FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4322732006> ?p ?o ?g. }

• W4322732006 endingPage "55" @default.
• W4322732006 startingPage "40" @default.
• W4322732006 abstract "SUMMARY Deep learning (DL) has achieved remarkable progress in geophysics. The most commonly used supervised learning (SL) framework requires massive labelled representative data to train artificial neural networks (ANNs) for good generalization. However, the labels are limited or unavailable for field seismic data applications. In addition, SL generally cannot take advantage of well-known physical laws and thus fails to generate physically consistent results. The weaknesses of standard SL are non-negligible. Therefore, we provide an open-source package for geophysics-steered self-supervised learning (SSL; taking application to seismic deconvolution as an example). With the wavelet given, we incorporate the convolution model into the loss function to measure the error between the synthetic trace generated by the ANN deconvolution result and the observed data, steering the ANN’s learning process toward yielding accurate and physically consistent results. We utilize an enhanced U-Net as the ANN. We determine a hard threshold operator to impose a sparse constraint on the ANN deconvolution result, which is challenging for current DL platforms because no layer is available. 2-D/3-D ANNs can naturally introduce spatial regularization to the ANN deconvolution results. Tests on synthetic data and 3-D field data with available well logs verify the effectiveness of the proposed approach. The approach outperforms the traditional trace-by-trace method in terms of accuracy and spatial continuity. Experiments on synthetic data validate that sparsity promotion matters for sparse recovery problems. Field data results of the proposed approach precisely identify the layer interfaces and mostly match well with the log. All codes and data are publicly available at https://doi.org/10.5281/zenodo.7233751 (Xintao Chai)." @default.
• W4322732006 created "2023-03-03" @default.
• W4322732006 creator A5005084143 @default.
• W4322732006 creator A5016566027 @default.
• W4322732006 creator A5031234889 @default.
• W4322732006 creator A5034441026 @default.
• W4322732006 creator A5070230075 @default.
• W4322732006 creator A5083028659 @default.
• W4322732006 date "2023-02-24" @default.
• W4322732006 modified "2023-10-15" @default.
• W4322732006 title "Geophysics-steered self-supervised learning for deconvolution" @default.
• W4322732006 cites W1498436455 @default.
• W4322732006 cites W1901616594 @default.
• W4322732006 cites W1979581468 @default.
• W4322732006 cites W1981142313 @default.
• W4322732006 cites W1981914807 @default.
• W4322732006 cites W1989082825 @default.
• W4322732006 cites W2024235597 @default.
• W4322732006 cites W2024392312 @default.
• W4322732006 cites W2053376610 @default.
• W4322732006 cites W2061069258 @default.
• W4322732006 cites W2078496737 @default.
• W4322732006 cites W2082261523 @default.
• W4322732006 cites W2091121667 @default.
• W4322732006 cites W2102589063 @default.
• W4322732006 cites W2103102567 @default.
• W4322732006 cites W2105536862 @default.
• W4322732006 cites W2111248943 @default.
• W4322732006 cites W2113143455 @default.
• W4322732006 cites W2128073813 @default.
• W4322732006 cites W2129556296 @default.
• W4322732006 cites W2129887242 @default.
• W4322732006 cites W2130464153 @default.
• W4322732006 cites W2147760898 @default.
• W4322732006 cites W2162312311 @default.
• W4322732006 cites W2172044679 @default.
• W4322732006 cites W2194775991 @default.
• W4322732006 cites W2325904566 @default.
• W4322732006 cites W2776585113 @default.
• W4322732006 cites W2894410771 @default.
• W4322732006 cites W2899283552 @default.
• W4322732006 cites W2900936384 @default.
• W4322732006 cites W2904005001 @default.
• W4322732006 cites W2911424749 @default.
• W4322732006 cites W2919115771 @default.
• W4322732006 cites W2923222994 @default.
• W4322732006 cites W2948230027 @default.
• W4322732006 cites W2955958579 @default.
• W4322732006 cites W2963322354 @default.
• W4322732006 cites W2964121744 @default.
• W4322732006 cites W2969722825 @default.
• W4322732006 cites W2970419158 @default.
• W4322732006 cites W2983807332 @default.
• W4322732006 cites W3001732295 @default.
• W4322732006 cites W3003922491 @default.
• W4322732006 cites W3004936775 @default.
• W4322732006 cites W3011674205 @default.
• W4322732006 cites W3012414209 @default.
• W4322732006 cites W3032032710 @default.
• W4322732006 cites W3047011887 @default.
• W4322732006 cites W3047035577 @default.
• W4322732006 cites W3081502560 @default.
• W4322732006 cites W3105374384 @default.
• W4322732006 cites W3111357769 @default.
• W4322732006 cites W3127080376 @default.
• W4322732006 cites W3136897673 @default.
• W4322732006 cites W3147262955 @default.
• W4322732006 cites W3159428095 @default.
• W4322732006 cites W3161445736 @default.
• W4322732006 cites W3163993681 @default.
• W4322732006 cites W3173375283 @default.
• W4322732006 cites W3183154679 @default.
• W4322732006 cites W3196492281 @default.
• W4322732006 cites W3201666041 @default.
• W4322732006 cites W3205073660 @default.
• W4322732006 cites W3208259041 @default.
• W4322732006 cites W3208869780 @default.
• W4322732006 cites W3210300097 @default.
• W4322732006 cites W3211225070 @default.
• W4322732006 cites W4206114143 @default.
• W4322732006 cites W4210741197 @default.
• W4322732006 cites W4226244456 @default.
• W4322732006 cites W4226266938 @default.
• W4322732006 cites W4293298413 @default.
• W4322732006 doi "https://doi.org/10.1093/gji/ggad015" @default.
• W4322732006 hasPublicationYear "2023" @default.
• W4322732006 type Work @default.
• W4322732006 citedByCount "1" @default.
• W4322732006 countsByYear W43227320062023 @default.
• W4322732006 crossrefType "journal-article" @default.
• W4322732006 hasAuthorship W4322732006A5005084143 @default.
• W4322732006 hasAuthorship W4322732006A5016566027 @default.
• W4322732006 hasAuthorship W4322732006A5031234889 @default.
• W4322732006 hasAuthorship W4322732006A5034441026 @default.
• W4322732006 hasAuthorship W4322732006A5070230075 @default.
• W4322732006 hasAuthorship W4322732006A5083028659 @default.
• W4322732006 hasConcept C11413529 @default.
• W4322732006 hasConcept C119857082 @default.

• next