[ABE-L] Fully funded industry-linked PhD studentship in Ireland focused on Statistical Deep Learning Models for Battery State Estimation.

[James.A.Sweeney]

Title:  Fully funded industry-linked PhD studentship in Ireland focused on Statistical Deep Learning Models for Battery State Estimation.

Description:
One full-time 4-year structured PhD project is available in the Department of Mathematics & Statistics at the University of Limerick, Ireland. The project is fully funded including fees, a tax-free stipend and expenses for computing equipment, generous budget for conference travel and materials.

We propose an exciting research programme where the PhD student will develop advanced statistical machine learning approaches (exploring the potential of deep gaussian processes and deep neural networks) for application in the research field of battery technology. This programme is in conjunction with Analog Devices, Inc. (NASDAQ: ADI) - ADI is a global semiconductor leader that bridges the physical and digital worlds to enable breakthroughs at the Intelligent Edge. Concentrated contact with ADI researchers is a key aim of the research project, allowing the student to observe research outputs being actioned in industry settings. It is also envisaged that, subject to visa requirements and funding, the studentship will include a placement at the Analog Garage Research Lab in Boston, MA, USA.

A key focus of the research programme will be on real-time estimation of battery state of health and state of charge for the purpose of improved optimisation of battery parameters. This is to facilitate improved end-user usage characteristics. This will require the development of low power algorithms that can be trained and run at the Edge, e.g. on low powered chips in cars. Another key focus is the development of predictive algorithms to expedite battery development for novel battery chemistries with the potential to accelerate the green transition via transfer learning strategies and approaches.

The challenges related to the computational and memory limitations will require the development of a suite of high dimensional statistical models adapted to run in such environments, as well as developing expertise in advanced computational statistics, numerical optimisation techniques and high performance computing.

Suggested skills:
The ideal candidate for this project is a student with a master's degree in statistical science, mathematics, computer science, or physics. In the first 12 months, the student will undertake training through a number of short of research projects focused on developing expertise in the field of Gaussian processes and application of neural networks (learning by doing), attending workshops, and mandatory PhD training in research skills provided by the University.
How to apply:
Queries and applications (cv & coverletter) can be sent to Prof. James Sweeney at james.a.sweeney em ul.ie<mailto:james.a.sweeney em ul.ie>
The application deadline is September 27th 2024.
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <http://lists.ime.usp.br/pipermail/abe/attachments/20240910/49ff6d12/attachment-0001.htm>