
spelling doaj-47df02517dab422f98ad99c5a7c037622021-07-04T11:47:08ZengNature Publishing GroupNature Communications2041-17232020-07-0111111110.1038/s41467-020-17123-6Automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classificationZhi Geng0Yanfei Wang1Key Laboratory of Petroleum Resources Research, Institute of Geology and Geophysics, Chinese Academy of SciencesKey Laboratory of Petroleum Resources Research, Institute of Geology and Geophysics, Chinese Academy of SciencesThe authors present an automated design approach to propose a new neural network architecture for seismic data analysis. The new architecture classifies multiple seismic reflection datasets at extremely low computational cost compared with conventional architectures for image classification.https://doi.org/10.1038/s41467-020-17123-6
collection DOAJ
language English
format Article
sources DOAJ
author Zhi Geng
Yanfei Wang
spellingShingle Zhi Geng
Yanfei Wang
Automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classification
Nature Communications
author_facet Zhi Geng
Yanfei Wang
author_sort Zhi Geng
title Automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classification
title_short Automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classification
title_full Automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classification
title_fullStr Automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classification
title_full_unstemmed Automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classification
title_sort automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classification
publisher Nature Publishing Group
series Nature Communications
issn 2041-1723
publishDate 2020-07-01
description The authors present an automated design approach to propose a new neural network architecture for seismic data analysis. The new architecture classifies multiple seismic reflection datasets at extremely low computational cost compared with conventional architectures for image classification.
url https://doi.org/10.1038/s41467-020-17123-6
work_keys_str_mv AT zhigeng automateddesignofaconvolutionalneuralnetworkwithmultiscalefiltersforcostefficientseismicdataclassification
AT yanfeiwang automateddesignofaconvolutionalneuralnetworkwithmultiscalefiltersforcostefficientseismicdataclassification
_version_ 1714461233645617152

Similar Items