Nuclear applications

Woking closely with industry, we apply and develop computational and experimental methods to detect radioactive and nuclear material across security, energy and medical applications. Our research draws on the latest artificial intelligence approaches including neural networks and genetic algorithms. 

Past projects

  • Machine learning techniques for nuclear decommissioning in collaboration with the ¿Û¿Û´«Ã½ Chemistry Department,  and part of the , 2019-2023
  • Optimised scintillator section through fuzzy logic in collaboration with the , 2021
  • Quantum dot enhanced detection technology, 2017-2021
  • Innovative alpha detection for environmental applications, 2018-2019
  • Thermoluminescence of fibres and beads for radiation dosimetry,  2018-2022

Selected publications and proceedings

  • J Wroe-Brown, C. Shenton-Taylor
  • A J Hickman, S Gomes, L M Warren, N A S Smith, C Shenton-Taylor
  •  L Lee-Brewin, R Holden, C Shenton-Taylor
  • A. Worthy, A. Mackenzie, N. Smith, and C. Shenton-Taylor SPIE IWBI 2024
  • An artificial neural network algorithm developed for shielded multi-isotope identification (2023) L Lee-Brewin, D. Read and C. Shenton-Taylor
  • C. Termsuk, S. Sweeney and C. Shenton-Taylor, Radiation Physics and Chemistry
  • K Ley, S A Hashim, A Lohstroh, C Shenton-Taylor, D A Bradley, Radiation Physics and Chemistry
  • X-ray Luminescence of Nanocomposite Plastic Scintillator using CuInS/ZnS Quantum Dots (2021)  C.L. Grove, I.H.B. Braddock, M.P. Taggart, C. Crean, S.J. Sweeney, P.J. Sellin, and C. Shenton-Taylor SORMA West
  • K Ley, S A Hashim, A Lohstroh, C Shenton-Taylor, D A Bradley, Radiation Physics and Chemistry
  • P K Soin, S Pitts, C Shenton-Taylor, J Barnes, IEEE Sensors Journal
  • S Parsons, A Langley, C Shenton-Taylor, A Lohstroh, IEEE Transactions on Nuclear Science 

PhD thesis

  • - Dr L Lee-Brewin
  • - Dr C Termsuk
  • - Dr C Grove
  • - Dr K Ley
  • - Dr S. Parsons

Areas of research interest include

  • Convolutional neutral networks applied to Nuclear Security
  • Machine leaning within Nuclear Health
  • Physics informed machine learning for the Nuclear Industry
  • AI deep learning methods applied to Nuclear Applications 
  • Genetic algorithms, sparse data techniques, fuzzy logic

Browse the University's frequently updated list of self-funded and funded studentships open for applications.

Areas of research interest include

  • Convolutional neutral networks applied to Nuclear Security
  • Machine leaning within Nuclear Health
  • Physics informed machine learning for the Nuclear Industry
  • AI deep learning methods applied to Nuclear Applications 
  • Genetic algorithms, sparse data techniques, fuzzy logic

Browse the University's frequently updated list of self-funded and funded studentships open for applications.