University of Bristol, U.K.
School of Geographical Sciences/Department of Mathematics
Research Assistant
Closing date: 06/04/2014
Salary: £30,728 - £34,565
Applications are invited for a position as Post-doctoral Research Assistant in statistical emulation and spatio-temporal modelling, on a joint project between the Bristol Glaciology Centre/ Department of Mathematics at the University of Bristol. The post is jointly supervised by Jonathan Bamber and Jonathan Rougier.
Current emulators focus on the reconstruction of a few outputs, with associated uncertainty, from numerical model (tuning) parameters. The aim of this project is to extend current work, and develop and implement an emulator able to reconstruct high-dimensional spatio-temporal fields from a small set of numerical model parameters. The approach is envisioned to make use of separable spatio-temporal models, Gaussian Markov random fields and sparse linear algebraic methods. The emulator will be tested on an ice sheet model, run with the help of collaborators, after which its potential will be shown through use of history matching methods. An R package for spatio-temporal emulation is a deliverable of this project.
The successful candidate should be in possession of a PhD (or nearing its completion) in statistics, machine learning or affiliated disciplines and have experience in Bayesian modelling and/or computational statistics. Experience with R software is desirable but not essential. The post is currently offered as a fixed-term position for 12 months.
Queries about this post should be addressed to Jonathan Bamber or Jonathan Rougier.
E-mail: [log in to unmask], [log in to unmask]
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|