Zhichao Li

Dr. Zhichao Li

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
6 March 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
CLChao Li
Chao Li
GLGuochang Liu
Guochang Liu
ZWZhiyong Wang
Zhiyong Wang
ZLZhichao Li
Zhichao Li
SFSergey Fomel
Sergey Fomel
Yangkang ChenYangkang Chen
Yangkang Chen
The popularity of blended acquisition is surging in the field of seismic exploration because of its higher efficiency and lower cost. As a compromise, a sophisticated deblending framework should be applied to remove interference noise. However, blended sources are usually fired at off-the-grid samples, and the recorded data are incomplete because of some inevitable barriers and instrument errors, increasing the challenges to apply classic deblending methods to off-the-grid data. Typically, the binning process and data reconstruction will be introduced for off-the-grid incomplete data before subsequent deblending. Nevertheless, the binning process may cause amplitude and phase distortion, degrading the deblending accuracy. To overcome this problem, we propose a deep learning (DL) based method without a binning process for off-the-grid (OTG) deblending and reconstruction, namely OTGDR, avoiding the errors related to preprocessing routines. The proposed OTGDR framework contains two components: deep image prior (DIP)-inspired coherency-enhancing network and bi-linear operator-guided projection onto convex sets (POCS) iteration. The DIP incorporates several fully connected (FC) layers, attention mechanism, and skip connection to extract useful features selectively for superior performance, and the following POCS aims to remove the blending and ambient noise iteratively for enhanced signal-to-noise ratio (SNR). Moreover, the proposed OTGDR is completely data-driven and does not require labels for training, which increases its generality and enables it to adapt to different datasets. In our experiments, we compare the proposed OTGDR with classic deblending methods, and the results demonstrate that OTGDR shows superior performance on off-the-grid denoising and reconstruction in terms of fidelity and SNR.

8 January 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
ZWZixu Wang
Zixu Wang
SWShoudong Wang
Shoudong Wang
ZLZhichao Li
Zhichao Li
ZWZhiyong Wang
Zhiyong Wang
CZChen Zhou
Chen Zhou
Yangkang ChenYangkang Chen
Yangkang Chen
The inherent non-uniqueness problem challenges acoustic impedance inversion, and thus it is meaningful to explore the possible solutions via advanced strategies, e.g., incorporating uncertainty estimation. At present, several generative adversarial network (GAN)-based inversion methods have been shown to offer advantages in terms of inversion accuracy. However, most of them have primarily focused on deterministic predictions, limiting their ability to explore the range of the solution space. Furthermore, the scarcity of labeled data pairs in field data tasks can reduce inversion accuracy. To address these shortcomings, we introduce a Bayesian GAN (BGAN) based on Bayes by Backprop , and integrate it into a closed-loop framework. Synthetic data experiments demonstrate that the closed-loop BGAN performs better than cycle-consistent GAN (cycle-GAN) with insufficiently labeled data pairs. Moreover, unlike the cycle-GAN, the closed-loop BGAN possesses the capability of assessing prediction uncertainties. Compared with the Bayesian linearized inversion (BLI) and Monte Calor (MC) dropout methods, the closed-loop BGAN is more accurate and robust in the inversion of noisy seismic data with lower uncertainty. Therefore, the closed-loop BGAN can achieve high accuracy inversion while estimating potential solutions more reasonably. The field data example also demonstrates that compared with BLI and MC dropout, the closed-loop BGAN can obtain more reasonable inversion results with more reliable uncertainty estimation.

Verified
Journal Article
Open access
PDF file
ZLZhichao Li
Zhichao Li
MLMing Li
Ming Li
GLGuochang Liu
Guochang Liu
YDYanlei Dong
Yanlei Dong
YWYannan Wang
Yannan Wang
YWYaqi Wang
Yaqi Wang
The central and deep reservoirs of the Wushi Sag in the Beibu Gulf Basin, China, are characterized by structurally complex settings, strong heterogeneity, multiple controlling factors for physical properties of reservoirs, rapid lateral variations in reservoir thickness and petrophysical properties, and limited seismic resolution. To address these challenges, this study integrates the INPEFA inflection point technique and Morlet wavelet transform to delineate system tracts and construct a High-Frequency Stratigraphic Framework (HFSF). Sedimentary facies are identified through the integration of core descriptions and seismic data, enabling the mapping of facies distributions. The vertical constraints provided by the stratigraphic framework, combined with the lateral control from facies distribution, which, based on identification with logging data and geological data, support the construction of a geologically consistent low-frequency initial model. Subsequently, geostatistical seismic inversion is performed to derive acoustic impedance and lithological distributions within the central and deep reservoirs. Compared with the traditional methods, the accuracy of the inversion results of this method is 8% higher resolution than that of the conventional methods, with improved vertical resolution to 3 m, and enhances the lateral continuity matched with the sedimentary facies structure. This integrated workflow provides a robust basis for predicting the spatial distribution of sandstone reservoirs in the Wushi Sag’s deeper stratigraphic intervals.

25 July 2026 in Geophysical Prospecting
Verified
Journal Article
Closed access
ZZZixiang Zhou
Zixiang Zhou
GLGuochang Liu
Guochang Liu
ZLZhichao Li
Zhichao Li
QWQibin Wu
Qibin Wu
JLJiahe Lu
Jiahe Lu