Ankit Biswas
Incoming Student at Harvard College; prospective dual major in astrophysics and statistics.
I’m an incoming freshman at Harvard College, working at the intersection of astrophysics and machine learning. My research involves applying computational techniques to discover elusive objects both small and very large (relatively), from detecting the coldest brown dwarfs (~failed stars) with novel ML models, to searching for the earliest stars using Bayesian optimization, to reconstructing the large-scale structure of the early universe with GANs trained on mock simulations of the universe.
I currently research with Dr. Patrick Treuthardt, Dr. Ian Hewitt, and Alp Tezbasaran at the North Carolina Museum of Natural Sciences Astronomy & Astrophysics Lab on developing methods for the extraction of galaxy substructure and the detection of intermediate-mass black holes. I have previously worked with Dr. Laura Dominé, Dr. Richard Cloete, and Dr. Wesley Andres Watters as part of the Galileo Project research team at the Harvard & Smithsonian Center for Astrophysics, where I assisted in the comissioning and calibration of one of the primary telescopes and helped develop computer-vision foundation models to detect anomalous aerial transients. Alongside Dr. Zheng Cai at the Tsinghua University High-z Team, I’ve also been the co-Principal Investigator on observing-time proposals for extragalactic targets at Keck, the VLT, and JWST.
Outside research, I enjoy youth education advocacy and have worked in various science communication initiatives. Currently, I run the Youth Research Initiative, where we mentor middle-to-high school kids around the world in learning the scientific method and completing research projects. My work has been featured in Bloomberg, Duke Today, and various other venues.
I’m eternally grateful to all the mentors and friends that have helped me so far on my journey—feel free to reach out at my email if you have something interesting!
recent news
| May 05, 2026 | Our NASA-funded citizen science project Cluster Buster started beta testing on Zooniverse! |
|---|---|
| Feb 14, 2026 | Presented poster on mapping the high-z cosmic web at AAAS in Phoenix. |
| Jan 20, 2026 | Featured in Duke Today for science communication work about cosmology research. |
| Sep 22, 2025 | Spoke at several UN Concordia Summit roundtables (invited by EXPLR and the National STEM Festival to represent youth research). |
| Jul 07, 2025 | Paper published in MNRAS for TY dwarf discovery with machine learning methods |
publications
2025
-
MNRASMonthly Notices of the Royal Astronomical Society, 2025
-
AASReconstructing the Cosmic Web Over the First 2 Gyr via Deep Learning Decomposition of the Cosmic Infrared BackgroundIn American Astronomical Society Meeting Abstracts, Jun 2025
2024
-
SNCURCSDiscovery of the 5 Oldest Population III LBG Candidates with a Population-Synthesis ApproachIn State of North Carolina Undergraduate Research and Creativity Symposium, 2024
-
NCAMThe Search for Intermediate-Mass Black Holes: Next Steps at NCMNSIn North Carolina Astronomers’ Meeting, 2024
research experience
- Developing galaxy image sets for ML and volunteer-based identification and segmentation of galactic arms
- Built computer vision algorithms to automatically extract arms from grand spiral galaxies
- Co-created the Cluster Buster citizen-science program on Zooniverse (8,700+ classifications; 2025 NASA Citizen Science Grant).
- Analyzing isolated spiral galaxies to constrain the (supermassive black hole mass)–(pitch-angle relation)

- Discovered a new brown dwarf candidate via an ensemble ML model trained on atmospheric models
- Identified luminous Population III candidates in Epoch of Reionization (co-PI of observing time proposals to Keck, VLT (DPR) and JWST)
- Developed CIB tomography method to map high-z large-scale structure with adversarial models

- Developed computer vision models for the detection and tracking of fast-moving aerial transients
- Benchmarked computer-vision detectors (e.g. YOLO, DETR) for source detection in an infrared observatory.
- Leveraged ADSB transponder data to calibrate positional stability of ground-based observatory

outreach & science communication
- Created Youth Research Mentorship Program for 200+ kids (leading 40 mentors worldwide)
- Ran live research talks for 2000+ students, 15 chapters worldwide
- Led development team in Project Pathways digital research tools- garnered 30k+ users
- Raised $8k+ for STEM Program micro-grants at Title 1 schools

- Reviewed and edited student research papers from NCSSM Durham and Online; led a 17-member editorial board.
- Published 2 editions (2024-2025 and 2025 and 2026) with UNC Press as chief editor

- One of four Science Communicators selected by science department
- Co-wrote and distributed monthly Science News pop science articles across the school campus
- Co-organized Art of a Scientist exhibit at NC Museum of Life and Science

- Raised $1550 dollars for STEM education through instruction
- Taught introductory Python and machine learning in research course to 30 kids
- Spearheaded creation of digital marketing posters and flyers (5k+ views)

awards & honors
- National Merit Scholarship Finalist
- U.S. Presidential Scholar Candidate
- Quiz Bowl Nationals (HSNCT) Qualifier
- Regeneron International Science & Engineering Fair Finalist
- UN Concordia Summit Roundtable Speaker
- Coolidge Senator + Nationwide Top 12 Finalist
- Taco Bell Live Más Scholar
- National STEM Challenge Finalist
- NC Student Academy of Sciences 1st Place (Physics)
- Quiz Bowl Nationals (HSNCT) Qualifier
- NC Student Academy of Sciences 1st Place (Physics)
- NC International Science Challenge Semifinalist
- Quiz Bowl Nationals (HSNCT) Qualifier
- Regeneron ISEF Grand Award in Physics/Astronomy
- Science Seed Award — Shanghai AASY
- Gold Presidential Volunteer Service Award
- Quiz Bowl Nationals (HSNCT) Qualifier
- Broadcom MASTERS Coding With Commitment Award + Nationwide Top 30
- Quiz Bowl Nationals (MSNCT) Qualifier