About me 🐝

Hi there, I'm Sihong Wu 👋

I am a geophysicist who develops machine learning methods to see beneath the Earth’s surface. I am broadly interested in turning sparse and heterogeneous geophysical datasets into subsurface images with quantified uncertainty, and in what those images reveal about groundwater, geothermal systems, critical minerals, natural hydrogen, and the structure and evolution of the crust and upper mantle. My research centers on deep learning and Bayesian approaches to probabilistic inversion, with electromagnetic methods as my home ground and extensions to seismic, magnetic, gravity, ground-penetrating radar, and borehole data. These methods make continental-scale imaging possible at a fraction of the cost of conventional approaches. Those efforts were recognized with the 2025 GWH Award for Excellence in Electrical Geophysics from the Hohmann Wannamaker Trust.

I am currently a postdoctoral researcher in the Department of Earth, Atmospheric, and Planetary Sciences at the Massachusetts Institute of Technology, where I work with Dr. Laurent Demanet and Dr. Aimé Fournier. Prior to MIT, I was a postdoctoral researcher at the University of Houston, collaborating with Dr. Jiajia Sun and Dr. Jiefu Chen, and at Peking University with Dr. Qinghua Huang, where I also received my PhD in Geophysics in 2021. I received my BS in Geophysics from the Special Class for the Gifted Young at the University of Science and Technology of China in 2016.

My research interests include:

• Uncertainty quantification of geophysical inverse problems based on machine learning techniques
• Deep learning-based signal processing, modeling, imaging, uncertainty quantification of geo-electromagnetic data
• Near-surface hydrological investigation
• Geothermal exploration