Chao Song
 |
SEG J. Clarence Karcher Award 2024
Chao Song has been credited with pioneering advancements in seismic modeling and inversion technologies. His contributions have had a particular emphasis on physics-informed neural networks. His work bridges the gap between traditional geophysical methods and cutting-edge machine learning techniques. Some of Song’s early contributions to full-waveform inversion (FWI), deep learning, and improvements in objective functions resulted in an Award of Merit for Best Student Poster Paper at the 2019 SEG Annual Meeting. His command of the science and his propensity for innovation is nowhere more evident than the 29 journal articles to his credit since 2015, including 16 as senior author. The significance of these contributions is evident in citation rates and h-index values commendable for late-career geophysical researchers. Song is most noted for his groundbreaking work with neural networks and inversion. Scholars in his field have suggested his approach to efficient wavefield inversion has significantly enhanced the accuracy of FWI. His expertise has been recognized with appointments as associate editors for Geophysical Prospecting and the Journal of Geophysics and Engineering.
Biography Citation for the J. Clarence Karcher Award
by Umair Bin Waheed and Tariq Alkhalifah
Chao Song, currently a professor of geophysics at Jilin University, is a distinguished young researcher in the exploration geophysics community. Chao’s academic journey began at Jilin University, where he earned his BS and MS in geophysics, before pursuing a PhD at King Abdullah University of Science and Technology with a focus on full-waveform inversion and deep learning applications in geophysics, covering applications ranging from wavefield modeling and velocity model building to microseismic event location and characterization. He further honed his expertise during a postdoctoral fellowship at Imperial College London, specializing in machine learning techniques for geophysical research.
Chao has made significant contributions to the field of seismic modeling and inversion, particularly through his work on physics-informed neural networks. His research has bridged the gap between traditional geophysical methods and advanced machine learning techniques, providing both theoretical insights and practical applications. His innovative work is both academically rigorous and highly applicable in real-world scenarios, showcasing a unique combination of theoretical knowledge and practical skill.
His excellence in research has been recognized with several prestigious awards, including an Award of Merit for Best Student Poster Paper at the 2019 SEG Annual Meeting for his presentation titled “An efficient wavefield inversion for isotropic elastic media,” which was also judged to be in the top 25 presentations overall at the Annual Meeting that year. Chao has an impressive publication record, with numerous articles in highly regarded journals. His work in seismic wave modeling and inversion using deep learning is widely cited, reflecting his significant impact on the scientific community. He has authored 29 journal articles since 2015, including 16 as the lead author, demonstrating his leadership in the field.
Beyond his research, Chao is a dedicated member of the academic community, serving as an academic peer reviewer and associate editor for various geophysical journals. His commitment to advancing the field through these roles underscores his dedication to knowledge sharing and academic excellence.
In recognition of his outstanding contributions, Chao Song is a deserving recipient of the 2024 J. Clarence Karcher Award, and knowing Chao, this honor will only motivate him to contribute even more to our field for the betterment of mankind.