RA in Bayesian Modelling of Flood Risk

The International Society for Bayesian Analysis; Newcastle upon Tyne; On-site; GBP 30,000 - 40,000; Full time

Job summary

A prestigious academic institution in Newcastle upon Tyne is seeking a Research Assistant/Associate in Statistics to work on the Flood-PREPARED project. The role involves developing a space-time model for rainfall and implementing Bayesian methods for real-time flood prediction. Candidates should have a PhD in Statistics, expertise in Bayesian inference, and strong programming skills in R and another efficient compiled language.

Qualifications

• PhD in Statistics or a closely related discipline (awarded or in submission).
• Expertise in Bayesian inference and computationally intensive inferential methodology.
• Track record of research in computational Bayesian statistics and developing efficient programs.

Responsibilities

• Devise a space-time model for rainfall integrating various data sources.
• Develop and implement Bayesian inferential methods for real-time rainfall forecasting.

Skills

Bayesian inference

Statistical computing

Programming in R

C/C++ or Java/Scala

Time management

Education

PhD in Statistics or closely related discipline

Tools

Modern statistical tools and libraries

Job description

D74668R – Research Assistant/Associate (Statistical Modeller)

School of Mathematics & Statistics, Newcastle University, U.K.

We are seeking to appoint a Research Associate in Statistics to the 4-year Natural Environment Research Council funded “Highlights” project, Flood-PREPARED: Predicting rainfall events by physical analytics of real-time data.

Project Overview

The project is made up of a research team from Newcastle University who will develop an international leading capability for real-time surface water flood risk and impacts analysis for cities.

Responsibilities

The appointed researcher will devise a space-time model for rainfall that can integrate data from a variety of sources, and a statistical emulator of an expensive hydrological flood prediction model, calibrated using observational data. They will develop and implement computationally intensive Bayesian inferential methods that allow real time forecasting of localised rainfall and flood prediction risk.

Qualifications

• PhD in Statistics or a closely related discipline (awarded or in submission)
• Expertise in Bayesian inference and computationally intensive inferential methodology
• Track record of research in computational Bayesian statistics and developing efficient programs for statistical computing
• Excellent statistical computing skills, including familiarity with modern statistical tools and libraries
• Strong programming skills in R and an efficient compiled language like C/C++ or Java/Scala
• Excellent written and oral communication skills and skills in effective time management

The post is full time and fixed-term for 36 months.

Informal enquiries can be made to Professor Darren Wilkinson ([e-mail]) or Dr Sarah Heaps ([e-mail]).