A Bayesian changepoint analysis of spatio-temporal point processes, with application to radioactive particle data

This work introduces a Bayesian approach for detecting multiple unknown change points over time in the inhomogeneous intensity of a spatio-temporal point process with spatial and temporal dependence within segments. We propose a new method for detecting changes by fitting a spatio- temporal log-Gaussian Cox process model using the computational efficiency and flexibility of INLA, and studying the posterior distribution of the potential changepoint positions. A simulation study assesses the validity and properties of the proposed method, before the approach is applied to examine potential unknown change points in the intensity of radioactive particles found on Sandside beach, Dounreay.