Prof. Xingye Liu | Geophysics | Young Researcher Award

Prof. Xingye Liu at Chengdu University of Technology, China

Prof. Xingye Liu 🧠 is a prominent geophysicist serving at the College of Geophysics, Chengdu University of Technology, China 🇨🇳. With a Ph.D. in Geological Resources and Engineering 🎓 from the China University of Petroleum, Beijing, he has become a dynamic contributor to reservoir characterization, seismic inversion, and AI applications in geoscience. His review portfolio 📚 spans 200+ manuscripts across 20+ global journals, demonstrating scholarly versatility. As an editorial board member in multiple geoscience publications 📝 and a seasoned researcher, he has authored over 50 journal papers and 20+ conference proceedings. His cutting-edge work bridges geophysical theory with real-world oil and gas field applications, contributing significant practical value 💡. Known for his sharp review acumen, he stays attuned to evolving research trends while mentoring innovation in geophysical exploration. His research impact is both economic and societal, proving him a pillar in modern geophysics and subsurface modeling 🔬🌍.

Professional Profile 

Orcid

Scopus

Google Scholar

🎓 Education

Xingye Liu’s academic roots began with a B.S. in Exploration Technology and Engineering (2013) 🧪, followed by a Ph.D. in Geological Resources and Geological Engineering (2018) from China University of Petroleum, Beijing 🏫. Under the guidance of Prof. Xiaohong Chen, he built a robust foundation in geological signal processing, seismic data interpretation, and resource modeling. During his Ph.D., he immersed himself in complex geophysical challenges, blending traditional geological theory with cutting-edge computation 🔍. This academic journey laid the intellectual groundwork for a career filled with practical innovation. His education reflects a deep integration of theoretical acumen and field-focused experimentation, enabling a seamless transition into research and academic leadership 🧬. These formative years have been crucial in shaping his multidisciplinary perspective that unites geophysics, data science, and reservoir engineering—a signature blend for his continued impact in energy exploration 🔧🛰️.

👨‍🏫 Professional Experience

Currently a Professor at the College of Geophysics, Chengdu University of Technology 🏢, Xingye Liu has cultivated a rich professional track that bridges academia and industry. His influence extends through his editorial roles, including positions on the Youth Editorial Boards of Petroleum Geology and Recovery Efficiency and Coal Geology & Exploration, and the Editorial Board of Earth Sciences 📖. He has also reviewed 200+ papers for elite journals like IEEE Transactions on Geoscience and Remote Sensing, Geophysics, and Marine and Petroleum Geology 🌊. His projects span signal processing, reservoir simulation, seismic modeling, and AI-based inversion workflows 🤖. His consulting and collaborative work with oilfield enterprises has provided real-time geophysical insights that directly enhanced oil production efficiency ⚙️. Liu’s career reflects not only scholarly leadership but also a strong practical orientation, where theory meets the tools and strategies of energy exploration 🌐.

🧠 Research Interests

Prof. Liu’s research pursuits weave together classic geophysics with innovative machine learning strategies 🧠📡. His core areas include seismic inversion, geophysical fluid analysis, and reservoir modeling using intelligent systems. He is passionate about integrating AI into seismic interpretation to enhance predictive accuracy and streamline resource mapping 🚀. Liu’s projects reflect a balance between theoretical depth and field-based applicability—working on how machine learning can de-noise signals, optimize inversion algorithms, and revolutionize seismic data analysis. He has also explored geophysical fluid dynamics and their role in subsurface behavior under varying geological conditions 🌍💧. These research endeavors aim to transform how oil and gas fields are explored, using smarter tools and faster algorithms. His contribution to reservoir characterization represents the nexus between traditional geophysical wisdom and modern computational innovation, making him a forward-looking leader in subsurface science 🔎🛰️.

🏆 Awards and Honors

Though not extensively detailed, Xingye Liu’s prestigious editorial board memberships and high-impact reviewer roles signify peer recognition and academic trust 🌟. His inclusion in elite scientific editorial teams and trusted reviewer status with globally reputed journals like Geophysics, Petroleum Science, and IEEE Sensors speaks volumes of his credibility, objectivity, and critical thinking ⚖️. With more than 50 internationally published papers and substantial contributions to global conferences, he has gained respect as a thought leader in geophysical and AI-based reservoir studies. The projects he has led or participated in have not only solved real-world exploration problems but also led to quantifiable economic and environmental benefits 🛢️🌱. These contributions are emblematic of a career distinguished by scholarly excellence and practical success. While formal awards may not be listed here, his academic and industry engagements reflect profound achievement and esteem within the global geophysical research community 🌐🏅.

📚 Publications Top Note 

1. Facies identification based on multikernel relevance vector machine

• Authors: X. Liu, X. Chen, J. Li, X. Zhou, Y. Chen

• Year: 2020

• Citations: 100

• Source: IEEE Transactions on Geoscience and Remote Sensing 58(10), 7269–7282

• Summary: This study presents a multikernel relevance vector machine (MKRVM) model to improve lithofacies identification accuracy from seismic data. By combining multiple kernel functions and relevance vector methodology, the proposed model shows higher generalization capability and reduced overfitting compared to traditional classifiers.

---

2. Lithofacies identification using support vector machine based on local deep multi-kernel learning

• Authors: X.Y. Liu, L. Zhou, X.H. Chen, J.Y. Li

• Year: 2020

• Citations: 60

• Source: Petroleum Science 17, 954–966

• Summary: The authors propose a hybrid method combining local deep learning with multi-kernel support vector machines for accurate lithofacies classification. The model exploits local structural information from seismic data and achieves superior performance compared to conventional SVMs.

---

3. Fast dictionary learning for high-dimensional seismic reconstruction

• Authors: H. Wang, W. Chen, Q. Zhang, X. Liu, S. Zu, Y. Chen

• Year: 2020

• Citations: 56

• Source: IEEE Transactions on Geoscience and Remote Sensing 59(8), 7098–7108

• Summary: This work introduces a fast dictionary learning algorithm for reconstructing high-dimensional seismic data. The method enhances seismic signal clarity and resolution by efficiently capturing data sparsity and reducing reconstruction time.

---

4. Deep classified autoencoder for lithofacies identification

• Authors: X. Liu, G. Shao, Y. Liu, X. Liu, J. Li, X. Chen, Y. Chen

• Year: 2021

• Citations: 55

• Source: IEEE Transactions on Geoscience and Remote Sensing 60, 1–14

• Summary: A novel deep classified autoencoder model is introduced for classifying lithofacies from seismic attributes. The model integrates deep learning with feature compression and classification, yielding improved prediction accuracy.

---

5. Prestack amplitude versus angle inversion for Young’s modulus and Poisson’s ratio based on the exact Zoeppritz equations

• Authors: L. Zhou, J. Li, X. Chen, X. Liu, L. Chen

• Year: 2017

• Citations: 46

• Source: Geophysical Prospecting 65(6), 1462–1476

• Summary: This paper proposes a method using prestack AVA inversion and exact Zoeppritz equations to estimate elastic parameters like Young’s modulus and Poisson’s ratio. The approach improves lithological and fluid content characterization.

---

6. Nonlocal weighted robust principal component analysis for seismic noise attenuation

• Authors: X. Liu, X. Chen, J. Li, Y. Chen

• Year: 2020

• Citations: 43

• Source: IEEE Transactions on Geoscience and Remote Sensing 59(2), 1745–1756

• Summary: This paper presents a robust noise attenuation method using nonlocal weighted RPCA. It improves the signal-to-noise ratio in seismic datasets by leveraging spatial redundancy and sparsity in the data structure.

---

7. Extreme learning machine for multivariate reservoir characterization

• Authors: X. Liu, Q. Ge, X. Chen, J. Li, Y. Chen

• Year: 2021

• Citations: 41

• Source: Journal of Petroleum Science and Engineering 205, 108869

• Summary: The authors employ extreme learning machines (ELMs) for characterizing reservoir properties from multivariate data. ELMs provide a fast and effective method for nonlinear regression, enhancing interpretation efficiency.

---

8. Nonlinear amplitude versus angle inversion for transversely isotropic media with vertical symmetry axis using new weak anisotropy approximation equations

• Authors: L. Zhou, Z.C. Chen, J.Y. Li, X.H. Chen, X.Y. Liu, J.P. Liao

• Year: 2020

• Citations: 41

• Source: Petroleum Science 17, 628–644

• Summary: This study improves AVA inversion techniques for anisotropic media by proposing weak anisotropy approximations, increasing the accuracy in elastic parameter estimations.

---

9. Quantitative characterization of shale gas reservoir properties based on BiLSTM with attention mechanism

• Authors: X. Liu, H. Zhou, K. Guo, C. Li, S. Zu, L. Wu

• Year: 2023

• Citations: 38

• Source: Geoscience Frontiers 14(4), 101567

• Summary: This work leverages BiLSTM neural networks with attention to model temporal dependencies in reservoir data, offering precise quantitative characterization of shale gas properties.

---

10. Nonstationary predictive filtering for seismic random noise suppression—A tutorial

• Authors: H. Wang, W. Chen, W. Huang, S. Zu, X. Liu, L. Yang, Y. Chen

• Year: 2021

• Citations: 37

• Source: Geophysics 86(3), W21–W30

• Summary: A comprehensive tutorial on nonstationary predictive filtering techniques used to suppress random noise in seismic data. It emphasizes algorithmic implementation and real-data applications.

---

11. Separation and imaging of seismic diffractions using a localized rank-reduction method with adaptively selected ranks

• Authors: H. Wang, X. Liu, Y. Chen

• Year: 2020

• Citations: 35

• Source: Geophysics 85(6), V497–V506

• Summary: This paper presents a localized rank-reduction approach for extracting and imaging seismic diffractions. The method adaptively selects matrix ranks to balance detail preservation and noise suppression.

---

12. Prestack AVA inversion of exact Zoeppritz equations based on modified Trivariate Cauchy distribution

• Authors: L. Zhou, J. Li, X. Chen, X. Liu, L. Chen

• Year: 2017

• Citations: 34

• Source: Journal of Applied Geophysics 138, 80–90

• Summary: A modified trivariate Cauchy distribution is used to enhance AVA inversion from Zoeppritz equations, producing more robust estimates of subsurface properties in noisy environments.

---

13. Robust AVO inversion for the fluid factor and shear modulus

• Authors: L. Zhou, X. Liu, J. Li, J. Liao

• Year: 2021

• Citations: 33

• Source: Geophysics 86(4), R471–R483

• Summary: AVO inversion method is developed to estimate fluid factor and shear modulus while addressing issues of instability and noise, improving fluid detection in seismic analysis.

✅ Conclusion

Prof. Xingye Liu stands as a bridge between classical geophysical theory and the digital transformation of earth sciences 🌐🔬. His work exemplifies how deep-domain expertise, when coupled with machine learning and data science, can unlock new possibilities in subsurface exploration. His academic rigor, practical focus, and dedication to advancing petroleum geophysics make him a strategic asset to both scholarly and industrial domains 🔧📊. Whether reviewing landmark research or leading field-changing projects, Liu maintains a clear vision: to evolve energy exploration into a smarter, faster, and more sustainable endeavor. As the world pivots toward more efficient resource discovery, scientists like him are at the frontier of that transformation—bringing intelligence into the core of geophysical decision-making 🤝⚡.