The following questions are aimed to capture a snapshot of an individual student within one the CDT cohorts. During proposal development, hypothetical students (with real Southampton supervisors, and hypothetical industrial ones) are used to help shape the training programme and give light to how the CDT would be experienced from the perspective of the student. If successfully funded, the same questions will be reused to help us tell the stories of our actual students.
XXX obtained an MMath degree from the UK. She studied a variety of topics in applied mathematics during her Masters year spanning numerical analysis, machine learning, modelling networks and information theory. For her Masters project she worked on modelling population compliance with Covid restrictions, using transportation data collected during Covid lockdowns to calibrate and test models.
During her Masters project XXX became interested in carrying out doctoral research on developing AI techniques to analyse complex spatiotemporal datasets, in the context of modelling and understanding physical and socio-economic phenonema. She was attracted to the interdisciplinary nature of the centre for doctoral training, and the wide range of PhD projects available. The CDT offered her opportunities to learn about the variety of techniques used to analyse complex data across different disciplines. In addition she was keen to work closely with industrial partners, both for internships and for research projects, and to have access to training around working in interdisciplinary teams.
XXX is supervised by Dr Adam Pound and Professor Marika Taylor in the School of Mathematical Sciences and Dr Srinandan Dasmahapatra in ECS. The main focus of her doctoral research is on developing templates and data analysis pipelines for space based gravitational wave detection, and she is partly funded by the European Space Agency. Gravitational wave observations are used to uncover fundamental physics but they also give very high precision geophysical information relevant to understanding flooding and droughts. During her doctorate XXX has also carried out short duration projects in collaboration with industrial partners such as Small Spark and Ikerlan using her skills on geospatial data analysis for applications such as identifying key features from satellite images using learning methods.
XXX had a strong theoretical background from her Masters studies and the training programme of the CDT has helped her to develop skills in building data templates from numerical models, applying learning methodologies and working with large complex data geospatial datasets. She benefits from working with doctoral researchers from different application areas, sharing approaches and methodologies with them. Work with industrial partners has enabled her to directly apply the methods developed during her doctoral research.
XXX has benefitted from working with researchers from a variety of disciplines. The techniques being used by XXX are new to the field in which she works and draw extensively from expertise in the geospatial cluster at Southampton. The opportunities for collaboration with industry provided by the CDT have given XXX the possibilities to carry out short duration projects applying her skills, which will strengthen her profile for future academic and industrial work. She has successfully bid for additional UKSA support for her research, supported by the generic skills training provided by the CDT.
XXX entered the CDT programme with a strong theoretical background but with little experience with working with real world data sets and with working collaboratively. Working with the cohort of students allowed her to learn techniques for working with complex data, and to understand the different terminologies and approaches used in diverse fields. The training programme provided by the CDT gave her experience of working optimally in groups, combining different skills and diverse viewpoints. The training has helped her to communicate well with stakeholders, adjusting the language and descriptions according to the backgrounds of the stakeholders.
The PhD research has generated publications in science, advancing the field of gravitational wave detection, and has also been used by external companies through collaborative projects.
The studentship has been supported in part by the European Space Agency, as part of its programme to develop the LISA gravitational wave detectors. The student has also worked collaboratively on several month projects with SMEs such as Small Spark.
XXX has spent several months working on collaborative projects with companies such as Small Spark, applying the methodologies developed during her doctorate to commercial questions.
XXX plans to apply for research fellowships to develop her own research group. In parallel she will look to secure impact acceleration funding and possibly enterprise fellowships to continue applying her research to commercial problems.
Most researchers working on gravitational wave data do not have the opportunity to interact extensively with a wide range of geospatial data science experts from computer science, engineering and geography. She has been able to learn about relevant geospatial AI methodologies from across many different disciplines. She has also had the opportunity to interact with researchers who work on hardware and data collection/observations, which has given her stronger insights into her own work on data analysis. The computing infrastructure provided by the CDT has been essential to the delivery of the project.