Coventry University Featured PhD Programmes
University of Southampton Featured PhD Programmes
University of East Anglia Featured PhD Programmes

Deep learning based classification of aerosol particles from holographic imagery

Department of Earth and Environmental Sciences

About the Project

The impacts that aerosol particles have on the climate, air-quality and thus human health, are linked to their evolving chemical and physical characteristics. We know that many processes taking place in/on atmospheric aerosol particles are accompanied by changes in the particles’ morphology (size and shape). Likewise, particles of primary original [e.g. desert dust, volcanic ash, soot, pollen] can have widely varying morphological features that should nonetheless offer significant information to aid detection and classification. Whilst offline techniques can provide valuable insights into the abundance of particles according to their morphology, they suffer from low temporal resolution and require significant expertise in offline analytical methods. Very few experiments are able to record the temporal evolution of particle size and shape in situ in real time for resolving, for example, health responses to sudden changes in source types and/or as components of networks used to provide important indicators of potential impact on infrastructure [e.g. volcanic ash detection]. An emerging area of development to mitigate these challenges is digital holography (DH), which is very well suited to image fast moving objects, such as aerosol particles. This is a growing area of development in aerosol science, where the unique potential of using digital holography for aerosol characterisation is highlighted by multiple instruments previously developed and used in a variety of environmental conditions [Kemppinen et al 2020]. Whilst the development of experimental frameworks continue, the marriage of developing compact systems and associated data analytics is lacking. In this PhD you will thus develop and evaluate classification algorithms for turning images obtained from digital holography into distinct particle types.
Based on the amount of data generated, and the ongoing use cases around benchmark image classification techniques, we will rely mainly on deep learning approaches [e.g. Convolutional Neural Networks, Variational Autoencoders etc]. This is already being used with very promising results for pollen detection, but this PhD will explore a number of particle types and also the potential for transfer-learning approaches where we take industry standard classification routines and repurpose them for aerosol detection.

About the Centre for Doctoral training in Aerosol Science
Aerosol science is crucial to disciplines as broad ranging as transmission of disease, drug delivery to the lungs, climate change, energy and combustion science, novel materials, and consumer and agricultural products.

An aerosol is any collection of particles dispersed in a gas. The CDT brings together a multi-disciplinary team of 80 post-graduate students and academics from 7 UK universities spanning the physical, environmental and health sciences, and engineering. Our aim is to tackle the global challenges in which aerosol science is key.

Doctoral Training in Aerosol Science
During your doctorate, you will learn to research in diverse multidisciplinary teams, gain an advanced understanding of the core physical science of aerosols, and collaborate with industrial and public sector partners, equipping you to undertake ground-breaking research in aerosol science.

During the first 7 months of your PhD, you will join the CDT cohort based at the University of Bristol. Core training in aerosol science, research methods, professionalism and translation will be delivered by Team Based Learning. You will then undertake a short research project at your home or partner institution before starting your PhD research. You will gain experience outside academia in a placement with an industrial/public sector partner in Year 2 or 3.

More Information and How to Apply
Candidates who aspire to work in a multidisciplinary field, and hold or will achieve a minimum of an upper second-class undergraduate degree in any of these areas are encouraged to apply: chemistry, physics, biological sciences, life and medical sciences, mathematics and computer science, chemical and mechanical engineering, pharmaceutical and environmental sciences.
Visit our website:

Application Deadline:
Apply by 9am on Monday 25th January 2021– eligible applicants with a suitable academic background will be invited to attend an online recruitment and assessment day on 1st February 2021. Applications after this date will be subject to remaining availability of studentships.

Application Enquiries
David Topping []

Funding Notes

This is a 4 year PhD studentship funded as part of the EPSRC CDT in Aerosol Science.

The programme will commence in September 2021.


• Kemppinen, O., Laning, J.C., Mersmann, R.D. et al. Imaging atmospheric aerosol particles from a UAV with digital holography. Sci Rep 10, 16085 (2020).

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here

The information you submit to The University of Manchester will only be used by them or their data partners to deal with your enquiry, according to their privacy notice. For more information on how we use and store your data, please read our privacy statement.

* required field

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2020
All rights reserved.