I use code and tools to understand how things work and share what I find.
My background is in electrical and electronics engineering. I have hands-on experience using technical tools to visualize and explore complex systems. I learn best by building things and testing my assumptions rather than just reading about them.
My deeper interest now is in artificial intelligence, systems, and the broader world of technology that shapes how we live and work. I am preparing for further study and exploring where in tech or research I want to focus next. I do not claim to be an expert in any of these areas. I am still figuring things out.
A Python toolkit built around the standard SGP4 orbital propagation model and a differentiable SGP4 (dSGP4) wrapper using PyTorch. It parses and validates TLE sets, propagates real satellites, performs TEME-to-ECEF coordinate transforms, runs B* drag-sensitivity experiments, and includes orbit visualization utilities. The toolkit adds robust error diagnostics with physical interpretation and an automatic two-body fallback so propagation degrades gracefully instead of crashing.
What I did: Implemented TLE parsing and validation utilities, an educational reference SGP4 propagator with extra numerical-stability checks, a DifferentiableSGP4 PyTorch module for gradient-based analysis (inspired by ESA's dSGP4 project), and a LiveSGP4 tracker with automatic two-body fallback, detailed error history, and a validation test suite.
What I learned: How to work through complex mathematical models by implementing them in code, the value of delegating core propagation to trusted open-source libraries like the sgp4 package while building higher-level tooling on top, and how to make technical concepts approachable through visualization.
This was a personal learning project, not a formal research appointment or professional aerospace experience.
A mobile-first web app that predicts LEO satellite passes for any location and calculates whether the link margin is strong enough to hold a connection. Given a satellite (by NORAD ID or name) and an observer position, it returns upcoming pass times, SNR and link-budget curves over each pass, a timeline chart, and supports ICS calendar export and PDF reports. Built with a FastAPI/Python backend and a Next.js frontend.
A web application that fetches live TLE data from CelesTrak and visualizes thousands of satellites orbiting in real time. It uses Skyfield for orbit computation and an adaptive time-stepping algorithm for pass prediction, with a React frontend and a Python backend. The main challenge was keeping the rendering performant while tracking thousands of moving objects without freezing the browser.