Deep learning for irregularly and regularly missing data reconstruction

Abstract Deep learning (DL) is a powerful tool for mining features from data, which can theoretically avoid assumptions (e.g., linear events) constraining conventional interpolation methods. Motivated by this and inspired by image-to-image translation, we applied DL to irregularly and regularly miss...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xintao Chai, Hanming Gu, Feng Li, Hongyou Duan, Xiaobo Hu, Kai Lin
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/d4a830846aec4e548fbeee9a348402f9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d4a830846aec4e548fbeee9a348402f9
record_format	dspace
spelling	oai:doaj.org-article:d4a830846aec4e548fbeee9a348402f92021-12-02T16:23:10ZDeep learning for irregularly and regularly missing data reconstruction10.1038/s41598-020-59801-x2045-2322https://doaj.org/article/d4a830846aec4e548fbeee9a348402f92020-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-59801-xhttps://doaj.org/toc/2045-2322Abstract Deep learning (DL) is a powerful tool for mining features from data, which can theoretically avoid assumptions (e.g., linear events) constraining conventional interpolation methods. Motivated by this and inspired by image-to-image translation, we applied DL to irregularly and regularly missing data reconstruction with the aim of transforming incomplete data into corresponding complete data. To accomplish this, we established a model architecture with randomly sampled data as input and corresponding complete data as output, which was based on an encoder-decoder-style U-Net convolutional neural network. We carefully prepared the training data using synthetic and field seismic data. We used a mean-squared-error loss function and an Adam optimizer to train the network. We displayed the feature maps for a randomly sampled data set going through the trained model with the aim of explaining how the missing data are reconstructed. We benchmarked the method on several typical datasets for irregularly missing data reconstruction, which achieved better performances compared with a peer-reviewed Fourier transform interpolation method, verifying the effectiveness, superiority, and generalization capability of our approach. Because regularly missing is a special case of irregularly missing, we successfully applied the model to regularly missing data reconstruction, although it was trained with irregularly sampled data only.Xintao ChaiHanming GuFeng LiHongyou DuanXiaobo HuKai LinNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-18 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Xintao Chai Hanming Gu Feng Li Hongyou Duan Xiaobo Hu Kai Lin Deep learning for irregularly and regularly missing data reconstruction
description	Abstract Deep learning (DL) is a powerful tool for mining features from data, which can theoretically avoid assumptions (e.g., linear events) constraining conventional interpolation methods. Motivated by this and inspired by image-to-image translation, we applied DL to irregularly and regularly missing data reconstruction with the aim of transforming incomplete data into corresponding complete data. To accomplish this, we established a model architecture with randomly sampled data as input and corresponding complete data as output, which was based on an encoder-decoder-style U-Net convolutional neural network. We carefully prepared the training data using synthetic and field seismic data. We used a mean-squared-error loss function and an Adam optimizer to train the network. We displayed the feature maps for a randomly sampled data set going through the trained model with the aim of explaining how the missing data are reconstructed. We benchmarked the method on several typical datasets for irregularly missing data reconstruction, which achieved better performances compared with a peer-reviewed Fourier transform interpolation method, verifying the effectiveness, superiority, and generalization capability of our approach. Because regularly missing is a special case of irregularly missing, we successfully applied the model to regularly missing data reconstruction, although it was trained with irregularly sampled data only.
format	article
author	Xintao Chai Hanming Gu Feng Li Hongyou Duan Xiaobo Hu Kai Lin
author_facet	Xintao Chai Hanming Gu Feng Li Hongyou Duan Xiaobo Hu Kai Lin
author_sort	Xintao Chai
title	Deep learning for irregularly and regularly missing data reconstruction
title_short	Deep learning for irregularly and regularly missing data reconstruction
title_full	Deep learning for irregularly and regularly missing data reconstruction
title_fullStr	Deep learning for irregularly and regularly missing data reconstruction
title_full_unstemmed	Deep learning for irregularly and regularly missing data reconstruction
title_sort	deep learning for irregularly and regularly missing data reconstruction
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/d4a830846aec4e548fbeee9a348402f9
work_keys_str_mv	AT xintaochai deeplearningforirregularlyandregularlymissingdatareconstruction AT hanminggu deeplearningforirregularlyandregularlymissingdatareconstruction AT fengli deeplearningforirregularlyandregularlymissingdatareconstruction AT hongyouduan deeplearningforirregularlyandregularlymissingdatareconstruction AT xiaobohu deeplearningforirregularlyandregularlymissingdatareconstruction AT kailin deeplearningforirregularlyandregularlymissingdatareconstruction
_version_	1718384201825255424

Deep learning for irregularly and regularly missing data reconstruction

Ejemplares similares