Suihong Song
Postdoctoral Scholar, Energy Resources Engineering
Bio
Suihong Song collaborates with Professor Tapan Mukerji at the Stanford Center for Earth Resources Forecast (SCERF) as a postdoctoral scholar. His research is centered on integrating machine learning with geosciences, specifically focusing on machine learning-based reservoir characterization and geomodelling, Physics-informed Neural Networks (PINNs) and neural operators as well as their applications in porous flow simulations, neural networks-based surrogate and inversion, decision-making under uncertainty, and machine learning-based geological interpretation of well logs and seismic data. These research endeavors have practical applications in managing underground water resources, oil and gas exploration, geological storage of CO2, and the evaluation of hydrothermal and natural hydrogen, among others.Song proposed GANSim, an abbreviation for Generative Adversarial Networks-based reservoir simulation, which presents a reservoir geomodelling workflow. This innovative approach has been successfully implemented in various 3D field reservoirs by international oil companies, including ExxonMobil.
Honors & Awards
-
Student Travel Grant, IAMG (2019)
-
First-class PhD. Scholarship, China University of Petroleum-Beijing (2017-2021)
-
National Scholarship, Ministry of Education of China (2017)
-
First-class Graduate Scholarship, China University of Petroleum-Beijing (2014-2016)
-
Outstanding Graduate Award, Beijing Municipal Education Commission (2013)
Boards, Advisory Committees, Professional Organizations
-
Associate Editor, Journal of Hydrology (2023 - Present)
-
Session Chair, Annual Conference of International Association of Mathematical Geosciences (IAMG) (2023 - 2023)
-
Journal Review, Water Resources Research, Journal of Hydrology, Geophysics, Computers and Geosciences, Mathematical Geosciences, Computational Geosciences, IEEE TGRS, etc. (2018 - Present)
Professional Education
-
Doctor of Philosophy, China University of Petroleum (2021)
-
Ph.D, China University of Petroleum-Beijing, Geological Resources and Geological Engineering (2021)
-
Visiting Ph.D., Stanford University, Energy Sciences & Engineering (2020)
-
M.Eng., China University of Petroleum-Beijing, Geological Resources and Geological Engineering (2017)
-
B.Eng., China University of Petroleum-Beijing, Petroleum Geology (2013)
All Publications
-
GANSim-surrogate: An integrated framework for stochastic conditional geomodelling
JOURNAL OF HYDROLOGY
2023; 620
View details for DOI 10.1016/j.jhydrol.2023.129493
View details for Web of Science ID 000990444800001
-
GANSim-3D for Conditional Geomodeling: Theory and Field Application
Water Resources Research
2022
View details for DOI 10.1029/2021WR031865
-
Bridging the Gap Between Geophysics and Geology With Generative Adversarial Networks
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
2022; 60
View details for DOI 10.1109/TGRS.2021.3066975
View details for Web of Science ID 000730619400075
-
Geological Facies modeling based on progressive growing of generative adversarial networks (GANs)
COMPUTATIONAL GEOSCIENCES
2021
View details for DOI 10.1007/s10596-021-10059-w
View details for Web of Science ID 000637662500001
-
GANSim: Conditional Facies Simulation Using an Improved Progressive Growing of Generative Adversarial Networks (GANs)
MATHEMATICAL GEOSCIENCES
2021
View details for DOI 10.1007/s11004-021-09934-0
View details for Web of Science ID 000634650800001
-
Geologist-level wireline log shape identification with recurrent neural networks
COMPUTERS & GEOSCIENCES
2020; 134
View details for DOI 10.1016/j.cageo.2019.104313
View details for Web of Science ID 000501616800011
-
Lithology identification using well logs: A method by integrating artificial neural networks and sedimentary patterns
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
2019; 182
View details for DOI 10.1016/j.petrol.2019.106336
View details for Web of Science ID 000483927500061
-
Local optimization of DFN by integrating tracer data based on improved simulated annealing
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
2018; 170: 858-872
View details for DOI 10.1016/j.petrol.2018.07.013
View details for Web of Science ID 000443829400072