The Supernova Simulator: testing AI learning for target location and character across scales in space and time
Dr A Lundgren
Dr P Benson
Prof D Bacon
No more applications being accepted
Competition Funded PhD Project (Students Worldwide)
Applications are invited for a fully-funded three year PhD to commence in October 2019.
The PhD will be based in the Institute of Cosmology and Gravitation and will be supervised by Dr Andrew Lundgren, Dr Philip Benson and Professor David Bacon.
The work on this project will seek to determine:
-the detection and classification thresholds whereby the AI accurately detects significant anomalies and their location in 3D
-the timeframe and spatial extent over which events become self-organized
-conditions leading to one event triggering a second
Laboratory simulations offer a dynamic and flexible route to testing and verifying a numerical models and observations in the physical sciences. For example, in the Earth sciences, high force hydraulic presses are routinely used to simulate earthquakes under simulated stresses, collecting acoustic emission (the laboratory analogue to tectonic seismic data) using an embedded array of sensors that collectively generate 830 Gb/Hr (0.23 Gb/s) in the form of waveforms. In astronomy, observatories like the Laser Interferometer Gravitational wave Observatory (LIGO) and large cosmology surveys also generate data rates up to 1 Gb/s. In both cases a common challenge is that the vast wealth of continuous data cannot be adequately processed for events embedded in the medium by direct user intervention, due to these high data rates. Instead, the data requires processing without knowing where events will occur or even exactly what they look like. Machine learning and AI provide exciting new methods for detecting transient events (whether earthquakes or supernovae). To address this challenge, the controlled conditions of the rock physics laboratory will be used to compress a medium to failure, generating a stream of data containing events analogous to supernovae embedded in a transmissive medium. Data will be analyzed using a new range of AI algorithms, but with the advantage of allowing post-test comparisons to the final “sample” and with respect to a range of conditions or materials. In particular the project will seek to determine: (i) the detection and classification thresholds whereby the AI accurately detects significant anomalies and their location in 3D, (ii) the timeframe and spatial extent over which events become self-organized, and (iii) conditions leading to one event triggering a second. Success will lead to new tools across a range of physical sciences, ranging from the science of Earthquake localization, to fundamental questions relating to the evolution of the universe via LIGO and other new, expensive, observatories.
General admissions criteria
You’ll need a good first degree from an internationally recognised university (minimum upper second class
or equivalent, depending on your chosen course) or a Master’s degree in Medical Engineering, Mechanical Engineering or a similar discipline. In exceptional cases, we may consider equivalent professional experience and/or Qualifications. English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.
How to Apply
We’d encourage you to contact Dr. Andrew Lundgren ([Email Address Removed]) to discuss your interest before you apply, quoting the project code.
When you are ready to apply, you can use our online application form and select ‘Mathematics and Physics, Institute of Cosmology and Gravitation’ as the subject area. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV. Our ‘How to Apply’ page offers further guidance on the PhD application process.
If you want to be considered for this funded PhD opportunity you must quote project code MPHY4630219 UK/EU students and MPHY4830219 International students when applying.
Candidates applying for this project may be eligible to compete for one of a small number of bursaries available.
Successful applicants will receive a bursary to cover tuition fees for three years and a stipend in line with the RCUK rate (£14,777 for 2018/2019). International (non-EEA) applicants will also receive one return flight to London during the duration of the course through the Portsmouth Global PhD scholarship scheme.
The Faculty of Technology may fund project costs/consumables up to £1,500 p.a.