Youzuo Lin
Associate Professor, School of Data and Information SciencesAdjunct Professor, Department of Earth, Marine and Environmental SciencesAdjunct Professor, Department of MathematicsUniversity of North Carolina at Chapel Hill
Embedded Files
Associate Professor, School of Data and Information SciencesAdjunct Professor, Department of Earth, Marine and Environmental SciencesAdjunct Professor, Department of MathematicsUniversity of North Carolina at Chapel Hill
ABOUT ME
ABOUT ME
Biography. I am currently an Associate Professor in the School of Data and Information Sciences (SDIS) at the University of North Carolina at Chapel Hill. Prior to joining SDIS, I was a Senior Scientist in the Earth and Environmental Science Division at Los Alamos National Laboratory, where I served from 2010 to 2024. I received my Ph.D. in Applied and Computational Mathematics from Arizona State University in 2010.
Research. My current research focuses on scientific machine learning (AI for Science),ย deep learning, computational methods, and their applications in medical imaging, signal and image Analysis, and geoscience. Specifically, I have worked on ultrasound imaging and cancer detection, subsurface imaging for energy exploration,and time series classification for small earthquake detection.ย
Ph.D. /Master Openings (Fall 2027). We invite applications for Ph.D./Master positions starting in Fall 2027. Prospective students interested in advancing cutting-edge research in this field are encouraged to Apply to the position that best matches their background and interests.
Intern Openings (Spring & Summer 2027). We also welcome applications for PAID research internships in Spring and Summer 2027. Interested candidates should complete the Application Form and Apply to the role most relevant to their skills and interests.
News
News
April 2026: Very excited to share that our review paper on ๐๐ผ๐บ๐ฝ๐๐๐ฎ๐๐ถ๐ผ๐ป๐ฎ๐น ๐ช๐ฎ๐๐ฒ ๐๐บ๐ฎ๐ด๐ถ๐ป๐ด has been accepted to the ๐ฃ๐ฟ๐ผ๐ฐ๐ฒ๐ฒ๐ฑ๐ถ๐ป๐ด๐ ๐ผ๐ณ ๐๐ต๐ฒ ๐๐๐๐.ย
January 2026: ICLR 2026, OpenPros: A Large-Scale Dataset for Limited View Prostate Ultrasound Computed Tomography, has been accepted. Thanks to all co-authors.ย
Octorber 2025: NVIDIA featured our EFWI dataset in their latest PhysicsNemo demo on diffusion-based FWI.ย Thanks to all co-authors for their excellent work!
September 2025: New NVIDIA Academic Grant Awarded โ Many thanks to NVIDIA for providing high-performance GPUs & hardwares to support our research!
August 2025: New NSF project funded: Advancing Scientific Machine Learning for Wave Imaging. Thank you to NSF for the support.
July 2025: New NSF project funded: Quantum Cyberinfrastructure for Geoscience. Thanks to NSF!
July 2025: ICML 2025: Exploring Invariance in Images through One-way Wave Equations. Thanks to our collaborators!
April 2025: Our Kaggle Competition on Geophysical Waveform Inversion is live. Come and join the fun!ย
February 2025: Honored to join the Editorial Board of the IEEE Open Journal of Signal Processing.
January 2025: Excited to announce that one paper has been accepted by The Leading Edge and another by ICLR 2025.
December 2024: Thrilled that one paper has been accepted by AAAI 2025.
September 2024: Our proposal was awarded by the DOE-ASCR program office!ย
Research
Research
Here are some of my most recent projects. For a full list of research projects and descriptions, see my complete Publications and Research Page.ย
OpenFWI: A Collection of Large-scale, Multi-structural Benchmark Datasets for Data-driven Seismic Full-waveform Inversion.
WaveDiffusion: Exploring Full Waveform Inversion via Joint Diffusion in the Latent Space
Physics-Guided Data-Driven Seismic Inversion: Recent Progress and Future Opportunities in Full Waveform Inversion
Mask-enhanced Deep-learning for Prostate Ultrasound Tomography with Narrow Data Acquisition Aperture
EFWI: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties
Learned Full Waveform Inversion Incorporating Task Informationย for Ultrasound Computed Tomography
VelocityGAN: Subsurface Velocity Image Estimation Using Conditional Adversarial Networks
DeepDetect: A Cascaded Region-based Densely Connected Network for Seismic Event Detectionย
Adaptive Filtering for Event Recognition from Noisy Signal: an Application to Earthquake Detection
Page updated
Google Sites
Report abuse