Research
Our methods aren't black boxes. They're published.
GTA's founder, Dr. William Basener, has spent two decades developing and validating the spectral-unmixing, mineral-mapping, target-identification, and atmospheric-correction science that powers FLUXX, OreVision, and SLiMS — in peer-reviewed journals and conferences, with the patents to match.
PhD Mathematics, Boston University · Professor of Data Science, University of Virginia (2016–2026) · RIT Emeritus Faculty
~40
Peer-reviewed publications
1,240+
Citations · Google Scholar
17
h-index
5
Patents & applications
Patents
The methods, patented
The engines behind GTA's products — invented and patented over fifteen years of hyperspectral work.
2025
FAST-BMA — Efficient Unmixing-Identification of All Pixels in a Hyperspectral Image
2024
Gaussian Process and Deep-Learning Atmospheric Correction
2022
System & Method for Hierarchical Identification, Multi-Tier Target-Library Processing, and Two-Stage Identification
2015
Probabilistic Identification of Solid Materials in Hyperspectral Imagery (PRISM)
2014
Object-Based Identification, Sorting and Ranking of Target Detections (NINJA · OBISR)
Publications
Hyperspectral imaging & remote sensing
Dr. Basener's peer-reviewed work in hyperspectral imaging and remote sensing — spectral unmixing, Bayesian material identification, anomaly and target detection, atmospheric correction, and vegetation, soil & mineral mapping.
2025
FAST-BMA: Bayesian Unmixing of Complete Images with Sparsity and Uncertainty Quantification for Mineral Mapping
2025
Soil Chemistry Estimation for Agriculture Planning and Land Management from Hyperspectral Imaging
2025
Hyperspectral Unmixing using Iterative, Sparse and Ensembling Approaches for Large Spectral Libraries Applied to Soils and Minerals
2025
Spectral Unmixing Comparison with Sparse, Iterative and Mixed-Integer Programming Models
2024
An Interpretable Neural Network for Vegetation Phenotyping with Visualization of Trait-Based Spectral Features
2024
Theoretical and Practical Progress in Hyperspectral Pixel Unmixing with Large Spectral Libraries from a Sparse Perspective
2024
Analysis of Vegetation Chemistry Using Feature Selection and Machine-Learning Methods on Hyperspectral Images
2023
Gaussian Process and Deep Learning Atmospheric Correction
2023
Bayesian Gaussian Process for Correcting Artifacts from Atmospheric Correction and Sensor Noise — A Performance Evaluation
2023
Modeling Uncertainty in Hyperspectral Image Classification using Neural Networks with Bayesian Monte Carlo Dropout
2023
Analysis of Spectral Library Variation Using Manifold Learning
2023
Ongoing Collection of Hyperspectral, Lidar, and Growth-Stage Fundamental Signatures for Vegetation Phenotyping and Large-Scale Urban Planning
2023
Predicting Food Insecurity in Africa from MODIS Imagery, Demographics, Economic Factors, Climate, and Supply-Chain Information
2023
Monitoring Landscape Change: Fundamental Spectral Signatures and the Adaptive Management of Nature-Based Infrastructure
2022
Target Identification and Bayesian Model Averaging with Probabilistic Hierarchical Factor Probabilities
2022
Deep Learning of Radiative Atmospheric Transfer with an Autoencoder
2022
Classifying Crop Types using Gaussian Bayesian Models and Neural Networks on GHISACONUS USGS Data from NASA Hyperspectral Satellite Imagery
2022
Neural Network Learning of Chemical Bond Representations in Spectral Indices and Features
2022
A Dynamical Systems Algorithm for Clustering in Hyperspectral Imagery
2018
Microscene Evaluation using the Bhattacharyya Distance
2017
Ensemble Learning and Model Averaging for Material Identification in Hyperspectral Imagery
2017
Geometry of Statistical Target Detection
2017
Classification and Identification of Small Objects in Complex Urban-Forested LIDAR Data using Machine Learning
2012
Metrics of Spectral Image Complexity with Application to Large-Area Search
2012
Interest Segmentation of Large-Area Spectral Imagery for Analyst Assistance
2012
Assessing the Impact of Background Spectral Graph Construction Techniques on the Topological Anomaly Detection Algorithm
2011
Spatially Adaptive Hyperspectral Unmixing
2011
The Target-Implant Method for Predicting Target Difficulty and Detector Performance in Hyperspectral Imagery
2011
High Spatial-Resolution Hyperspectral Spatially Adaptive Endmember Selection and Spectral Unmixing
2011
Graph-Theoretic Metrics for Spectral Imagery with Application to Change Detection
2011
An Automated Method for Identification and Ranking of Hyperspectral Target Detections
2011
A Detection–Identification Process with Geometric Target Detection and Subpixel Spectral Visualization
2010
Clutter and Anomaly Removal for Enhanced Target Detection
2010
Iterative Convex-Hull Volume Estimation in Hyperspectral Imagery for Change Detection
2010
Spectral Image Complexity Estimated through Local Convex-Hull Volume
2010
A Comparison Study of Dimension-Estimation Algorithms
2010
A Novel Method for Change Detection in Spectral Imagery
2010
Interest Segmentation of Hyperspectral Imagery
2010
High-Resolution and LIDAR Imaging Support to the Haiti Earthquake Relief Effort
2009
Enhanced Detection and Visualization of Anomalies in Spectral Imagery
2009
Geometric Estimation of the Inherent Dimensionality of Single- and Multi-Material Clusters in Hyperspectral Imagery
2009
Anomaly Clustering in Hyperspectral Images
2009
Effect of Manmade Pixels on the Inherent Dimension of Natural Material Distributions
2009
Topological Anomaly Detection Performance with Multispectral Polarimetric Imagery
2008
Geometric Estimation of the Inherent Dimensionality of a Single Material Cluster in Multi- and Hyperspectral Imagery
2007
Anomaly Detection using Topology
2007
Clutter Removal via Topology for Improved Target Detection in Hyperspectral Imagery
Dr. Basener's peer-reviewed work most relevant to hyperspectral imaging and remote sensing. Full profile and citation metrics: ORCID 0000-0002-8593-2362.
From the paper to the product
See the science at work
The methods above ship in FLUXX, OreVision, and SLiMS. Book a working demo, or download the free FLUXX Viewer.