Bayesian source detection and parameter estimation of a plume model based on sensor network measurements

Authors

Chunfeng Huang, Indiana University
Tailen Hsing, Seoul National University
Noel Cressie, University of WollongongFollow
Auroop R. Ganguly, University of Tennessee
Vladmir A. Protopopescu, Oak Ridge National Laboratory
Nageswara S. Rao, Oak Ridge National Laboratory

RIS ID

72390

Publication Details

Huang, C., Hsing, T., Cressie, N., Ganguly, A. R., Protopopescu, V. A. & Rao, N. S. (2010). Bayesian source detection and parameter estimation of a plume model based on sensor network measurements. Applied Stochastic Models in Business and Industry, 26 (4), 331-348.

Abstract

We consider a network of sensors that measure the intensities of a complex plume composed of multiple absorption-diffusion source components. We address the problem of estimating the plume parameters, including the spatial and temporal source origins and the parameters of the diffusion model for each source, based on a sequence of sensor measurements. The approach not only leads to multiple-source detection, but also the characterization and prediction of the combined plume in space and time. The parameter estimation is formulated as a Bayesian inference problem, and the solution is obtained using a Markov chain Monte Carlo algorithm. The approach is applied to a simulation study, which shows that an accurate parameter estimation is achievable.