Talent - Research

Undergraduate research in reinforcement learning and satellite observation optimization.

FURI Research Grant

Awarded $4,600 through the Fulton Undergraduate Research Initiative (FURI) to investigate reinforcement learning approaches for optimizing satellite observation priorities.

Duration:January 2025 - Present
Lab:CoDe Lab, Arizona State University
Focus:Machine Learning, Satellite Systems
Funding:$4,600 USD

Research Overview

My research focuses on developing reinforcement learning algorithms to optimize satellite observation scheduling. The project addresses the challenge of efficiently allocating limited satellite resources to maximize coverage of high-priority targets while considering constraints such as orbital mechanics, sensor capabilities, and ground station availability.

Technical Approach

Using PyTorch and GeoPandas, I'm developing deep reinforcement learning models that learn optimal observation policies through interaction with a simulated satellite environment. The system processes spatial-temporal data to make real-time decisions about which targets to observe, balancing immediate rewards with long-term strategic objectives.

Tools & Technologies

PythonPyTorchGeoPandasTAT-CJupyterNumPyPandas

Impact

This research has applications in Earth observation, disaster response, and scientific data collection. By improving satellite scheduling efficiency, we can enhance our ability to monitor climate change, respond to natural disasters, and support critical infrastructure.