Project Grant 2553937

Federal Grant Award Summary

The University of New Mexico received a $225,000 Project Grant from the National Science Foundation's Directorate for Engineering (CFDA 47.041), effective October 1, 2026 through September 30, 2029, to develop a Smart Event-Based Spectral Imager (SEBI) system that addresses data compression and classification challenges in hyperspectral imaging. The project delivers three primary technical products: (1) a configurable smart spectral imaging system with advanced sensing algorithms that dynamically control an electrically-tunable spectral filter to selectively capture only application-relevant spectral and spatial information; (2) intelligent analog readout integrated circuits (IROICs) designed for on-chip implementation of sensing algorithms and tightly coupled with the tunable spectral filter; and (3) optimized machine learning models configured for edge device deployment integrated with the IROIC circuitry. This software-hardware co-design approach enables the device to transmit only high-value outcomes (such as event detections) rather than raw sensor data, thereby reducing communication traffic, power consumption, and latency while improving data processing speed, privacy, and decision-making performance.

The research addresses a critical bottleneck in modern hyperspectral imaging by performing data processing and analysis proximate to the sensor array rather than relying on cloud or centralized server infrastructure. Conducted at the University of New Mexico's Office of Sponsored Projects in Albuquerque, the collaborative research effort leverages NSF's Engineering Directorate focus on fostering innovation in fundamental engineering research. The project represents a novel approach to overcoming the big-data constraints inherent in contemporary spectral imaging systems without compromising analytical quality or decision outcomes.