Chu-Han Zheng

Chu-Han Zheng

Auto-generated profile, based on publicly available information

Chu-Han Zheng

College of Geological Engineering and Geomatics, Changan University, Xian, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
17 March 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
CZChuhan Zheng
Chuhan Zheng
XLXingye Liu
Xingye Liu
PWPengqi Wang
Pengqi Wang
QLQingchun Li
Qingchun Li
FHFeifan He
Feifan He
Pre-stack seismic data retain the amplitude variation with offset (AVO) characteristics, providing more geophysical information reflecting lateral reservoir variations, thus facilitating the identification of oil and gas reservoirs. However, due to the band-limited nature of seismic data, the precision of forward modeling, and the accuracy of algorithms, traditional pre-stack approaches suffer from ambiguity and uncertainty. With the development of deep learning and big data, an increasing number of deep learning methods have been proposed. We integrate the extended Long Short-Term Memory (xLSTM) modules with the Unet framework, and design a novel neural network architecture, i.e., xLSTM-Unet, for elastic parameter inversion (VP, VS and ρ) from pre-stack seismic gathers. Through testing on synthetic seismic records and field data, the proposed xLSTM-Unet outperforms both the traditional Unet and LSTM-Unet models in predicting elastic parameters from pre-stack seismic data. The xLSTM-Unet proposed in this paper provides a stable and effective approach for predicting pre-stack elastic parameters, offering new insights for the intelligent development of seismic exploration.

4 December 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
PWPengqi Wang
Pengqi Wang
XLXing-Ye Liu
Xing-Ye Liu
QLQingchun Li
Qingchun Li
TYTao Yang
Tao Yang
CZChu-Han Zheng
Chu-Han Zheng
YFYi-Fan Feng
Yi-Fan Feng
The assumption of transversely isotropic media with a vertical symmetry axis vertically transverse isotropic (VTI) has been widely utilized in the exploration of shale reservoirs, with its reflection response and pre-stack inversion attracting significant attention from geophysicists. However, accurately estimating anisotropic parameters using existing approximate reflection coefficient formulas for VTI media remains challenging. In theory, inversions based on exact reflection coefficients for VTI media could overcome these limitations. Nevertheless, such inversions present a highly nonlinear problem. The simultaneous inversion of five parameters further exacerbates the ill-posed nature of the inversion, making it difficult for conventional linearized algorithms to handle effectively. To address these challenges, this article proposes a nonlinear pre-stack inversion scheme based on the exact reflection coefficient equations for VTI media. Specifically, we establish an inversion objective function within a Bayesian framework and introduce a heuristic Newton-Raphson-based optimization (NRBO) algorithm for solving the nonlinear objective function. This approach mitigates the inaccuracies introduced by conventional linearized algorithms, enhancing the precision of the inversion results. Tests on 1-D single-well synthetic data, 2-D Hess VTI model synthetic data, and field data demonstrate that the proposed inversion scheme can stably and effectively estimate both elastic and anisotropic parameters simultaneously. Moreover, the inversion accuracy of the proposed approach surpasses that of inversions based on an approximate formula.