Matthew Lary
Papers
3
Total Citations
16
H-Index
3
About
Matthew Lary is pioneering the frontier of autonomous environmental sensing, merging robotics, hyperspectral remote sensing, and machine learning to create self-learning robotic teams. His core research focuses on developing scalable, multi-robot systems that can rapidly characterize unfamiliar environments—from terrestrial landscapes to complex inland waters—without human intervention. Lary’s major contribution is a flexible paradigm that integrates comprehensive in-situ sensing with hyperspectral imaging and machine learning, enabling robots to autonomously learn and adapt to new settings. This work is critical for satellite calibration and validation, as it dramatically reduces the time and expense of collecting reference data needed to calibrate remote sensing products. His most cited paper (2021, 8 citations) demonstrates a robotic team that autonomously learns new environments, while a follow-up (2024, 5 citations) extends this approach to water quality monitoring, addressing the challenge of small-scale spectral variability in inland waters. By incorporating conformal prediction, Lary’s systems also quantify uncertainty, enhancing reliability. His research promises to revolutionize how we monitor Earth’s changing environments, making high-quality, real-time data collection accessible and efficient.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3