000145561 001__ 145561
000145561 005__ 20260112133347.0
000145561 0247_ $$2doi$$a10.1109/TGRS.2024.3458870
000145561 0248_ $$2sideral$$a140419
000145561 037__ $$aART-2024-140419
000145561 041__ $$aeng
000145561 100__ $$aWu, Yinghe
000145561 245__ $$aUnsupervised-learning stable inverse Q Filtering for seismic resolution enhancement
000145561 260__ $$c2024
000145561 5203_ $$aAffected by near-surface absorption, seismic wave energy attenuation and phase distortion greatly reduce the resolution and signal-to-noise ratio (SNR) of seismic data, causing changes in seismic attributes much greater than other factors. Inverse Q filtering is a common method to compensate for these undesirable effects. To overcome the drawbacks of the traditional inverse Q filtering, such as the difficulty of parameter selection and the instability of wave amplitude compensation, we propose a new unsupervised inverse Q filtering method in a deep learning (DL) framework, using a forward attenuation operator based on the seismic wave attenuation theory to drive the network. The filtering strategy does not require actual training labels and avoids the numerical instability of the amplitude compensation. First, we design a hybrid CNN-BiLSTM-Attention model for multivariate time series prediction, and then take the data to be compensated as input for the DL network and the compensated data as output. The output is then attenuated using a forward attenuation operator constructed from the near-surface Q model. After, the error between the attenuated data and the original input data is transmitted back to the DL network to modify the network output, and the error is minimized by optimizing the network parameters to generate the final compensation result. In the entire prediction process, there is no need to produce un-attenuated data labels, which achieves the effect of unsupervised learning. The results with synthetic and field data demonstrate that the unsupervised method can effectively and stably compensate for seismic signals. Compared to the classical inverse Q filtering, the proposed method improves the resolution and SNR of seismic records. Index Terms-Inverse Q filtering, forward attenuation operator, CNN-
000145561 540__ $$9info:eu-repo/semantics/closedAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000145561 590__ $$a8.6$$b2024
000145561 592__ $$a2.397$$b2024
000145561 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b25 / 366 = 0.068$$c2024$$dQ1$$eT1
000145561 591__ $$aIMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY$$b5 / 36 = 0.139$$c2024$$dQ1$$eT1
000145561 591__ $$aREMOTE SENSING$$b5 / 65 = 0.077$$c2024$$dQ1$$eT1
000145561 591__ $$aGEOCHEMISTRY & GEOPHYSICS$$b4 / 100 = 0.04$$c2024$$dQ1$$eT1
000145561 593__ $$aElectrical and Electronic Engineering$$c2024$$dQ1
000145561 593__ $$aEarth and Planetary Sciences (miscellaneous)$$c2024$$dQ1
000145561 594__ $$a13.6$$b2024
000145561 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000145561 700__ $$aPan, Shulin
000145561 700__ $$aLan, Haiqiang
000145561 700__ $$aChen, Yaojie
000145561 700__ $$0(orcid)0000-0002-3424-7744$$aBadal, José$$uUniversidad de Zaragoza
000145561 700__ $$aQin, Ziyu
000145561 7102_ $$12004$$2405$$aUniversidad de Zaragoza$$bDpto. Física Teórica$$cÁrea Física Teórica
000145561 773__ $$g62 (2024), 1-12$$pIEEE trans. geosci. remote sens.$$tIEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING$$x0196-2892
000145561 8564_ $$s10117779$$uhttps://zaguan.unizar.es/record/145561/files/texto_completo.pdf$$yVersión publicada
000145561 8564_ $$s3908016$$uhttps://zaguan.unizar.es/record/145561/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000145561 909CO $$ooai:zaguan.unizar.es:145561$$particulos$$pdriver
000145561 951__ $$a2026-01-12-13:17:41
000145561 980__ $$aARTICLE