Jun 10, 2022 - An overview of the Stochastic Partial Differential Equations approach for spatial and spatio-temporal models - Speaker: Elias Krainski (King Abdullah University of Science and Technology)

UFSCar/USP joint Seminar

Announcement file.

Scheduled for:
Jun 10, 2022, at 2:00 pm
(GMT-03:00) Brasilia Standard Time - Sao Paulo

Click here to watch again.

Speaker:
Elias Krainski (King Abdullah University of Science and Technology)

Title:
An overview of the Stochastic Partial Differential Equations approach for spatial and spatio-temporal models

Abstract:
In this talk we will briefly introduce some work on the Stochastic Partial Differential Equations approach for building models for Gaussian Random Fields. We consider the link between the discrete and continuous domain models and how this framework can be used to build nonstationary and nonseparable spatio-temporal models. We will point how to implement this model class taking advantages of direct solvers for general sparse matrices so that the computation time does not increase much when comparing with stationary and separable models. An application will be shown as an illustration.

Bio:
Elias did his PhD at the Norwegian University of Science and Technology in Trondheim, Norway. He was adjunct professor at the statistics department of the Universidade Federal do Paraná until September 2019. He was a postdoctoral fellow at the Statistics department of the Dalhousie University in Halifax, Canada and is currently a postdoctoral fellow at the King Abdullah University of Science and Technology, working with the Bayesian Computation research group led by Professor Håvard Rue. His work is mainly on applying new models.