معرفی
Suihong Song is a Research Fellow at Stanford University's Energy Resources Engineering department, affiliated with the Stanford Center for Earth Resources Forecast (SCERF). He collaborates closely with Professor Tapan Mukerji, focusing on integrating machine learning with geosciences. His work emphasizes reservoir characterization, geomodelling using generative adversarial networks (GANs), physics-informed neural networks (PINNs), and applications in subsurface flow simulations, CO2 storage, and hydrocarbon exploration.
Education includes a Ph.D. from China University of Petroleum (2021), a visiting Ph.D. at Stanford (2020), and earlier degrees from China University of Petroleum-Beijing (B.Eng. 2013, M.Eng. 2017). His research bridges computational methods with geoscience challenges, notably through the GANSim framework, widely adopted by companies like ExxonMobil.
Key research areas include machine learning-driven reservoir modeling, porous media flow simulations, decision-making under uncertainty, and geological interpretation of well logs and seismic data. His publications highlight advancements in stochastic modeling, neural operator applications, and interdisciplinary approaches between geophysics and geology.
Contact: suihong@stanford.edu.
