About Me:
I am a PhD student at the University of Edinburgh working on sequential Bayesian inference. My project title is “Sequential Bayesian inference for spatio-temporal probabilistic models of changes in global vegetation and ocean properties using Earth Observation data“. I am part of the SENSE CDT which is funded in part by NERC and UKSA. I am supervised by Dr Víctor Elvira.
My research focuses on inference of a high dimensional sufficient state from lower dimensional noisy observations.
I am currently working on software for Bayesian filtering of state-space models, working repo is here: https://github.com/BenjaminJCox/BFaS. It is very much a work in progress and should not be considered usable in any real capacity.
Current research topic: Spasity detection in LG state space models, with extensions to nonlinear nongaussian models coming later. Next area will likely be a parameterisation of nonlinear SSMs (so that I can mechanically extract their form rather than specifying), which will be miles hard hopefully.
Relevant Links/Stuff:
- My Github: https://github.com/BenjaminJCox
- My CDT: https://eo-cdt.org/
- Contact: (firstname).(lastname)@ed.ac.uk
