Dr. Yang Gao, Shale Gas Research Institute, Petro China Southwest Oil and Gas field Company, China
Yang Gao is a PhD candidate in Geophysics at China University of Petroleum – Beijing, specializing in exploration geophysics under the supervision of Professor Guofa Li. His research focuses on advanced seismic data processing techniques, including low-frequency extrapolation, resolution enhancement, and seismic inversion using deep learning methodologies. Yang holds a Master’s degree in Geological Resources and Geological Engineering, also from China University of Petroleum – Beijing, where he conducted research on seismic facies interpretation with CNN-based encoder-decoder networks. He completed his Bachelor’s degree in Applied Geophysics at Yangtze University, where he developed a thesis on Q factor estimation based on post-stack seismic data. Yang has actively contributed to several significant research projects and has published extensively in leading journals, highlighting his expertise in deep learning applications in geophysics and seismic signal processing. He has received multiple academic honors, including the Doctoral National Scholarship and the first prize at the “Oriental Cup” National University Student Exploration Geophysics Competition. Fluent in English and a member of the European Association of Geoscientists and Engineers (EAGE), Yang is also skilled in programming languages such as Python and Matlab, and various geophysical software tools.
Professional Profile:
ORCID
Suitability of Yang Gao for the Best Scholar Award
Yang Gao is a highly qualified candidate for the Best Scholar Award, distinguished by his significant contributions to the field of geophysics, particularly in exploration geophysics. His educational background, research experience, and publications demonstrate his commitment to advancing knowledge in seismic signal processing and deep learning applications within geophysics.
Education 🎓
- PhD in Geophysics (Exploration Geophysics)
China University of Petroleum – Beijing, Beijing, China (2020–2024)
- Supervisor: Guofa Li
- Research Focus: Low-frequency extrapolation, resolution enhancement, and seismic inversion using deep learning.
- Master in Geological Resources and Geological Engineering (Exploration Geophysics)
China University of Petroleum – Beijing, Beijing, China (2018–2020)
- Supervisor: Guofa Li
- Research: Seismic facies interpretation with CNN-based encoder-decoder networks.
- Bachelor in Applied Geophysics
Yangtze University, Wuhan, China (2014–2018)
- Thesis: Q factor estimation based on post-stack seismic data.
Research Interests 🔍
- Deep learning applications in geophysics
- Seismic signal processing
- Seismic inversion
Research Experience 💡
- Key Research Member: Research on high-resolution processing methods for deep fusion of multi-source information (Ministry of Science and Technology of the People’s Republic of China, 2019–2024).
- Key Research Member: Adaptive recognition and absorption attenuation correction of source-consistent Q-wavelet signals (National Natural Science Foundation, 2020).
- Principal Investigator: Multi-wave reflection interference correction based on adaptive spatial inversion structure (National Natural Science Foundation, 2018).
- Principal Investigator: Parameterization method for geophysical exploration in Block II, Pengdong Oilfield (CNPC Penglai Oilfield, 2022).
- Key Research Member: Technology for controlling noise of non-stationary compression waves (CNPC East Geophysical Exploration Company, 2021).
- Key Research Member: Multiple wave processing technology for shallow marine areas (CNPC East Geophysical Exploration Company, 2019).
Honors and Awards 🏆
- 2020–2024: The Doctoral First Prize Academic Scholarship, China University of Petroleum – Beijing
- 2021: First prize at the “Oriental Cup” National University Student Exploration Geophysics Competition
- 2022: Doctoral National Scholarship, China University of Petroleum – Beijing
Skills 💻
- Programming: Python, Matlab, C
- Software: GeoEast, Petrel, Jason, HRS, Madagascar; Pytorch, TensorFlow, Keras
- Research Tools: Linux, LaTeX, MS Office
- Languages: Chinese (native), English (fluent)
Publication Top Notes
Structurally-Constrained Unsupervised Deep Learning for Seismic High-Resolution Reconstruction
Deep learning for high-resolution multichannel seismic impedance inversion
Deep Learning Vertical Resolution Enhancement Considering Features of Seismic Data
Incorporating Structural Constraint Into the Machine Learning High-Resolution Seismic Reconstruction