• Ellie Smallwood

  • Theme:Digital Systems, Optimisation and Integration
  • Project:Autonomous Anomaly Detection and Self-healing in a smart test environment
  • Supervisor:Richard Burke
  • Industry Partner: AVL
  • Back to bio


Ellie completed a BSc in Environmental Sciences from the University of Leeds in 2020, gaining an understanding and appreciation for the complexity of environmental, social, and technological systems. From this, an overarching goal of climate change mitigation led her to complete an MSc in Energy Systems and Data Analytics at UCL, within which the connectivity of transport, built environment, and social and political sectors were explored using machine learning techniques on big data, to identify plausible solutions for decarbonisation. Projects completed included investigating the driving factors of micromobility demand, and carrying out an uncertainty analysis on global net zero pathways using clustering for her thesis. Outside of her university work Ellie was also involved in additional research roles, including looking into public responses to carbon taxes, and how demographics can impact this, and also the applicability of digital platforms to inform and engage the public in local policy changes.

It is due to the dynamism of the transportation sector, and the challenge that it poses to reaching net zero targets by 2050, that Ellie chose to pursue this area of study. Her specific research interests revolve around sustainability and efficiency; by utilising machine learning techniques she hopes to identify novel approaches that unlock the potential of technological innovation, policy measures, and behavioural change for large scale decarbonisation.

Research Journey: Year 1

My first key takeaway from my first year on the AAPS CDT relates to the community spirit that it provides. After a year studying for my MSc completely remotely during COVID-19, being in person with a group of like-minded and enthusiastic students was extremely valuable. Although it may seem unimportant to some, being able to discuss my interests with others, gain their opinions and, in general, experience the benefits from a social setting is something that I look back on very fondly. It also was very impactful to my development over that year. The transdisciplinary nature of the cohort meant that I was able to learn about new perspectives and research approaches, whilst also being reassured that my goal for my research to span disciplines held merit; I was able to understand how my research could be applied to the engineering sector, whilst still being aligned with my environmental sciences and data analytics background.
Drawing on this, the cohort structure also had benefits which were visible through tangible outputs. All of our assignments had some element of group collaboration, whether that be actually working together on a singular project or simply requiring us to inform our work with insights from other disciplines represented in the group. Two assignments in particular come to mind - the first was an individual essay on how our own discipline and expertise could influence the automotive sector. For me, this meant examining which of my skills was relevant to tackling a challenge currently faced in the sector; I strongly informed this by speaking to my peers about how their work also fitted into the automotive sector and thus, we could identify where our skills would help each other. This truly drew on the transdisciplinarity that the AAPS CDT promised when I first applied to them.
The second assignment that I particularly remember, was a semester long group project to design a mobility solution. This project technically spanned two semesters, with the ideation phase lasting the first two months and the specification and design phases occurring over  approximately three months. The second half however stands out to me especially, with the fourteen cohort members all coming together to contribute their skillset to our group vision there was a real sense of excitement, as well as pressure, to produce a good final output. I believe we did achieve this since we presented the project at the Department of Mechanical Engineering’s annual design exhibition. My part of the project was also useful to me going forward since I was able to link my knowledge from my previous degrees and apply it directly to an automotive concept. I first estimated the carbon emissions associated with different trips made by our small, city-car-like solution based on grid carbon intensity, and then I investigated how the accompanying app could be designed to encourage customers to choose the travel option with the lowest environmental impact. This project therefore was not only exciting to be a part of, due to its team-motivation, but also confirmed that I could apply my skillset to automotive challenges.
Finally, the MRes year concluded with a 9 week summer project (thesis). I wrote my report on the same topic that my PhD is on: anomaly detection methodologies for automotive testbed data. The project provided benefits to my development in three key areas; first, it allowed me to get back into the rhythm of independent working, finding how I could optimise my time, ready for the PhD. Second, it allowed me to brush up on my more specialised technical skills: coding in R, and re-acquainting myself with machine learning algorithms that I had learnt in my masters previously but had not used during the MRes year. I am also glad that I chose to undertake my thesis on the same topic as my PhD since it provided me with some useful insights and starting points from day 1. Although this project may not directly be included in my final PhD thesis, the takeaways from it will have guided the early stages and provided me with good foundational knowledge of the topic, thus saving valuable time and energy.

© Copyright 2021 AAPS CDT, Centre for Doctoral Training in Advanced Automotive Propulsion Systems at the University of Bath