S
Siwei Yu
Researcher at Harbin Institute of Technology
Publications - 23
Citations - 751
Siwei Yu is an academic researcher from Harbin Institute of Technology. The author has contributed to research in topics: Noise reduction & Computer science. The author has an hindex of 8, co-authored 17 publications receiving 331 citations. Previous affiliations of Siwei Yu include Tsinghua University & University of California, Los Angeles.
Papers
More filters
Journal ArticleDOI
Deep learning for denoising
Siwei Yu,Jianwei Ma,Wenlong Wang +2 more
TL;DR: Synthetic and field results indicate the potential applications of DL in automatic attenuation of random noise (with unknown variance), linear noise, and multiples.
Journal ArticleDOI
Deep learning for geophysics: Current and future trends
Siwei Yu,Jianwei Ma +1 more
TL;DR: A new data-driven technique, i.e., deep learning (DL), has attracted significantly increasing attention in the geophysical community and the collision of DL and traditional methods has had an impact on traditional methods.
Journal ArticleDOI
Interpolation and denoising of high-dimensional seismic data by learning a tight frame
TL;DR: In this article, the authors studied an application of the data-driven tight frame (DDTF) method to noise suppression and interpolation of high-dimensional seismic data, where instead of choosing a model beforehand (for example, a family of lines, parabolas or curvelets) to fit the data, the DDTF derives the model from the data itself in an optimum manner.
Journal ArticleDOI
Monte Carlo data-driven tight frame for seismic data recovery
TL;DR: This work has designed a new patch selection method for DDTF seismic data recovery to accelerate the filter bank training process in DDTF, while doing less damage to the recovery quality.
Journal ArticleDOI
Complex Variational Mode Decomposition for Slop-Preserving Denoising
Siwei Yu,Jianwei Ma +1 more
TL;DR: The motivation behind this paper is to overcome the potential low performance of empirical mode decomposition (EMD) for energy preservation of the steeply dipping events when used for noise attenuation, and low resolution when using for signal decomposition.