John Wu
Associate Astronomer
Baltimore, Maryland, United States
Summary
👤
Senior🎓
Top SchoolJohn Wu is an Associate Astronomer and applied AI scientist with a decade of experience at leading institutions including the Space Telescope Science Institute and Johns Hopkins University, specializing in interpretable AI/ML for scientific discovery. He builds and interprets deep learning models that extract physical galaxy properties from imaging, delivering state-of-the-art results such as a novel image-based estimator for cold gas content and the largest-ever sample of faint nearby galaxies. His work blends rigorous statistical methods, convolutional neural networks, and visualization tools (e.g., Grad-CAM and dimensionality reduction) to probe model behavior and astrophysical correlations. John has extensive experience across multi-wavelength datasets (Hubble, Herschel, ALMA, MeerKAT) and in developing data pipelines for large surveys and instruments, including the Roman Telescope. Based in Baltimore, he balances tenure-track research leadership with hands-on model development, collaborating across astronomy and CS to make machine learning both predictive and physically interpretable. An early interest in applied computer vision (CMU CyLab intern) underpins his long-standing commitment to trustworthy, reproducible ML for astronomy.
10 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD, Astrophysics, Doctor of Philosophy - PhD, Astrophysics at Rutgers University–New BrunswickBachelor of Science - BS, Physics/Astrophysics, Bachelor of Science - BS, Physics/Astrophysics at Carnegie Mellon University
Github Skills (107)
diffusion-probabilistic10
bayesian10
contrastive-learning10
fractions9
denoising9
galaxy9
astronomy9
mass9
generative-model9
predict9
nancy9
stellar9
telescope8
self-supervised-learning8
fastai8
Programming languages (8)
Github contributions (5)
rutgers-physics-ml/astro-hack-2018-spring
Jan 2018 - Apr 2018
Contributions:39 commits, 19 PRs, 9 pushes in 2 months
spsrasastro
jwuphysics/xSAGA
Dec 2020 - Dec 2021
Extending the SAGA survey to the wide-field regime using deep learning
Contributions:3 releases, 161 commits, 2 PRs in 11 months
deep-learningsagasaga-surveyfieldsurvey
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.