The University of Bristol's central hub for data science and data-intensive research, connecting a multidisciplinary community of experts across the University and beyond.
Lily Tu, 3rd year PhD student, in the Department of Mechanical Engineering at the University of Bristol
JGI Student Experience Profiles: Lily Tu (Ask-JGI Data Science Support 2022-23)
I came across machine learning models in a summer project just before my PhD and have since been looking to incorporate it into my PhD project, as data analysis forms a big part of my research field. I applied to join the Ask-JGI team so that I can share my experience and understanding of data science with other researchers across the university, as well as expand my horizon of how data science is applied in other disciplines. I found that the Ask-JGI team is a really good community of PGRs at similar stages as me. Although no one is supposed to know every aspect of data science, it was a great experience to discuss the queries over the weekly meetings and learn from each other.
From the technical aspect, I have worked with queries ranging from machine translation, data visualisation for biology experimental data, to spectral data in earth science. It was a great opportunity to hone my communication skills through talking to people from unfamiliar research backgrounds, getting hold of the key question that they want support from and sending through my thoughts and ideas. I think it’s an essential skill to have and prepares me well in future inter-disciplinary collaborations.
From the non-technical aspect, there’re lots of great initiatives and ad-hoc activities coming through the mailbox. I’ve attended the AI UK conference in London this year and helped at the e-scooter stand. It was good to have the exposure to communities outside my research field. I also took part in the DataFace project and did some filming for data analysis skill videos – that was some media experience I’d otherwise not have gained just from my PhD.
Marina Vabistsevits, Final year PhD student in Population Health Sciences at Bristol Medical School
JGI Student Experience Profiles: Marina Vabistsevits (Ask-JGI Data Science Support 2022-23)
What made you decide to apply to join the Ask-JGI team?
I applied to join the Ask-JGI team because I wanted to be involved in a wider data science community at the University of Bristol. I wanted to learn about data-intensive research in other disciplines and possibly gain data science skills outside my PhD project.
What did you find most rewarding about your Ask-JGI experience?
Being a part of the Ask-JGI team meant helping other researchers at the University with their data science queries. The queries we received involved anything from statistics, programming, data visualisation, machine learning, NLP, but also data ethics, data storage, software development, and even public engagement. I enjoyed being exposed to many aspects of data science, which would otherwise be impossible during one PhD programme. The most rewarding part of this experience was researching how to best help the person with their query to find the solution that would work for them, thereby helping them to advance their research at the University.
What sort of work did you do as a part of your Ask-JGI experience?
My favourite queries involved helping people with R programming, often including statistics, data visualisation, and app development. I was also involved in a long-term project with the Professional Services team at the University with another Ask-JGI student. We helped the team with analysing and producing insights from an extensive survey. This allowed the team to make data-informed decisions about the next steps, which may have a University-wide impact.
Another exciting part of my Ask-JGI experience was going to the AI UK 2023 conference in London to present and promote the Data Hazards framework developed by former colleagues at the JGI.
Would you recommend this experience to other students?
I would absolutely recommend joining the Ask-JGI Data Science support team. It is an excellent opportunity to learn about data science outside your immediate field, gain practical knowledge in new areas, and experience a data science consulting role! You also get to meet really interesting people and learn about the broader application of the skills you’re gaining in your current PhD programme.
JGI Seed Corn Funding Project Blog 2022-2023: Dr Wenzhi Zhou and Prof. Xibo Yuan
The power electronics industry is currently experiencing significant changes due to the emergence of ultra-fast transistors made from wide bandgap (WBG) materials, which are replacing silicon transistors. These new transistors have a switching speed that is 10 times faster, resulting in a 70% reduction in energy loss in converters and enabling motor drive systems to be reduced to less than half their previous size. However, the short voltage rise times (<20ns) and high frequencies (up to MHz) of WBG converters pose new challenges for the insulation of motor drive systems, leading to a drastic decrease in their lifespan.
PD is a well-established diagnostic indicator for assessing the deterioration of electric motor insulation in power converter-fed motor drive systems. It allows for the estimation of service requirements or the prediction of imminent failures. However, the adoption of WBG converters introduces new complexities that can impact the accuracy of PD measurements. Factors such as short voltage rise times (less than 20 ns, comparable to the time it takes light to travel 6 meters) and high frequencies (reaching up to MHz) associated with WBG converters pose significant challenges for insulation within motor drive systems, ultimately leading to a reduction in their lifespan.
To address these challenges and improve PD detection accuracy, we have undertaken research supported by funding from the Jean Golding Institute (JGI). As part of this endeavour, we have developed a specialized PD detection setup, as illustrated in Figure 1. Figure 1a depicts the schematic representation, while Figure 1b showcases the experimental setup we have established. Through this setup, we have conducted preliminary experiments to examine PD behaviour under different excitations, including two-level and three-level pulse width modulation (PWM) waveforms. An example of the PD signal observed under two-level PWM excitations is shown in Figure 2.
(A)
(B)
Fig. 1Experimental PD setup: (a) schematic and (b) hardware.
Fig. 2. The PD signal under the two-level PWM excitation.
The JGI funding has also facilitated collaboration with esteemed experts in the field, including Dr. Jin Zheng from the Engineering Mathematics Department and Dr. Wenbo Wang from Dynex Semiconductor. Their expertise and insights will play a crucial role in advancing our research efforts. Furthermore, we plan to leverage state-of-the-art artificial intelligence techniques to analyse the data we have collected. These techniques will enable us to extract meaningful insights and further enhance our understanding of PD in WBG-based motor drive systems.
JGI Seed Corn Funding Project Blog 2022-2023: Isolde Glissenaar
Sea ice thickness is a key variable when characterising an ice cover and its impact on the local environment and provides important insight into how an ice cover is changing in response to climate change. Unfortunately, observations of ice thickness are sparse, especially in the channels in the Canadian Arctic Archipelago. Sea ice thickness is also an important factor in assessing the safety of shipping in Arctic regions. The Canadian Arctic Archipelago is bisected by the Northwest Passage and is home to many northern communities that rely on marine traffic for resupply. Understanding the changes in ice thickness within the Canadian Arctic Archipelago and monitoring it in the future is therefore of vital importance.
The JGI funded my seed corn project to make sea ice thickness maps in the Canadian Arctic operationally available on a website. The ice thickness maps are created with a machine learning model that uses ice charts (maps of sea ice) from the Canadian Ice Service to estimate sea ice thickness. The ice charts have information about the sea ice concentration, the age of the ice, and the size of the separate ice floes. These characteristics all relate to sea ice thickness and can thus be used to create a proxy for sea ice thickness.
After comparing multiple machine learning methods, a Random Forest Regression model was found to give the best results. For my PhD, I applied this method on the archive of ice charts to determine sea ice thickness for the historic period 1996-2020. However, ice charts continue to be released every week, and this gave the possibility to run the model straight after a new ice chart is released and publish the resulting sea ice thickness map.
In this project I have automized the workflow so that a new sea ice thickness map is created as soon as an ice chart is released. This operational sea ice thickness map is subsequently made available online within 12 hours after the release of the ice chart. A beta-version of the website with both the operational ice thickness maps and the archive of sea ice thickness is now available on https://canadian-sit.streamlit.app/ for shipping navigators, local communities, and climate researchers to use.
Currently, the sea ice thickness maps can only be created for the winter months November-April. Future work would include extending the methods to the summer months when there is more shipping activity. The work can also be extended to the seas around Greenland, as the Danish Meteorological Institute creates similar ice charts for these regions.
For this project I collaborated with the Canadian Ice Service who create the ice charts and are responsible for communicating ice conditions with stakeholders in the region. If the method proves effective and the website reliable, the Ice Service could consider including the sea ice thickness maps in their advice to stakeholders.
The Jean Golding Institute Seed Corn Funding is a fantastic opportunity to develop multi and interdisciplinary ideas and promote collaboration in data science and AI. We are delighted that a new cohort of interdisciplinary research has been supported through this funding.
The Winners
Tom Williams is an Associate Professor in Molecular Evolution at the University of Bristol, UK. He obtained an undergraduate degree in Genetics and a PhD in bioinformatics from Trinity College Dublin, Ireland, the latter under the supervision of Mario Fares. From 2010-2015, he worked as a postdoc with Martin Embley at Newcastle University, UK, on phylogenetic methods and the origin of eukaryotic cells. He started a research group at the University of Bristol in 2015.
Tom’s work in the lab focuses on studying the early evolution of life, and the genomes of microbes, using phylogenetic and comparative genomic methods (that is, with bioinformatics, on a computer). The key questions relate to the nature of early life, the phylogeny of prokaryotes, the processes of microbial/genome evolution, and the origin of eukaryotic cells.
Neo Poon is a behavioural data scientist and is currently a Senior Research Associate in the Medical School at the University of Bristol. Neo’s research focuses on the socioeconomic factors behind self-medication behaviours, with his doctoral research (PhD Behavioural Science at Warwick Business School) covering a range of topics related to human decision making, including consumer choices and public opinions. He also has research experience in healthcare and well-being, as well as teaching experience in statistics and behaviour change which has led to two awards.
Emmanouil Tranos is a Professor of Quantitative Human Geography at the University of Bristol, and a Fellow at the Alan Turing Institute. Emmanouil has published extensively on the geographies of various digital technologies: from the internet’s backbone networks and the internet’s uptake at a global scale, to the usage of mobile phone and internet speeds at a very granular level of spatial and temporal resolution.
In their research they have been developing research frameworks and computational workflows to use the digital traces human and, more specifically, the economic activities left behind, to better understand cities, their structure, and economies. This is important, as such digital traces allow us to observe behaviours and phenomena and, consequently, answer research questions that traditional data sources have not allowed us to do. To effectively handle the complexities of such unconventional data – from mobile phone records to very large archives of websites – Emmanouil’s research employs diverse methodological tools, from data science, computational linguistics, as well as network science alongside more traditional geographical methods.
Jin Zheng is a Lecturer in Data Science in Engineering Mathematics Department at the University of Bristol. Her research focuses on machine learning, big data engineering, cloud computing, natural language process, with particular attention to financial market. In their project, her team will develop the first open-sourced and intelligent algo-trading platform, which could be used not only by researchers and individual users, but also be used as an education tool for students in Finance, Data Science, Computer Science, and Financial Technology majors. With this platform, the users could create their own trading robots, develop their trading strategies, and design and construct their own trading algorithm.
Cheryl McQuire is a public health researcher with a particular interest in maternal and child health, specialising in foetal alcohol spectrum disorders (FASDs). Cheryl is a NIHR SPHR Postdoctoral Launching Fellow and Programme Manager for the SPHR Healthy Places, Healthy Planet Programme and is based in the Centre for Public Health, within the Population Health Sciences Institute at the University of Bristol. She has expertise in both quantitative and qualitative analyses, natural experimental approaches, causal inference methods and systematic reviews.
During her career Cheryl has led discussions at parliamentary roundtables, convened by the Department of Health, All-Party Parliamentary Group (APPG) for FASD and Welsh Government and has used this to advance policy recommendations for FASD (Policy Bristol Briefing 65). Her work on the screening prevalence of FASD, using ALSPAC data, was featured in over 400 media outlets worldwide, including appearances on Radio 4’s Women’s Hour, Sky News and Talk Radio.
Wenzhi Zhou is a Research Associate with the Electrical Energy Management Group (EEMG) within the Department of Electrical and Electronic Engineering at the University of Bristol. His background stretches from power electronics to electrical machine. His research interests are mainly oriented towards future applications in the fields of electromechanical propulsion, power conversion and renewable energy. Until now, he has been working on the development of high power density, high efficiency and high reliability drive systems for sustainable mobility and advanced industry automation/robotics, aiming at disruptive performance improvements.
Jasmina Stevanov & Laszlo Talas
Jasmina Stevanov is a Research Fellow at the Bristol Veterinary School. Trained as an experimental psychologist and artist, she incorporates these disciplines through her research in the neuroscience of aesthetics, vision, and art perception. In her research she is using machine learning and eye-tracking techniques to explore individual preferences for visual art, with the goal to offer automatic feedback about observers’ aesthetic preferences and predict their future choices.
Laszlo Talas is a Lecturer in Animal Sensing & Biometrics at the Bristol Veterinary School. His research interests primarily focus on computational approaches to visual perception, including animal, human, and machine vision. With a background in zoology and experimental psychology, he is particularly passionate about how visual scenes can be “understood” using computers and what comparisons can be drawn with biological visual systems.
Sion Bayliss and Daniel Lawson
Sion Bayliss
In a collaboration between Bristol University Veterinary School and Bristol University School of Mathematics, Sion Bayliss and Daniel Lawson will be conducting a research project titled; ‘Assessing the recombinogenic potential of novel bacterial lineages: Towards an early warning system for problem pathogens.’
Daniel Lawson
In this collaborative research project they will apply innovating methodologies to assess the potential for newly identified bacterial lineages to uptake foreign DNA, and increase their potential to become the problem pathogens of the future.
More information
For more information about other funding we have provided and schemes we offer, find out more on our Funding page, and take a look at previous projects we have supported, on our Projects page.
