FET: Quantum Intelligent Sensor Network: Entanglement-Assisted Sensing and Machine-Learning Co-Design

Quantum technologies have the potential to transform sensing, communication, and information processing by enabling measurements beyond the limits of classical systems. However, building practical networks of quantum sensors remains challenging because fragile quantum correlations are difficult to maintain, coordinating many distributed sensors is complex, and large volumes of noisy data can limit performance. This project investigates a new framework for Quantum Intelligent Sensor Networks that integrates quantum sensing with advanced data-driven methods to improve how weak signals are measured, shared, and interpreted across distributed systems. The goal is to develop sensing networks that can adapt to changing environments, reduce unnecessary data collection, and extract useful information more efficiently than existing approaches. Outcomes from this work may impact applications such as medical imaging, environmental monitoring, electromagnetic sensing, and next-generation communication systems. The project also contributes to education and workforce development through new courses, open-source tools, and outreach activities that broaden participation in quantum science and engineering. The project develops an end-to-end framework for distributed quantum sensing that co-designs network architecture, physical signal processing, and learning-based inference. One thrust establishes the architectural and information-theoretic foundations of quantum sensor networks, including scalable photonic implementations for entanglement distribution, models for non-local signal extraction, and performance limits that quantify sensitivity and robustness under realistic noise and loss. A complementary thrust formulates sensing as a machine learning–driven optimization problem, combining physics-based simulation with graph-based models and reinforcement learning to adapt network topology, entanglement routing, and sensor parameters to task-specific objectives. The framework incorporates selective quantum error correction strategies that protect task-relevant information while minimizing resource overhead, enabling scalable operation in noisy environments. Together, these efforts produce new algorithms, simulation tools, and design principles for adaptive, robust quantum sensor networks, and establish a general methodology for integrating quantum hardware and learning-based optimization in distributed sensing systems. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria. NSF Award ID: 2551811 | Program: 01002627DB NSF RESEARCH & RELATED ACTIVIT | Principal Investigator: Bo-Han Wu | Institution: University of Hawaii, HONOLULU, HI | Award Amount: $600,000 View on NSF Award Search: https://www.nsf.gov/awardsearch/show-award/?AWD_ID=2551811 View on Research.gov: https://www.research.gov/awardapi-service/v1/awards/2551811.html