Research Fellow

Contract Type: Fixed Term contract up to October 2027

Background

We invite applications from a highly motivated postdoctoral scientist to deliver automatic classification capability based on machine learning approaches for RSO characterization and anomaly detection using space-borne sub-THz Inverse Synthetic Aperture Radar Imagery. The researcher will be part of the research team within the renowned Microwave Integrated Systems Laboratory (MISL) in the University of Birmingham, where research fellow will be based, and the Queen’s University of Belfast group headed by Prof. Iain Styles  to work on the EPSRC funded project Multi-dimensional quantum-enabled sub-THz Space-Borne ISAR sensing for space domain awareness and critical infrastructure monitoring – SBISAR, to create a framework of novel supervised and unsupervised learning approaches and image processing methods for characterisation of Resident Space objects suitable for space-edge computing.

Main Duties

• Develop research objectives and proposals for own or joint research, with assistance of a mentor if required
• Contribute to writing bids for research funding
• Analyse and interpret data
• Apply knowledge in a way which develops new intellectual understanding
• Disseminate research findings for publication, research seminars etc
• Supervise students on research related work and provide guidance to PhD students where appropriate to the discipline
• Contribute to developing new models, techniques and methods 
• Undertake management/administration arising from research
• Contribute to Departmental/School research-related activities and research-related administration
• Contribute to enterprise, business development and/or public engagement activities of manifest benefit to the College and the University, often under supervision of a project leader
• Collect research data; this may be through a variety of research methods, such as scientific experimentation, literature reviews, and research interviews
• Present research outputs, including drafting academic publications or parts thereof, for example at seminars and as posters
• Provide guidance, as required, to support staff and any students who may be assisting with the research
• Deal with problems that may affect the achievement of research objectives and deadlines
• Promotes equality and values diversity acting as a role model and fostering an inclusive working culture.

Specific tasks will include:

• Investigation and development of suitable algorithms for image and point cloud segmentation to distinguish RSO features based on the statistical and semantic characteristics;
• Investigate supervised ML approaches to detect anomalies in RSOs, trained on an ISAR hybrid dataset developed as part of the project;
• Investigate unsupervised and supervised ML approaches to teach a model to adapt to unseen observations;
• Identify best methods based on key performance indicators and develop tailored algorithms and inference approaches;
• Assess the space-edge computing requirements and optimize developed approaches accordingly.

Person Specification

The applicant should have a PhD qualification (or close to completion) in the fields of ML, computer vision, radar image processing, signal processing, classification in radar-based remote sensing. Upper class degree in computer science,  physics, electrical engineering or a related discipline (or equivalent qualifications) are expected with experience in ML-based data processing. Strong background in radar, signal processing and related technologies is highly desirable

Informal enquiries to Professor Marina Gashinova, email: m.s.gashinova@bham.ac.uk 

To download the full job description and details of this position and submit an electronic application online please click on the 'Apply' button above.

Valuing excellence, sustaining investment
We value diversity and inclusion at the University of Birmingham and welcome applications from all sections of the community and are open to discussions around all forms of flexible working

Closes: 19/02/2025 

Advert information