Yashil Sukurdeep is a researcher and instructor at Johns Hopkins University.
His research lies in applied mathematics, with an emphasis on developing principled, mathematically grounded methods for analyzing large-scale, high-dimensional geometric and imaging data. His work includes foundational contributions to shape analysis, where he develops algorithmic and variational frameworks for the representation and comparison of surfaces and shape graphs, as well as advances in computational imaging through the design of modern multi-frame image restoration methods. Notably, his ImageMM framework has been featured in scientific highlights for its ability to combine multiple ground-based telescope exposures to produce images approaching the clarity of space-based observations, enabling deeper and more precise study of faint astronomical structures.
Yashil's research integrates tools from geometry, optimization, statistical modeling, and machine learning to address challenging problems arising in scientific data analysis. His guiding philosophy is the development of interpretable methodologies that scale effectively to modern, data-intensive settings. His work is inherently interdisciplinary, with applications spanning domains such as medical imaging and astronomy, where extracting meaningful structure from complex data is central to discovery. His broader goal is to develop mathematically rigorous frameworks that bridge theory, computation, and real-world scientific impact.
Yashil’s teaching portfolio includes courses in applied mathematics, data science, machine learning, and the mathematical foundations of artificial intelligence. His teaching emphasizes strong mathematical foundations alongside practical, real-world applications, enabling students to develop both conceptual understanding and applied problem-solving skills. He is committed to creating rigorous yet accessible curricula that bridge theory and practice within inclusive learning environments. He actively mentors students in both technical and professional development, guiding them in areas ranging from mathematical modeling and algorithm design to implementation and applied data science workflows.
Education
- PhD, Applied Mathematics and Statistics, Johns Hopkins University
- MS, Applied Mathematics, Brown University
- BS, Mathematics, Brown University
Research
- Y. Sukurdeep, T. Budavári, A.J. Connolly, F. Navarro. ImageMM: Joint multi-frame image restoration and super-resolution. The Astronomical Journal, vol 170 (4), pp. 233, 2025.
- Y. Sukurdeep, F. Navarro, T. Budavári. AstroClearNet: Deep image prior for multi-frame astronomical image restoration. Astronomy & Computing, vol 53, pp. 100999, 2025.
- Z. Ahmad, M. Yin, Y. Sukurdeep, N. Rotenberg, E. Kholmovski, N. Trayanova. A computational pipeline for clustering left atrial appendage morphology via elastic shape analysis. Computers in Biology and Medicine, vol 196 (C), pp. 110905, 2025.
- E. Hartman, Y. Sukurdeep, E. Klassen, N. Charon, M. Bauer. Elastic shape analysis of surfaces with second- order Sobolev metrics: a comprehensive numerical framework. International Journal of Computer Vision, vol 131 (5), pp. 1183-1209, 2023.
- Y. Sukurdeep, M. Bauer, N. Charon. A new variational model for shape graph registration with partial matching constraints. SIAM Journal of Imaging Sciences, vol 15 (1), pp. 261-292, 2022.
Courses
Current
- Data Science and Business Intelligence (JHU Carey)
- Practical Machine Learning (JHU Carey)
HONORS AND DISTINCTIONS
- Professor Joel Dean Award for Excellence in Teaching, Johns Hopkins University (2021, 2022)
- NVIDIA Academic Hardware Grant (2022)
IN THE MEDIA
- Selections from 2025: A New Way to Combine Ground-Based Images, AAS Nova (19 December 2025)