Construction of an Improved Bayesian Clutter Suppression Model for Gas Detection
This technical report describes a nonlinear Bayesian Regression model that can be used to estimate effuent concentrations from IR hyperspectral data. As the title implies, the model is constructed to account for background clutter more effectively than current estimators. Although the main objective is to account for background clutter, which is the dominant source of variability in IR data, the model could easily be extended to allow for uncertainties in the atmosphere. The term, "clutter," refers to the variations that occur in the image spectra because emissivity and background temperature change from pixel to pixel. The Bayesian regression model utilizes a more complete description of background clutter to obtain better estimates. The description is in terms of a "prior distribution" on background radiance.
- Research Organization:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-76RL01830
- OSTI ID:
- 15010144
- Report Number(s):
- PNNL-14093; TRN: US200502%%138
- Country of Publication:
- United States
- Language:
- English
Similar Records
Prediction Metrics for Chemical Detection in Long-Wave Infrared Hyperspectral Imagery
Comparison of Two Gas Selection Methodologies: An Application of Bayesian Model Averaging