University College London Featured PhD Programmes
University of Dundee Featured PhD Programmes
Engineering and Physical Sciences Research Council Featured PhD Programmes
University of Oxford Featured PhD Programmes
University College London Featured PhD Programmes

Machine Learning from Complex Disk Models (ESR9)

  • Full or part time
  • Application Deadline
    Monday, January 06, 2020
  • Competition Funded PhD Project (Students Worldwide)
    Competition Funded PhD Project (Students Worldwide)

Project Description

Molecular emission features observed in the near and mid infrared, for example with the VLT and JWST, will allow us to determine the chemical composition of the gas in protoplanetary disks in the planet-forming regions within 10 au around new-borne stars. This project will combine our previous expertise in modelling the line radiative transfer, chemistry and heating/cooling balance in disks, see Woitke et al. (2016, A&A 586, 103) with new machine learning techniques developed in the exoplanet community, e.g. Zingales & Waldmann (2018, AJ 156, 268). Neutral networks (NNs) will be trained on the predictions by tens of thousands of complex thermo-chemical 2D disk models, where we will apply the radiative transfer code FLiTs (Woitke et al. 2018, A&A 618, 57) to post-process the ProDiMo results to identify the spectral signatures. Using an algorithm developed for the ARCiS code (artful modelling of cloudy exoplanet atmospheres, author M. Min), these NNs will enable us to retrieve the chemical composition and the physical disk parameters, including their errorbars, from the observations. We can then use these new machine learning algorithms to quickly predict the emergent near-mid infrared line emission spectra from disks as function of physical parameters like UV irradiation, dust/gas ratio and element abundances, capable to thoroughly fit and analyze JWST data to determine the physical disk parameters and their observational uncertainties, taking into account all degeneracies.

This project is part of the Marie Sklodowska-Curie Innovative Training Network (ITN) CHAMELEON “Virtual Laboratories for Exoplanets and Planet Forming Disks”. The ITN combines the expertise of eight European research institutes (Universities of St Andrews, Groningen, Copenhagen, Edinburgh, Leuven and Antwerp, the Max-Planck Institute in Heidelberg and the Netherlands Institute for Space Research) to cover all relevant aspects for this complex modelling task, joining the expertise in planetary atmospheres and protoplanetary disks, including observation and interpretation. For a complete list of all open PhD positions within this training network please visit

The selected PhD students will be offered a fully funded PhD place at the University of St Andrews’ Centre for Exoplanet Science with training secondment for this position foreseen at the University of Copenhagen, with additional short training at the University of Groningen. The PhD student will receive a double degree from St Andrews and from Copenhagen. The funding will be commensurate to the standard scale for PhD students in according to the Marie-Curie funding rules. The successful PhD applicants will have to register at, and comply with, the regulations of the St Leonard’s Postgraduate College at the University of St Andrews and the rules from the University of Copenhagen. The successful PhD applicants will follow a doctoral programme including personal training in management, science communication, and teaching.

Funding Notes

CHAMELEON PhD studentships open to any nationality. However, Marie S Curie Actions have two strict eligibility criteria:

1. Applicant must be within the first four years (full-time equivalent research experience) of their research career (starting from the moment a degree is obtained that gives eligiblity to study for a PhD) and not have a doctoral degree. Adjustments can be made for career breaks.

2. Applicant must not have resided/carried out their main activity (e.g. work/studies) in the country where they have been recruited for more than 12 months in the three years immediately before the recruitment date (PhD start date).

Related Subjects

How good is research at University of St Andrews in Physics?
(joint submission with University of Edinburgh)

FTE Category A staff submitted: 36.90

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.