YYYoucai Yu

Youcai Yu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Youcai Yu has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Reverse time migration for distributed acoustic sensing data based on a pressure and strain-rate wave equation

    by Youcai Yu, Jidong Yang, Jianping Huang, Ning Qin, Kun Tian, Chong Zhao

    Distributed acoustic sensing (DAS), as a novel type of receiver, has been increasingly used in seismic exploration due to its low cost, small trace interval, and wide frequency coverage. Because the DAS system records the axial strain rate along the optical fiber, conventional seismic imaging methods cannot be directly applied and usually require a complex transition between the strain rate and particle velocity. To mitigate this issue, a direct imaging method for DAS data was developed using a modified reverse time migration (RTM) framework. First, a novel pressure and strain-rate acoustic wave equation was proposed for backward wavefield extrapolation. The DAS data were directly used as the boundary condition for this wave equation, which automatically corrected the incident-angle-dependent effects of DAS records during wavefield extrapolation and thus did not require data transformation. As in conventional RTM, the extrapolated pressure wavefields were chosen for the zero-lag correlation imaging condition. To enhance weak energy at great depth, source- and receiver-side illuminations were applied to compensate for deep image amplitudes. Examples from benchmark models and field data demonstrate the feasibility and adaptability of the proposed method to complex geologic settings.


  • Open Access

    Well-Constrained Conditional Generative Adversarial Network for Weak Seismic Signal Enhancement

    by Jiao Wang, Youcai Yu, Huaifeng Sun, Xuedong Ma, Guanqun Sheng, Peixue Liu, Yujie Chen

    Seismic images are critical for understanding subsurface geology and resource distribution. However, deep seismic signals are often extremely weak due to subsurface absorption and random noise, limiting imaging resolution and accurate geological interpretation. Generative adversarial networks (GANs) can enhance resolution and suppress noise, but their unconstrained generation may overfit noise, produce geologically inconsistent artifacts, and fail to recover high- frequency details. Furthermore, the high-dimensional and complex nature of seismic data increases the risk of mode collapse, reducing output diversity. To address these challenges, we propose a well-constrained conditional GAN (W-CGAN) that incorporates well-log data as a geophysical constraint. This conditional guidance explicitly directs the generator to learn a mapping from low- to high-resolution signals, reducing the solution space, mitigating adversarial training blind spots, and lowering mode collapse risk. Additionally, integrating a VGG- based perceptual loss enables the model to recover weak effective signal energy and high-frequency details. Experiments on synthetic datasets demonstrate that the proposed method substantially improves weak-signal recovery, noise suppression, and resolution enhancement, while applications to field seismic data further validate its robust generalization capability, even when trained exclusively on synthetic data.

  • Generative adversarial network-enhanced directional seismic wavefield decomposition and its application in reverse time migration

    by Jiaxing Sun, Jidong Yang, Jianping Huang, Youcai Yu, Yiwei Tian, Shanyuan Qin

    Reverse time migration (RTM) is an accurate method for imaging complex geologic structures without imposing any dip limitations. However, a large amount of high-amplitude low-frequency noise, which is mainly generated by the crosscorrelation of source and receiver wavefields propagating in the same directions, seriously contaminates the image quality. The causal imaging condition with separated up- and downgoing wavefields is an effective approach to reduce these low-frequency artifacts. Explicit up- and downgoing wavefield decomposition based on the Hilbert transform is computationally expensive due to additional wavefield extrapolation and storage for the imaginary parts. Directionally propagating wavefields have distinctive kinematic patterns such as traveltime and wavefront curvature, which provide us an opportunity to implement the wavefield decomposition using the statistical neural network method. Using extrapolated wavefields as the input and the decomposed up-, down-, left-, and rightgoing wavefields as the labeled data, we train a pair of generative adversarial networks to predict the directional wavefields. The training data sets are generated using seismic full-waveform modeling and explicit wavefield decomposition based on the Hilbert transform. Then, the decomposed directional wavefields are incorporated into a novel imaging condition that depends on the subsurface dip angles to compute the reflectivity perpendicular to the reflectors. Numerical experiments demonstrate that our method can produce accurate directional wavefield decomposition results and high-quality reflectivity images without low-wavenumber artifacts.


  • Multitask Deep Learning for Least-Squares Imaging: Seismic Reflectivity Inversion and Quantitative Error Analysis

    by Jiaxing Sun, Jidong Yang, Jianping Huang, Shanyuan Qin, Xuanhao Chen, Youcai Yu

    Least-squares migration (LSM) produces an accurate solution for subsurface reflectivity by solving a linear inverse problem, which can effectively mitigate the unbalanced subsurface illumination, suppress acquisition footprint and improve image resolution. It can be implemented in the data or image domain. Data-domain LSM requires intensive computations for many times of Born modeling and adjoint migration. By contrast, image-domain LSM requires a large memory storage for calculating and saving the Hessian matrix. Due to the ability of describing sophisticated nonlinear relations, the neural network can be used to approximate Hessian inverse by using the reverse time migration (RTM) image as the input and the true reflectivity model as the output. However, previous neural network-based LSMs mainly focused on the enhancement of image resolution and amplitude fidelity, but few on error and uncertainty analysis of network predicted images. We present a novel multi-task deep learning method for the image-domain LSM to simultaneously estimate Hessian inverse and evaluate kinematic and dynamic errors of network predicted results. We first use the RTM images along with migration velocity and source illumination as the network input and regard both the true reflectivity model and kinematic or dynamic error between predicted and labeled images as the output to train the network weights. Then, the L2-norm misfits of two terms are incorporated in the loss function to calculate the gradient to optimize the network trainable weights for producing an accurate LSM image. Numerical examples demonstrate that as the epoch of network training increases, the imaging accuracy of subsurface reflectors is gradually enhanced and the kinematic and dynamic errors of network predicted results are reduced, suggesting that the proposed multi-task deep learning method is effective in simultaneously predicting high-quality LSM image and conducting quantitative error analysis.


  • LsmGANs: Image-Domain Least-Squares Migration Using a New Framework of Generative Adversarial Networks

    by Jiaxing Sun, Jidong Yang, Jianping Huang, Youcai Yu, Zhenchun Li, Chong Zhao

    Compared with traditional adjoint migration, the least-squares migration (LSM) can effectively mitigate the unbalanced illumination and limited resolution associated with finite acquisition apertures, complex overburden structures and band-limited records. Data-domain LSM needs many times of Born modeling and adjoint migration to converge to a good solution, which is still challenging for large-scale 3D model under current computational capacity. To reduce computational cost and produce high-quality images, we directly approximate the Hessian inverse in the image-domain LSM using a new framework of generative adversarial networks (GANs). The migrated images, source illumination and migration velocity model are used as input data for the GANs, and the ground-truth reflectivity is utilized as the label data to train the network. Directly applying conventional GAN framework to implement the image-domain LSM leads to dislocated reflection events and incorrect images. To overcome this issue, we develop a new GAN framework that is more suitable for the Hessian approximation of image-domain LSM, which is named as LsmGANs. In the new framework, we use a max-pooling instead of convolution to downsample the feature maps to capture horizontal and vertical variations of reflectors. This enables us to map reflection events to correct location in downsampling. To address the lateral discontinuity of events in the predicted image from conventional GANs, we further apply multiple transform layers to strengthen feature transformation to guide Hessian approximation. Finally, we add the skip connection in the transform layer to enhance the information exchange of the feature channels and avoid the gradient vanishing problem to improve image resolution. Assembling predicted patches to construct a whole reflectivity image is a key step in the neural-network-based LSM. We investigate four strategies using different overlapping ratio and window functions to assemble the LSM patches and observe that less overlapping produces more patch-edge artifacts and the partition of unit with a Gaussian window has the best performance. Numerical experiments for synthetic and field data show that the proposed LsmGAN method can produce high-quality images with balanced amplitudes, reduced artifacts and improved resolution.


  • Full Waveform Inversion Using a High-Dimensional Local-Coherence Misfit Function

    by Youcai Yu, Jidong Yang, Jianping Huang, Weiqi Wang, Shanyuan Qin, Zhenchun Li

    Conventional full-waveform seismic inversion (FWI) tries to estimate a subsurface model that can accurately predict surface records by minimizing an L 2 -norm misfit between observed and synthetic data. If the initial model is far away from the true model, the cycle-skipping issue might occur and the L2-norm based FWI produces a spurious model. To mitigate this problem, we present a novel FWI scheme using a high-dimensional local coherence misfit function. A 2D/3D window is first used to extract local seismic waveform from the common-shot gathers. Then, we apply a normalized cross-correlation to measure the coherence of local synthetic and observed records, which is used as the misfit to iteratively update subsurface velocity model. The new misfit function enhances the contribution of phase fitting while reducing the amplitude contribution, which helps to increase the tolerance of FWI to an inaccurate initial velocity model. In addition, the computation of local waveform coherence along the temporal and spatial axes can adaptively balance the adjoint source amplitudes for strong near-offset reflections and weak far-offset refractions, which improves the low-wavenumber updates. Numerical experiments for synthetic and field data demonstrate that the proposed FWI scheme has a better tolerance to inaccurate starting models and is less sensitive to cycle-skipping issue compared with conventional FWI method.