Applications are invited for a self-funded, 3-year full-time or 6-year part time PhD project.
The PhD will be based in the School of Computing and will be supervised by Dr Jiacheng Tan (School of Computing) and Dr Mel Krokos (School of Creative Technologies).
The work on this project could involve:
- Evaluating existing machine learning methods on sky survey data to gain understanding of the core characteristics of celestial objects from the perspective of machine learning and data science.
- Proposing, implementing and verifying novel methods for data representation, manipulation and learning of multi-spectrum astronomical structures using convolutional neural networks and their variants.
- Developing a prototype of scalable testbed for classifying, manipulating, and visualising large-scale datasets.
- Investigating synergies for repurposing and application of the resulting framework to suit other big data domains.
Project description
Next-generation observational astronomy instruments, e.g., the Square Kilometre Array or the recently launched James Webb telescope, are expected to produce big data at a rate of hundreds of gigabytes or terabytes per day, inviting interesting research challenges as it becomes increasingly difficult to process and understand such big amounts of data through traditional approaches. Over time, machine learning techniques have become fundamental in addressing the underlying challenges; classification algorithms such as DBSCAN have seen progress in identifying celestial objects, and dimension reduction techniques such as PCA have made it possible for researchers to plot and visualise intrinsic relations and synergies in highly complex datasets. Despite this, there are still gaps in research, with many classes of celestial objects yet to be investigated successfully by existing classification methods.
This project will extend previous work undertaken on the EU Horizon 2020 project (NEANIAS), where research partners from several European countries investigate the feasibility of creating an integrated cloud-based framework to provide on-demand services for processing such datasets. The core aim of the project is to develop and optimise a novel machine learning framework that exploits intrinsic structure in multi-spectral imaging and spectroscopic survey data, to efficiently identify a variety of celestial objects in large-scale datasets with accuracy on par with that of professional astronomers.
The project envisions the development of the proposed framework as a scalable testbed for prototyping novel workflows for classifying, manipulating, and visualising large-scale datasets coming from next-generation observational astronomy instrumentation. In the interest of cultivating research collaborations with international institutions and paving the way for further research funding, the project will also identify synergies for the repurposing of the resulting classification framework so that it may be applied to other big data communities and integrate seamlessly with the day-to-day workflows of scientists from a variety of domains.
General admissions criteria
You'll need a good first degree from an internationally recognised university or a Master’s degree in an appropriate subject. 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.
Specific candidate requirements
Candidates with experience in machine learning would be advantageous.
How to Apply
We encourage you to contact Dr Jiacheng Tan ([Email Address Removed]) to discuss your interest before you apply, quoting the project code below.
When you are ready to apply, please follow the 'Apply now' link on the Computing PhD subject area page and select the link for the relevant intake. 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.
When applying please quote project code:COMP5981023
Continue with Facebook
