Yaxing Li

Yaxing Li

Auto-generated profile, based on publicly available information

Yaxing Li

Key Laboratory of Earth Exploration and Information Techniques, Ministry of Education, Chengdu University of Technology, Chengdu, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 September 2022 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YLYaxing Li
Yaxing Li
XJXiaofeng Jia
Xiaofeng Jia
XWXinming Wu
Xinming Wu
ZGZhicheng Geng
Zhicheng Geng
Reverse time migration (RTM) is a technique used to obtain high-resolution images of underground reflectors; however, this method is computationally intensive when dealing with large amounts of seismic data. Multisource RTM can significantly reduce the computational cost by processing multiple shots simultaneously. However, multisource-based methods frequently result in crosstalk artifacts in the migrated images, causing serious interference in the imaging signals. Plane-wave migration, as a mainstream multisource method, can yield migrated images with plane waves in different angles by implementing phase encoding of the source and receiver wavefields; however, this method frequently requires a trade-off between computational efficiency and imaging quality. We propose a method based on deep learning for removing crosstalk artifacts and enhancing the image quality of plane-wave migration images. We designed a convolutional neural network that accepts an input of seven plane-wave images at different angles and outputs a clear and enhanced image. We built over 500 $1024\,\times \, 256$ velocity models, and employed each of them using plane-wave migration to produce raw images at 0°, ±10°, ±20°, and ±30° as input of the network. Labels are high-resolution images computed from the corresponding reflectivity models by convolving with a Ricker wavelet. Random sub-images with a size of $512\,\times \, 128$ were used for training the network. Numerical examples demonstrated the effectiveness of the trained network in crosstalk removal and imaging enhancement. The proposed method is superior to both the conventional RTM and plane-wave RTM (PWRTM) in imaging resolution. Moreover, the proposed method requires only seven migrations, significantly improving the computational efficiency. In the numerical examples, the processing time required by our method was approximately 1.6% and 10% of that required by RTM and PWRTM, respectively.

12 September 2022 in Geophysics
Verified
Journal Article
Closed access
YYYuwei Yu
Yuwei Yu
YLYaxing Li
Yaxing Li
XWXinming Wu
Xinming Wu
XJXiaofeng Jia
Xiaofeng Jia
One advantage of one-way wave equation-based migration is its low computational cost. However, due to the limited wavefield propagation angle, it is difficult to use one-way wave equation-based migration for high-precision imaging of structures with large inclinations due to issues such as inaccurate amplitudes and migration image artifacts. In addition, when the model has large horizontal velocity differences, it is difficult for the one-way wave propagator to calculate an accurate wavefield phase. Reverse time migration (RTM) based on the two-way wave propagator has a high resolution and avoids the issues associated with one-way wave propagators; however, it has a high computational cost in practical applications. We develop a convolutional neural network (CNN) application mode that improves one migration method by learning from another one and design a CNN with a structure similar to U-net that combines the advantages of both migration methods. The CNN label is the RTM result, and the corresponding input is the result of one-way wave migration with a generalized screen propagator (GSP). The trained CNN model improves the amplitude in the one-way wave migration image and removes the errors caused by large lateral velocity perturbations. Moreover, by maintaining the high migration calculation efficiency, our CNN model allows for a high resolution, few artifacts, and accurate images of steep structures in the one-way wave migration result. With our method, the accuracy of the one-way wave migration result is close to that of the RTM result. The use of GSP-based migration in our CNN model rather than conventional RTM to generate prospecting images can considerably reduce the calculation costs.

24 May 2022 in Geophysics
Verified
Journal Article
Closed access
XWXinming Wu
Xinming Wu
YLYaxing Li
Yaxing Li
PSPaphop Sawasdee
Paphop Sawasdee
Seismic flattening maps a seismic volume from the original space in depth (or two-way traveltime) to the Wheeler domain in geologic time where all of the seismic reflections are horizontally aligned. It provides an efficient way to interpret a whole volume of horizons all at once by extracting the horizontal slices in the flattened space. Conventional slope-based flattening methods that can locally flatten the seismic reflections, however, often fail to flatten the reflections in a global sense and cannot accurately align the reflections across faults. We have developed an iterative method to improve the flattening by using the slopes and correlations of seismic traces. The local slopes, estimated for each image sample, can locally follow reflections but may fail to track the reflections over a long distance or correlate the reflections across faults. The seismic correlations, computed for randomly and sparsely extracted seismic traces, help to align the corresponding reflections over a long distance and across faults. We compute flattening shifts, one for each image sample, by fitting the seismic slopes and correlating in the least-squares sense. We further apply the shifts to relatively adjust the seismic samples in the vertical direction so that all of the reflections are horizontally aligned. We iteratively flatten the seismic volume by repeating the process multiple times (often less than five times). With the flattening shifts, we can compute a relative geologic time (RGT) volume that implicitly contains all the structure information of the seismic volume. An arbitrary number of horizons then can be extracted as isosurfaces of RGT values. Multiple field examples demonstrate that our method significantly improves the flattening, especially across faults and missing data zones, compared with conventional flattening methods. Our method is especially helpful to interpret subtle stratigraphic features (e.g., vertically thin channels) by providing an accurately flattened seismic volume.

25 December 2024 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
SLSanfu Li
Sanfu Li
YLYaxing Li
Yaxing Li
YSYunzhi Shi
Yunzhi Shi
XWXinming Wu
Xinming Wu
XJXiaofeng Jia
Xiaofeng Jia
Seismic migration is a tool to obtain images of underground structures; however, it requires accurate velocity models. Errors in estimated migration velocities lead to defocused and distorted migration images. We propose a deep learning method for accurate seismic imaging in the presence of velocity errors. Our idea is to correct the distorted common image gathers (CIGs) due to velocity errors by using a convolutional neural network (CNN). We design a CIG-to-CIG (CIG2CIG) CNN, in which both the inputs and outputs are CIGs. Furthermore, we apply velocity constraints to the CIG2CIG CNN, forming another velocity-constrained CIG-to-CIG (VC-CIG2CIG) CNN to perform the same task. To train the two CNNs, we create hundreds of true and wrong velocity models, which are applied to migration to produce true CIGs and distorted CIGs, respectively. Experiments demonstrate that the VC-CIG2CIG network is superior to the CIG2CIG network in correcting distorted CIGs and suppressing artifacts.

17 March 2020 in Interpretation
Verified
Journal Article
Closed access
YSYunqiang Sun
Yunqiang Sun
LGLuo Gang
Luo Gang
YLYaxing Li
Yaxing Li
Mingwen WangMingwen Wang
Mingwen Wang
XJXiaofeng Jia
Xiaofeng Jia
RZRui Zhang
Rui Zhang
It has been recognized that stress perturbations in sediments induced by salt bodies can cause elastic-wave velocity (seismic velocity) changes and seismic anisotropy through changing their elastic parameters, thus leading to difficulties in salt imaging. To investigate seismic velocity changes and seismic anisotropy by near-salt stress perturbations and their impacts on salt imaging, taking the Kuqa depression as an example, we have applied a 2D plane-strain static geomechanical finite-element model to simulate stress perturbations and calculate the associated seismic velocity changes and seismic anisotropy; then we used the reverse time migration and imaging method to image the salt structure by excluding and including the stress-induced seismic velocity changes. Our model results indicate that near-salt stresses are largely perturbed due to salt stress relaxation, and the stress perturbations lead to significant changes of the seismic velocities and seismic anisotropy near the salt structure: The maximum seismic velocity changes can reach approximately 20% and the maximum seismic anisotropy can reach approximately 10%. The significant changes of seismic velocities due to stress perturbations largely impact salt imaging: The salt imaging is unclear, distorted, or even failed if we exclude near-salt seismic velocity changes from the preliminary velocity structure, but the salt can be better imaged if the preliminary velocity structure is modified by near-salt seismic velocity changes. We find that the locations where salt imaging tends to fail usually occur where large seismic velocity changes happen, and these locations are clearly related to the geometric characteristics of salt bodies. To accurately image the salt, people need to integrate results of geomechanical models and stress-induced seismic velocity changes into the imaging approach. The results provide petroleum geologists with scientific insights into the link between near-salt stress perturbations and their induced seismic velocity changes and help exploration geophysicists build better seismic velocity models in salt basins and image salt accurately.

5 January 2022 in TechRxiv
Verified
Preprint
Open access
PDF file
YLYaxing Li
Yaxing Li
XJXiaofeng Jia
Xiaofeng Jia
XWXinming Wu
Xinming Wu
ZGZhicheng Geng
Zhicheng Geng
Reverse time migration (RTM) is a technique used to obtain high-resolution images of underground reflectors; however, this method is computationally intensive when dealing with large amounts of seismic data. Multi-source RTM can significantly reduce the computational cost by processing multiple shots simultaneously. However, multi-source-based methods frequently result in crosstalk artifacts in the migrated images, causing serious interference in the imaging signals. Plane-wave migration, as a mainstream multi-source method, can yield migrated images with plane waves in different angles by implementing phase encoding of the source and receiver wavefields; however, this method frequently requires a trade-off between computational efficiency and imaging quality. We propose a method based on deep learning for removing crosstalk artifacts and enhancing the image quality of plane-wave migration images. We designed a convolutional neural network that accepts an input of seven plane-wave images at different angles and outputs a clear and enhanced image. We built 505 1024×256 velocity models, and employed each of them using plane-wave migration to produce raw images at 0°, ±20°, ±40°, and ±60° as input of the network. Labels are high-resolution images computed from the corresponding reflectivity models by convolving with a Ricker wavelet. Random sub-images with a size of 512×128 were used for training the network. Numerical examples demonstrated the effectiveness of the trained network in crosstalk removal and imaging enhancement. The proposed method is superior to both the conventional RTM and plane-wave RTM (PWRTM) in imaging resolution. Moreover, the proposed method requires only seven migrations, significantly improving the computational efficiency. In the numerical examples, the processing time required by our method was approximately 1.6% and 10% of that required by RTM and PWRTM, respectively.