October 2018
Message 106

[Periods|Index by:DateThreadSubjectAuthor|Date:PreviousNext|Thread:(Previous)(Next)|List Information]

[Met-jobs] PhD -- Statistical Postprocessing -- Innsbruck, Austria

From Thorsten Simon <>
Date Wed, 24 Oct 2018 13:40:21 +0200

PhD Position:

**Multivariate Probabilistic Forecasting of Weather Using Joint Distributional Regression**
is a 3-year project for a PhD embedded in a larger interdisciplinary research

group working at the interface between atmospheric science and applied
statistics, which is affiliated partly to the Department of Statistics and
partly to the Department of Atmospheric and Cryospheric Sciences.


A numerical weather prediction (NWP) ensemble prediction system (EPS)
simulates the state of the atmosphere in a probabilistic manner with a
physically consistent covariance in space, time, and among atmospheric parameters.
Multivariate post-processing aims at preserving this covariance structure,
traditionally by sequentially calibrating the margins using univariate methods and
restoring the covariance by (empirical) copulas.

Typical multivariate weather prediction applications are:

* Predicting temperature for multiple forecast horizons.
* Predicting precipitation for multiple sites or continuously over space.
* Predicting wind speed for multiple heights to derive a wind profile.

The project aims at developing a new framework for single-step multivariate
post-processing that simultaneously models both margins and correlations of a multivariate
normal distribution. Both the marginal and the joint correlation parameters will be
conditioned on NWP-EPS output by linking them to additive predictors in a distributional
regression framework.

After laying the methodological foundation for the joint distributional regression
approach (along with corresponding software), the methods will be applied to
multivariate temporal or spatial forecasting,
of temperature, pressure, and wind speed dealing with different temporal scales
(meso vs. synoptical) or different spatial dimensions (horizontal vs. vertical).

The task will be split among the PhD candidate and a PostDoc researcher affiliated
to the same project.

Required Qualifications:

* Master's degree in statistics, mathematics, physics, or atmospheric sciences
with a solid statistical background.
* Computing: Proficiency in R; further skills helpful (e.g., Linux, Python, handling
of numerical weather prediction data).
* Language: Fluent English; German optional.


Send a cover letter, resume/CV, and the names and contact details
of two references to ``. Review of applications will begin
immediately but applications will be considered until at least
26 November 2018.
References will not be contacted without prior notification of the candidates.

Dr. Thorsten Simon
PostDoc Researcher

University of Innsbruck
Institute of Atmospheric and Cryospheric Sciences

Attachment: PhD_StatPostProcessing_IBK.pdf
Description: Adobe PDF document

Go to: Periods · List Information · Index by: Date (or Reverse Date), Thread, Subject or Author.