Paul Gader has been researching hyperspectral image analysis, a.k.a. imaging spectroscopy, algorithms since 2002 for agriculture, the environment, and national security.

His team conducted a VIS/NIR LiDAR airborne data collection and built a well-ground truthed collection. He has engaged in a variety of research activities in unmixing (an inverse-problem), dimensionality reduction, and classification using NASA and NSF big data sets and investigated hyperspectral and color imaging for disease detection in apples and for detecting and estimating ripeness of blueberries.

He is developing physics-based, data-driven nonlinear, and hybrid computational models for the inverse problem of unmixing.  

In June 2013, he was General Chair of the IEEE Workshop on Hyperspectral Image and Signal Processing (WHISPERS). Professor Gader gave tutorials on sub-pixel analysis (unmixing) at WHISPERS in 2016 and 2018.   He is currently writing a textbook on this topic.

Want to know more about Unmixing? Click on these links:

A Gaussian Mixture Model representation of Endmember Variability in Hyperspectral Unmixing

Unmixing Urban Hyperspectral Imagery with a Gaussian Mixture Model on Endmember Variability

Current research includes studying the unstable behavior of deep networks when presented with samples from unknown distributions.

Paul Gader has published over 100 journal and over 300 total papers, served for three years as a UF Research Foundation Professor and was named an IEEE Fellow in 2011.