Lead Supervisor’s full name & email address:
Dr Anuradha Pallipurath a.r.pallipurath@leeds.ac.uk
Co-supervisor name(s) & email address(s)
To be confirmed
Project summary:
This interdisciplinary project presents an exciting opportunity for an ambitious scientist or engineer to work across the boundaries of chemistry, physics and engineering, with opportunities to develop a broad portfolio of skills.
* Being able to predictively design particle properties is of great economic value and is applicable to a range of industries such as pharmaceuticals, agrochemical, additives, cosmetics and food.
* This project aims to develop machine learning models to predict a particle shape and size for a given chemical formulae and crystallisation method.
* Extractive Language learning models developed will be able to understand crystallographic information from the big data available in the CSD and enable future applications in considering other particle properties.
* This project will enhance the understanding of the value of metadata that could be associated with structural information and will help define the standards required for crystal structure data curation necessary to deliver Materials 4.0.
The project will combine data science and structural science work with researchers at Leeds and at the Cambridge Crystallographic Data Centre, and will involve development of Large language modelling to process metadata from structural information. You will also have an opportunity to learn machine learning methods for the analysis of structural information with a view to predict particle properties. You will be funded by the Royce CDT and the Cambridge Crystallographic Data Centre.
References:
None
Please state your entry requirements plus any necessary or desired background:
First class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline.
Subject Area:
Chemical Engineering, Materials Science, Pharmaceutical/Medicinal Chemistry, Physical Chemistry, Artificial Intelligence, Machine Learning
#J-18808-Ljbffr