Yaqi Li

Dr. Yaqi Li

orcid

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
1 June 2024 in Physics of Fluids
Verified
Journal Article
Closed access
PDF file
DZDongxu Zhang
Dongxu Zhang
CWChengxi Wu
Chengxi Wu
ZSZejin Shi
Zejin Shi
YLYaqi Li
Yaqi Li
Yulong ZhaoYulong Zhao
Yulong Zhao
XWXudong Wu
Xudong Wu
The fluid–solid coupling effect is more pronounced in the process of deep coal seam development compared to shallow coalbed methane, exerting a greater influence on production, and cannot be disregarded. Throughout the extraction process, the interaction between effective stress and gas desorption triggers deformation within the coal seam, leading to dynamic changes in both porosity and permeability. This paper has developed a fully coupled gas flow and deformation model that contains the coal matrix and discrete fractures to describe the dynamic gas seepage behavior and deformation of deep coal seams within a coupled wellbore–hydraulic fractures–matrix system. The model's validity is corroborated through the examination of fracture aperture, employing the finite element numerical simulation capabilities of COMSOL Multiphysics. Subsequent to the model's validation, an in-depth investigation into the permeability and production variations under diverse parametric conditions is conducted. This analysis also encompasses the assessment of hydraulic fracture geometry's impact. The simulation outcomes reveal that the permeability alterations during coal seam development are subject to the counteracting influences of gas desorption and effective stress. Moreover, it is observed that an increase in the Langmuir volume strain constant and initial porosity correlates with enhanced production, whereas a diminution in the hydraulic fracture compression coefficient leads to increased cumulative production. Notably, the optimal production is attained when hydraulic fractures are oriented vertically yet asymmetrically relative to the horizontal well.

18 October 2026 in Processes
Verified
Journal Article
Open access
PDF file
YLYaqi Li
Yaqi Li
JWJin Wu
Jin Wu
CLChengyong Li
Chengyong Li
YLYi Liu
Yi Liu
YWYang Wan
Yang Wan
YTYuchen Tang
Yuchen Tang
Precise lithofacies identification is essential for efficient deep shale gas exploration and predictive targeting of reservoir “sweet spots.” However, deep shale reservoirs exhibit strong heterogeneity. In addition, well-log signals are inherently susceptible to environmental noise, instrumental limitations, and acquisition anomalies, which further complicate facies classification and fine-scale characterization. Traditional facies recognition methods rely heavily on expert interpretation and qualitative assessment, resulting in low automation and limited quantitative accuracy. Moreover, because of the strong nonlinearity of well-log data and the complex coupling among geological features, existing machine learning models remain limited in deep feature extraction, adaptive representation, and generalization, making them insufficient for complex subsurface conditions. To address these challenges, this study proposes a novel intelligent facies identification framework, ZOA-PCNN-AT-SVM, which integrates the Zebra Optimization Algorithm (ZOA), Parallel Convolutional Neural Networks (PCNN), and a multi-head attention mechanism. Through multidimensional collaborative optimization, the framework enables accurate deep-feature extraction and efficient facies recognition. First, Gramian Angular Fields (GAF) are used to convert one-dimensional well-log sequences into two-dimensional topological images, thereby leveraging the image-learning capability of CNNs. A parallel dual-branch convolutional architecture is then designed to enhance feature extraction through multi-branch complementarity. Subsequently, a multi-head attention mechanism is introduced to adaptively weight critical features and strengthen the capture of complex geological correlations. Finally, ZOA searches for the initial learning rate and convolutional kernel sizes within predefined bounds, selecting the configuration with the lowest observed validation-set classification error. Using data from 10 cored wells in the ZG block, the dataset was divided into training, testing, and validation sets at a ratio of 7:2:1. On the held-out test set comprising 120 samples from two wells, the ZOA-PCNN-AT-SVM model achieved an overall accuracy of 96.67% and a macro-F1 score of 96.72%. In a separate field evaluation, the model achieved an accuracy of 92.6% on Well L1. Application to an additional deep shale gas well in the LZ block achieved an accuracy of 91.7%, providing preliminary support for the model’s cross-block applicability.

1 April 2026 in Petroleum Science
Verified
Journal Article
Open access
QWQi-Gui Wang
Qi-Gui Wang
CLCheng-Yong Li
Cheng-Yong Li
YFYin Feng
Yin Feng
RZRun-Hua Zhu
Run-Hua Zhu
YLYaqi Li
Yaqi Li
YZYang Zeng
Yang Zeng