hongyus@mit.edu
Hongyu Sun
- 2022 Alum (PhD)
- PhD, Earth, Atmospheric and Planetary Sciences, MIT, 2022
- MSc, Geophysics, Jilin University, 2017
Biographical Overview
Dr. Sun recently completed her PhD in geophysics in the Department of Earth, Atmospheric and Planetary Sciences and in Imaging and Computing Group, working with Laurent Demanet. She uses machine-learning algorithms to explore (i.e., extrapolate, generate, extract, etc.) seismic waves and to infer the Earth's structures and properties. Meanwhile, she has studied fault weakening and earthquake instability with Matej Pec using rock deformation experiments. Her research interests range from computational to experimental studies of the Earth, including but not limited to machine learning, seismic imaging, seismic interferometry, inverse problems, signal processing, and geomechanics.
Publications
-
H. Sun, L. Demanet, 2022, "Beyond Correlations: Deep Learning for Seismic Interferometry", IEEE Transactions on Neural Networks and Learning Systems, 1 - 12
-
H. Sun, L. Demanet, 2022, "Deep Learning for Low-Frequency Extrapolation of Multicomponent Data in Elastic FWI", IEEE Transactions on Geoscience and Remote Sensing, 60, 1 - 11
-
H. Sun, M. Pec, 2021, "Nanometric flow and earthquake instability", Nature Communications, 12
-
H. Sun, L. Demanet, 2021, "Seismic interferometry with neural networks", First International Meeting for Applied Geoscience & Energy
-
H. Sun, L. Demanet, 2020, "Elastic full-waveform inversion with extrapolated low-frequency data", SEG Technical Program Expanded Abstracts 2020
-
H. Sun, L. Demanet, 2020, "Extrapolated full waveform inversion with deep learning", GEOPHYSICS, 85, R275-R288
-
H. Sun, L. Demanet, 2019, "Extrapolated full waveform inversion with convolutional neural networks", SEG Technical Program Expanded Abstracts 2019
-
H. Sun, M. Peç, 2019, "Linear Viscous Flow of Nanocrystalline Fault Rocks at 300 – 500˚C", AGU Fall Meeting
-
H. Sun, L. Demanet, 2018, "Low-frequency extrapolation with deep learning", SEG Technical Program Expanded Abstracts 2018