Burzin Balsara

Papers

Total Citations

H-Index

About

Burzin Balsara is a researcher at the forefront of applying machine learning to enhance nuclear safeguards and nonproliferation efforts. His work focuses on developing intelligent systems that operate at the edge—bringing advanced computational analysis directly into field inspections rather than relying on centralized data processing. Balsara’s most-cited paper, “Machine learning at the edge to improve in-field safeguards inspections” (2024), demonstrates how lightweight AI models can be deployed on portable devices to analyze sensor data in real time, significantly improving the speed and accuracy of detecting undeclared nuclear activities. This contribution addresses a critical challenge in international security: enabling inspectors to make informed decisions on-site without requiring extensive infrastructure or connectivity. While his citation count is still growing, Balsara’s work represents a novel intersection of edge computing, anomaly detection, and nuclear verification—a field where practical impact often outpaces publication metrics. His research has implications for reducing inspection costs, increasing transparency, and strengthening global nonproliferation regimes. For students and researchers interested in applied machine learning for high-stakes environments, Balsara’s approach offers a compelling model of how to bridge theoretical advances with real-world security needs.