Generative AI-powered framework for optimisation of resilient critical minerals supply chains
Project ID: 2531bd1709
(You will need this ID for your application)
Research Theme: Circular Economy
Research Area(s): Process systems: components and integration, Artificial intelligence technologies, Operational Research
UCL Lead department: Chemical Engineering
Lead Supervisor: Vassilis Charitopoulos
Project Summary:
Hedging against climate change and by extension the feasibility of net-zero efforts depends largely on large-scale deployment of energy storage systems and widespread electrification of various sectors, including heat and transport. The deployment of storage and renewable technologies is a resource-intensive process that has put a lot of pressure on the resilient supply chains of key critical minerals required. For instance, according to the IEA’s latest report, the base case supply for lithium will be 60% short of primary demand in 2040.
Incumbent approaches on the criticality of minerals focus on linear input-output frameworks, in isolation from cross-sectoral evolution pathways towards net-zero. Moreover, systematic methods for evaluating the impacts of uncertainty on the future supply chains remain scarce. Leveraging recent advances in generative artificial intelligence (GenAI) this project will develop a first-of-its-kind hybrid optimal decision-making approach to hedging against disruptions in supply chains of critical minerals.
The successful PhD applicant will: (i) examine the impact of circularity on critical minerals supply chains and net-zero, via advanced process and supply chain optimisaton models, (ii) engineer an AI-based adversarial approach to studying supply chain vulnerabilities and the optimal selection of recourse actions to disruptions and (iii) develop a LLM-based model to automate scenario analysis and network resilience quantification.
The successful candidate will be based in the Department of Chemical Engineering at UCL and the world-leading Sargent Centre for Process Systems Engineering (SCPSE) working with Dr Charitopoulos and his team. You will be an enthusiastic and self-motivated person with a 2:1 (or higher) degree in an engineering or related discipline, and an enquiring and rigorous approach to research together with a strong intellect. Good team-working, observational and communication skills are essential. Experience with machine learning models, optimization algorithms and chemical process simulators, e.g., AspenPlus and proficiency in Python coding are strongly desirable.