About the Project
Sensors in laboratories, factories, satellites and particle detectors produce continuous streams of data. Most of that data is routine, represented by regular machine functioning outputs, steady telemetry, ordinary particle collisions. The energy spent by traditional computing to process these data is generally the same on every sample. Therefore, as the data volume grows, so does the energy consumption for its processing. In neuromorphic chips, spiking neurons fire and draw more power when a…
signal crosses a threshold, so streams of ordinary data are less expensive to process. The research question of this PhD project has two strands: first, whether the spiking-energy behaviour of neuromorphic architectures can be adapted to be employed in outlier detection, and secondly whether such architectures have a lower carbon impact throughout their lifecycle in a case study. This PhD project builds on BOA, a machine-learning compressor developed at the University of Manchester, built on a state-space architecture that compresses scientific data by predicting each byte from the ones before it. That same prediction can be used as an anomaly score: unexpected input produces a poor prediction and a high score. Our early results show that BOA flags new-physics-like signals in simulated Large Hadron Collider data without being specifically trained to recognise them.
In the first strand of this project, the student will convert BOA into a spiking neural network, building on recent work that distilled a comparable state-space model into spiking form. The student will run it on neuromorphic hardware developed in Manchester, moving from simulation to the physical chip, using particle physics data as a benchmark. The student will test whether the network's spike rate, and so its energy draw, tracks the anomaly score of its input. If it does, the chip's own power consumption could act as an anomaly signal.
In the second strand, the student will assess the full environmental cost of compression on neuromorphic hardware, including embodied carbon. Neuromorphic hardware processes single samples far more efficiently than conventional processors, but that advantage narrows once conventional hardware batches its workload and the embodied carbon is considered. The student will compare a spiking version of BOA on neuromorphic hardware against a conventional, quantised baseline, tracking emissions from manufacturing through to daily operation. The student will identify which compression workloads (e.g. archival storage or live streaming), are feasible and would favour neuromorphic compression. This strand builds on our earlier work evaluating the environmental impact of neural data compression.
The student will start from particle physics data and then extend the methods to other fields, working with partners across the University. The student will join the Manchester particle physics group and University-wide networks for research software and computing, and will receive training in particle physics, modern machine learning for compression and anomaly detection, and both conventional and neuromorphic computing. The student will present results locally and internationally, supported by postdocs and research software engineers.
This project is expected to start in September 2027.
Before you apply:
We strongly recommend that you contact the supervisors for this project before you apply.
How to apply:
To be considered for this project you must complete a formal application through our online application portal. If you already have an applicant account this link will directly open an application for PhD School of Natural Sciences Scholarships. If you don’t already have an applicant account, please follow the instructions here.
When applying, please specify the full title and supervisor/s of the project, details of your previous study, and names and contact details of two referees. You must also upload a Supporting Statement describing your motivation to apply to the project, your CV and transcripts of awarded and in-progress university qualifications. Please note late or incomplete applications will not be considered.
Equality, diversity and inclusion are fundamental to the success of The University of Manchester and central to all our activities. A diverse research community strengthens creativity, productivity and quality, while increasing the societal and economic impact of our work. We welcome applicants from all career paths, backgrounds and sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation or transgender status.
We welcome applications from candidates returning to study after a career break or experience in other roles. Flexible study arrangements may be available, including part-time study at 50%, 60% or 80%, subject to the requirements of the project and funder.
Eligibility: The standard academic entry requirement for this PhD is an upper second-class (2:1) honours degree (or international equivalent) in Physics, Computer Science or Engineering OR any upper-second class (2:1) honours degree and a Master’s degree at merit (or international equivalent) in Physics, Computer Science or Engineering. Previous research experience in software programming is desirable.
This project will remain open until filled.
If your application is submitted by 1st November 2026, you can expect a decision by 18th December 2026.
If your application is submitted by 15th January 2027, you can expect a decision by 30th March 2027.
Self or externally funded students can also be considered for this project.
FSE_SoNS
Funding Notes
Funding covers tuition fees, an annual stipend at the UKRI minimum rate (currently £21,805 per year), and a research training support grant of up to £2,500 per year for the full 3.5-year programme.