We recommend that you apply early as the advert may be removed before the deadline.

This PhD project addresses the "calibration problem" in particulate continuum models and particle simulations. Specifically, it focuses on developing robust methodologies for selecting and parameterising contact models, a crucial but challenging task due to the lack of standardised measurement techniques. The research will explore and refine "indirect" or "bulk" calibration methods, using characterisation machines to match simulation results with experimental data. This project will integrate advanced AI techniques, including machine learning for parameter optimisation (e.g., Bayesian optimisation, reinforcement learning), AI-driven model selection, and deep learning for data analysis and feature extraction from characterisation data. Surrogate modelling will be employed to reduce computational costs, and AI-based uncertainty quantification will enhance the reliability of calibrated parameters. Overcoming challenges like dimensionless indices, varying machine types across disciplines, and multi-parameter dependencies, the project aims to establish improved, AI-enhanced calibration strategies for diverse industrial and geophysical materials. Ultimately, it seeks to determine the optimal, AI-informed approach for selecting and calibrating discrete particle models for specific materials.

Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science or engineering related discipline.

To apply please contact Dr Anthony Thornton - Anthony.Thornton@manchester.ac.uk. Please include details of your current level of study, academic background and any relevant experience and include a paragraph about your motivation to study this PhD project.

We recommend that you apply early as the advert may be removed before the deadline.

This PhD project addresses the "calibration problem" in particulate continuum models and particle simulations. Specifically, it focuses on developing robust methodologies for selecting and parameterising contact models, a crucial but challenging task due to the lack of standardised measurement techniques. The research will explore and refine "indirect" or "bulk" calibration methods, using characterisation machines to match simulation results with experimental data. This project will integrate advanced AI techniques, including machine learning for parameter optimisation (e.g., Bayesian optimisation, reinforcement learning), AI-driven model selection, and deep learning for data analysis and feature extraction from characterisation data. Surrogate modelling will be employed to reduce computational costs, and AI-based uncertainty quantification will enhance the reliability of calibrated parameters. Overcoming challenges like dimensionless indices, varying machine types across disciplines, and multi-parameter dependencies, the project aims to establish improved, AI-enhanced calibration strategies for diverse industrial and geophysical materials. Ultimately, it seeks to determine the optimal, AI-informed approach for selecting and calibrating discrete particle models for specific materials.

Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science or engineering related discipline.

To apply please contact Dr Anthony Thornton - Anthony.Thornton@manchester.ac.uk. Please include details of your current level of study, academic background and any relevant experience and include a paragraph about your motivation to study this PhD project.