Pavlos Protopapas

Pavlos Protopapas is a Scientific Program Director and Lecturer in the Department of Computer Science at Harvard University's John A. Paulson School of Engineering and Applied Sciences (SEAS). His research focuses on machine learning, data science, and their applications in astronomy, astrophysics, and quantum computing. He has expertise in neural networks, uncertainty quantification, and physics-informed models, with contributions to projects like NeuroDiffEQ and ASTROMER.

Protopapas' work bridges computational methods with astronomical challenges, including light curve analysis, black hole image inference, and cross-matching astrophysical sources. He has pioneered transformer-based models for spectral and time-series data, contributing to open-source libraries and domain adaptation techniques. His interdisciplinary approach spans cybersecurity (sysBERT for malware detection), turbulence modeling, and stellar characterization via hierarchical neural networks (StelNet).

His advising includes Rachel Moon (S.M. ’20), whose work applied data science to canine health. Current research trends emphasize scalable solutions for differential equations, semi-supervised learning, and Bayesian inference in complex systems. He collaborates on initiatives like the ALeRCE alert broker for variable star classification and domain adaptation frameworks like ConDA.

• Labs/Teams: Involved with Harvard's machine learning and astronomy groups, leading projects in computational astrophysics and data-driven science.