Centre de documentation
scientifique

Poststack seismic data denoising based on 3-D convolutional neural network / Dawei Liu in IEEE Transactions on geoscience and remote sensing, vol 58 n° 3 (March 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 3 (March 2020) . - pp 1598 - 1629 Titre : Poststack seismic data denoising based on 3-D convolutional neural network Type de document : Article/Communication Auteurs : Dawei Liu, Auteur ; Dawei Liu, Auteur ; Xiaokai Wang, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 1598 - 1629 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] apprentissage profond [Termes IGN] bruit blanc [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données localisées 3D [Termes IGN] échantillonnage [Termes IGN] filtrage du bruit [Termes IGN] filtre de Gauss [Termes IGN] post-stratification de données [Termes IGN] séisme [Termes IGN] sismologie Résumé : (Auteur) Deep learning has been successfully applied to image denoising. In this study, we take one step forward by using deep learning to suppress random noise in poststack seismic data from the aspects of network architecture and training samples. On the one hand, poststack seismic data denoising mainly aims at 3-D seismic data. We designed an end-to-end 3-D denoising convolutional neural network (3-D-DnCNN) that takes raw 3-D cubes as input in order to better extract the features of the 3-D spatial structure of poststack seismic data. On the other hand, denoising images with deep learning require noisy–clean sample pairs for training. In the field of seismic data processing, researchers usually try their best to suppress noise by using complex processes that combine different methods, but clean labels of seismic data are not available. In addition, building training samples in field seismic data has become an interesting but challenging problem. Therefore, we propose a training sample selection method that contains a complex workflow to produce comparatively ideal training samples. Experiments in this study demonstrate that deep learning can directly learn the ability to denoise field seismic data from selected samples. Although the building of the training samples may occur through a complex process, the experimental results of synthetic seismic data and field seismic data show that the 3-D-DnCNN has learned the ability to suppress the Gaussian noise and super-Gaussian noise from different training samples. Moreover, the 3-D-DnCNN network has better denoising performance toward arc-like imaging noise. In addition, we adopt residual learning and batch normalization in order to accelerate the training speed. After network training is satisfactorily completed, its processing efficiency can be significantly higher than that of conventional denoising methods. Numéro de notice : A2020-087 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2947149 Date de publication en ligne : 06/11/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2947149 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94661 [article]