Peter Melchior
Assistant Professor at Princeton University
New Jersey, United States
Summary
👤
Senior🎓
Top SchoolPeter Melchior is an Assistant Professor of Statistical Astronomy at Princeton who builds physics-informed machine learning and statistical algorithms to extract reliable signals from noisy, incomplete, and contaminated astronomical data. With 19 years of experience spanning postdoctoral and research roles in Europe and the U.S., he leads the Princeton Astro Data Lab and the Dynamical Learning Lab, developing methods for signal separation, data fusion, fast inference, and outlier detection used in major surveys like DES, Rubin/LSST, Euclid, and Roman. His group produces open-source tools (e.g., SCARLET) and joint-survey processing frameworks funded by NSF, NASA, Keck Foundation, and Schmidt Sciences to enable cross-mission image and spectral analysis. He applies physics-ML hybrids beyond astronomy to remote and environmental sensing, and currently leads NSF HydroGEN work to generate hydrologic scenarios for national drought and water availability forecasting. Notably, he couples principled physical models with deep learning to tackle real-world “messy” observations rather than relying on purely data-driven approaches.
19 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Physics, Doctor of Philosophy (Ph.D.), Physics at Ruprecht-Karls-Universität Heidelberg
German, English
Github Skills (114)
nmf10
astronomy10
mixture10
crystallography10
zx-spectrum10
image-analysis10
optimization-methods10
mixture-model10
signal-processing10
sampling10
dtw10
autoencoder10
galaxy10
maps10
principal-component-analysis10
Programming languages (6)
Github contributions (5)
pmelchior/skylens
Mar 2009 - Feb 2015
Contributions:142 commits, 13 pushes in 6 years
pmelchior/epsnoise
Apr 2012 - Nov 2016
Contributions:10 commits, 2 pushes in 4 years 7 months
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.