FindAPhD Weekly PhD Newsletter | JOIN NOW FindAPhD Weekly PhD Newsletter | JOIN NOW

Harvesting information from hyperspectral images

   Cardiff School of Physics and Astronomy

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Prof W W Langbein, Dr F Masia, Prof P Borri  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

The UKRI CDT in Artificial Intelligence, Machine Learning and Advanced Computing (AIMLAC) aims at forming the next generation of AI innovators across a broad range of STEMM disciplines. The CDT provides advanced multi-disciplinary training in an inclusive, caring and open environment that nurture each individual student to achieve their full potential. Applications are encouraged from candidates from a diverse background that can positively contribute to the future of our society. 

For centuries, light microscopy has been used by biologists and material scientists to unveil the physico-chemical properties of specimens. Scientists used their experience and knowledge to describe the sample by extracting qualitative information from visual assessment, and to recognise and separate different objects in the image. With the development of more sophisticated light sources, optics, labelling, and detectors, the last few decades have witnessed a rapid emergence of novel advanced imaging modalities. Among those, hyperdimensional imaging (HDI) adds a further dimension to the spatial ones to provide a step change in information content. For example, adding the light spectrum (indeed HDI is often also called hyperspectral imaging, HSI), providing for each spatial pixel a wavelength dependent intensity. In fluorescence microscopy, detecting the light emitted by fluorophores tagged to a biomolecule, HSI enabled imaging many biomolecules at once and correlate their spatial distribution. In environmental monitoring, satellite HSI allows the measurement of deforestation, pollution, etc. However, the increased information contained in the multi-dimensional voxel precludes their visual analysis, calling for suited algorithms.

 Driven by the necessity of harvesting such a wealth of information, we are developing efficient computational tools to extract salient quantities. Our analysis concept is based on a dimensionality reduction while exploiting prior knowledge such as physical constrains, to condense the HSI data into few quantitative properties. These are then used as input for machine learning approaches to identify and classify objects in the image. Owing to the generality of such methods, we were able to gain insight of both biological and inorganic specimens investigated with a range of imaging modalities, from vibrational microscopy (based on Raman [1] and Brillouin [2] scattering) to fluorescence lifetime imaging (FLIM) [3], as well as electron microscopy techniques such as low energy electron microscopy (LEEM) and scanning or transmission electron microscopy (SEM or TEM) energy dispersive x-ray (EDX).

In this project, the student will join research in our group towards the development of new algorithms for HSI data analysis, encompassing the following lines of investigation

1)  Solve a major issue in Raman vibrational imaging by factorization into separate fluorescence and Raman signals

2)  Extend the uFLIM-FRET method [3] to multiple donor-acceptor pairs and non-resonant processes.

3)  Improve the analysis of Brillouin data [2] by introducing additional physical constrains to the component spectral shape

4)  Explore and validate new methodologies for the unsupervised classification of objects extracted from analysis of HSI data [4]

5)  Extend the application of the method to electron microscope techniques [5]

Start date: 1st October 2022

The UKRI CDT in Artificial Intelligence, Machine Learning and Advanced Computing provides 4-year, fully funded PhD opportunities across broad research themes:

  • T1: data from large science facilities (particle physics, astronomy, cosmology)
  • T2: biological, health and clinical sciences (medical imaging, electronic health records, bioinformatics)
  • T3: novel mathematical, physical, and computer science approaches (data, hardware, software, algorithms)

 Its partner institutions are Swansea University (lead institution), Aberystwyth University, Bangor University, University of Bristol and Cardiff University.

Training in AI, high-performance computing (HPC) and high-performance data analytics (HPDA) plays an essential role, as does engagement with external partners, which include large international companies, locally based start-ups and SMEs, and government and Research Council partners. Training will be delivered via cohort activities across the partner institutions.

Positions are funded for 4 years, including 6-month placements with the external partners. The CDT will recruit 10 positions in 2022.

The partners include: We Predict, ATOS, DSTL, Mobileum, GCHQ, EDF, Amplyfi, DiRAC, Agxio, STFC, NVIDIA, Oracle, QinetiQ, Intel, IBM, Microsoft, Quantum Foundry, Dwr Cymru, TWI and many more.

More information, and a description of research projects, can be found at the UKRI CDT in Artificial Intelligence, Machine Learning & Advanced Computing website.

How to apply:

To apply, and for further details please visit the CDT website and follow the instructions to apply online.

This includes an online application for this project at (with a start date of 1st October 2022):

Applicants should submit an application for postgraduate study via the Cardiff University webpages including:

• your academic CV

• a personal statement/covering letter

• two references, at least one of which should be academic

• Your degree certificates and transcripts to date.

In the "Research Proposal" section of your application, please specify the project title and supervisors of this project.

In the funding section, please select that you will not be self funding and write that the source of funding will be “AIMLAC CDT”

The deadline for applications for the UKRI CDT Scholarship in Artificial Intelligence, Machine Learning and Advanced Computing (AIMLAC) is 12th February 2022. However, AIMLAC will continue to accept applications until the positions are filled.

For general enquiries, please contact Rhian Melita Morris [Email Address Removed]


The typical academic requirement is a minimum of a 2:1 physics and astronomy or a relevant discipline.

Applicants whose first language is not English are normally expected to meet the minimum University requirements (e.g. 6.5 IELTS) (

Candidates should be interested in AI and big data challenges, and in (at least) one of the three research themes. You should have an aptitude and ability in computational thinking and methods (as evidenced by a degree in physics and astronomy, medical science, computer science, or mathematics, for instance) including the ability to write software (or willingness to learn it).

For more information on eligibility, please visit the UKRI CDT in Artificial Intelligence, Machine Learning & Advanced Computing website

Funding Notes

The UK Research and Innovation (UKRI) fully-funded scholarships cover the full cost of 4 years tuition fees, a UKRI standard stipend of currently £15,921 per annum and additional funding for training, research and conference expenses. The scholarships are open to UK and international candidates.


[1] F Masia, A Glen, P Stephens, P Borri, W Langbein, Quantitative chemical imaging and unsupervised analysis using hyperspectral coherent anti-Stokes Raman scattering microscopy
Analytical Chemistry 85, 10820 (2013) – 10.1021/ac402303g
[2] F Palombo, F Masia, S Mattana, F Tamagnini, P Borri, W Langbein, D Fioretto, Hyperspectral analysis applied to micro-Brillouin maps of amyloid-beta plaques in Alzheimer's disease brains, Analyst, 143, 6095 (2018) – 10.1039/C8AN01291A
[3] F Masia, P Borri, W Dewitte, W Langbein, uFLIM - Unsupervised analysis of FLIM-FRET microscopy data, arXiv:2102.11002v2
[4] F Masia, I Pope, P Watson, W Langbein, P Borri, Bessel-Beam Hyperspectral CARS Microscopy with Sparse Sampling: Enabling High-Content High-Throughput Label-Free Quantitative Chemical Imaging, Analytical Chemistry 90, 3775 (2018) – 10.1021/acs.analchem.7b04039
[5] F Masia, W Langbein, S Fischer, JO Krisponeit, J Falta, Low-energy electron microscopy -- intensity-voltage data factorization, sparse sampling, and classification, submitted

How good is research at Cardiff University in Physics?

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs