Vafaei, Nafiseh
- Institutionen för sydsvensk skogsvetenskap, Sveriges lantbruksuniversitet
Sammanfattning
Determinantal point processes (dpps) are widely used for modeling repulsive behavior in spatial point patterns, yet their extension to spatio-temporal settings has received little attention. This paper develops a comprehensive framework for spatio-temporal dpps (stdpps) based on covariance and spectral representations. We establish fundamental existence conditions; derive closed-form expressions for first- and second-order summary functions-including the pair correlation function, spectral density, and space-time K-function; and introduce both separable and non separable covariance structures that capture spatial, temporal, and joint space-time inhibition. The theoretical developments are illustrated through simulated examples, which highlight how spatial and temporal range parameters govern the strength and extent of repulsion. Together, these results provide a flexible and computationally tractable framework for modeling regularity in space-time point process data.
Nyckelord
Covariance function; regularity; simulation; spatio-temporal point process; spectral density
Publicerad i
Communications in Statistics - Theory and Methods
2026
Utgivare: TAYLOR AND FRANCIS INC
SLU författare
Ghorbani, Mohammad
- Institutionen för biosystem och teknologi, Sveriges lantbruksuniversitet
- Institutionen för biosystem och teknologi, Sveriges lantbruksuniversitet
UKÄ forskningsämne
Sannolikhetsteori och statistik
Publikationens identifierare
- DOI: https://doi.org/10.1080/03610926.2026.2631039
Permanent länk till denna sida (URI)
https://res.slu.se/id/publ/146782