Developing and Applying Probabilistic Tracking Methods for Bumblebee Learning Flights and Foraging
Details
Using the latest probabilistic machine learning techniques, you will develop systems for tracking insects in 3d and across the landscape, take part in field work to discover the secrets of bumblebee navigation and behaviour.
About the project
We will develop two methods for insect tracking, one at the meso-scale, allowing us to infer the full 3d complexity of learning flights; and one at the landscape-scale, to discover foraging paths of bumblebees. The project involves probabilistic machine learning, electronics, coding and field work. We are working with neuroethologists and ecologists, to apply these methods in the field.
(a) You will combine data from multiple tracking systems using Gaussian process-based Bayesian inference to compute 3d learn flights, taking part in the field work and work to discover, using cognitive modelling, how bees learn.
(b) You will develop a system using multiple low-energy Bluetooth high-gain transmitters to allow a receiver on the bee to collect data about its path.
The overarching theme in both is using Bayesian machine learning approaches to enable the use of low-cost equipment to record different aspects of bee flight.
Supervisor bio
Dr Mike Smith is a lecturer in probabilistic machine learning: modelling air pollution and solving insect tracking. Using Bayesian inference one can combine physically-informed priors with limited data to produce robust predictions. His projects involve exciting collaborations across a wide range of disciplines (ecology, neuroscience, chemistry, RF electronics, air-pollution and atmospherics).
About the Department and Research Group
The department is expanding its work in machine learning and AI with the launch of the strategic Centre for Machine Intelligence and membership of the Turing University network. The department’s research is world-leading (REF 2021) with an emphasis on collaboration and a focus on impact and quality. We are well supported by the wider university research community, for example by the expertise of Research Software Engineering, and the AMRC.
Candidate requirements
- A degree in an engineering or science discipline.
- Comfortable with relevant mathematics (linear algebra, calculus, probability).
- Ideally, competent at coding in a high-level language (e.g. python).
- The English language requirements must also be met. Details on this can be found here: https://www.sheffield.ac.uk/postgraduate/english-language
How to apply
To apply for a PhD studentship, applications must be made directly to the University of Sheffield using the Postgraduate Online Application Form. Make sure you name Michael Smith as your proposed supervisor.
Information on what documents are required and a link to the application form can be found here – https://www.sheffield.ac.uk/postgraduate/phd/apply/applying
Your research proposal should:
- Be no longer than 4 A4 pages, include references
- Outline your reasons for applying for this studentship
- Explain how you would approach the research, including details of your skills and experience in the topic area
Funding Notes
This PhD studentship will cover standard UK home tuition fees and provide a tax-free stipend at the standard UK Research Council rate (currently £17,668 for
2022/23) for 3.5 years. If you are an overseas student, you are eligible to apply but you must have the means to pay the difference between the UK and overseas
tuition fees by securing additional funding or self-funding. Further information on International fees can be found here – www.sheffield.ac.uk/new-students/tuition- fees/fees-lookup
