Improving satellite communications using AI (Ref: CO/SD-SF1/2026)

About the Project

Spiking Neural Networks (SNN) are an energy efficient alternative to Artificial Neural Networks (ANN). Low Earth Orbit (LEO) satellites could particularly benefit from using SNNs to perform Artificial Intelligence (AI) workloads in an energy-efficient manner. Availability of off-the-shelf components for assembling satellites and lower costs for launching have increased usage of LEO satellites for applications like climate monitoring, search-and-rescue, satellite broadband. Many of these applications rely on onboard deployments of AI which can impose a significant burden on the power resources of a satellite. This project will focus on developing efficient SNN-based techniques and demonstrate their effectiveness for applications onboard LEO satellites.

Name of primary supervisor/CDT lead:
Shirin Dora s.dora@lboro.ac.uk

Name of secondary supervisor:
Mahsa Derakshani https://www.lboro.ac.uk/schools/meme/staff/mahsa-derakhshani/

Entry requirements:
Students should have a bachelor degree in computer science or mathematics and be comfortable with programming.

English language requirements:
Applicants must meet the minimum English language requirements. Further details are available on the International website (http://www.lboro.ac.uk/international/applicants/english/).

Bench fees required: No

Closing date of advert: 31st July 2026

Start date: April 2026, July 2026, October 2026

Full-time/part-time availability: Full-time 3 years, Part-time 6 years

Fee band: 2025/26 Band RB (UK £5,006, International £28,600)

Project search terms:
artificial intelligence, communications engineering, machine learning, satellite communications, neuromorphic computing, low-power AI, LEO satellites