Mubashir Suhail
From zero research experience to ISEF Finalist with groundbreaking astrophysics research
Where Mubashir Started
His Background
- • High school student passionate about physics and computer science
- • No prior research experience
- • Deep interest in astrophysics and machine learning
- • Curious about democratizing access to scientific computing
His Goals
- • Conduct original research in physics
- • Compete at international science fairs
- • Address real-world problems through research
- • Build a strong profile for top university admissions
His Vision
"I noticed that cutting-edge gravitational-wave research required expensive GPU clusters that most students don't have access to. I wanted to find a way to make this kind of science accessible to anyone with a laptop and curiosity."
— Mubashir, before joining YRI
The Research
Working with his YRI mentor, Mubashir tackled a fundamental problem in astrophysics: how can students and researchers in low-resource environments participate in gravitational-wave machine learning research? His solution combined deep learning with innovative distributed computing.
A Low-Resource Convolutional Neural Network Pipeline for Gravitational-Wave Signal Classification
GW detection requires $50,000+/year infrastructure, excluding Global South researchers
G2Net Kaggle dataset - LIGO-Virgo detector strain data
Lightweight CNN (~92,000 parameters) trained on free Google Colab
P2P-DTF framework enabling 100 laptops to match GPU performance
Novel P2P Distributed Training Framework
Mubashir didn't just identify the problem—he engineered a solution. His P2P-DTF framework enables collaborative training across low-power devices using federated learning principles, 80x gradient compression, and gossip-based synchronization.
Transforming computational inequality from an insurmountable barrier into a solvable engineering problem
The Outcome
International Science and Engineering Fair Finalist
Physics and Astronomy / Systems Software
International (1,800+ finalists from 80+ countries)
Democratizing Gravitational-Wave ML Research
Framework applicable to any compute-intensive ML task
When I joined YRI, I had passion but no direction. My mentor helped me transform a vague interest in astrophysics into a concrete research project that addresses real inequality in scientific access. The structured approach—from literature review to methodology to writing—gave me skills I'll use for the rest of my career. Becoming an ISEF finalist felt surreal, but looking back, it was the result of months of deliberate, guided work.
Zero research experience, limited resources, no clear path forward
ISEF Finalist with original astrophysics research and novel ML framework
Why This Research Matters
Annual cost of traditional GW ML infrastructure—now achievable with $0
Gradient compression ratio enabling training on low-bandwidth connections
Framework enables institutions worldwide to participate in frontier research
Ready to Start Your Research Journey?
Join the YRI Fellowship and work with expert mentors to conduct original research, compete at ISEF, and build a profile that stands out.
Apply Now