Machine learning accelerated Inverse Design of Graphene Nanoribbons for Green Energy
This is a fully-funded 4-year PhD position based in the HetSys Centre for Doctoral Training at the University of Warwick.
Project outline
Thermoelectric materials convert heat into electrical energy, crucial for sustainable power and waste heat recovery. Their efficiency is measured by the figure of merit, ZT. Achieving high ZT requires a delicate balance: high electrical conductance (G) and Seebeck coefficient (S) with low thermal conductance (k).
Graphene Nanoribbons (GNRs) are promising but currently, designing high-ZT GNRs is a slow, trial-and-error process, as the inverse problem is computationally intractable.
This project uses an AI-guided inverse design loop. A goal-directed AI proposes novel GNR architectures, which a fast machine learning model rapidly evaluates, accelerating the discovery of next-generation thermoelectrics.
Supervisors
Primary: Dr Sara Sangtarash (Engineering)
Dr Zsuzsanna Koczor-Benda (Chemistry)
Project Partner: University of Liverpool
The primary aim of this project is to overcome the computational intractability of designing high-performance thermoelectric materials by moving beyond the current trial-and-error design process.
The specific goals are:
- Develop an AI-guided inverse design loop specifically for GNRs.
- Leverage a goal-directed, structure-generating AI model to propose novel GNR chemical architectures that are conditioned on a high target Figure of Merit (ZT).
- Rigorously evaluate these proposed structures using a fast, high-fidelity Machine Learning (ML) surrogate model trained on key thermoelectric parameters (G,S,ZT).
- Enable the efficient filtering and selection of next-generation thermoelectric materials.
The student will contribute to several high-impact deliverables and discoveries over the four-year program:
Software/Workflow: Development of an automated, end-to-end scientific pipeline (AI/ML/Generative AI) for materials discovery.
Database: Creation of a massive, iteratively built database of GNRs with high ZT.
Models: Development of a computationally inexpensive Machine Learning surrogate model capable of predicting the Seebeck coefficient and conductivity.
Discovery: The discovery of several novel GNR structures predicted to exhibit a high ZT figure of merit.
Publications: High-impact publications in the fields of materials science, computational physics, and machine learning.
The student will gain a unique, interdisciplinary skill set essential for leadership in emerging technology sectors, covering technical, analytical, and transferable skills:
Quantum Transport & Generative AI: Employing quantum simulation methods with goal-directed AI models for GNR design.
Advanced AI/ML: Training and deploying ML surrogate models to quickly predict complex material properties.
High-Performance Computing (HPC): Mastering the full research pipeline as robust scientific software, including Git, Continuous Integration (CI), and containerisation.
Uncertainty Quantification (UQ): Assessing model reliability and guiding AI design based on both high performance (ZT) and low predictive error.
The student will graduate with a unique, interdisciplinary skill set spanning quantum mechanics, high-performance computing, and advanced generative AI/ML, perfectly positioning them for leadership roles in the emerging quantum and sustainable material.
These skills position you for careers in AI research, computational materials science, national laboratories, tech industry or academic research. The HetSys training provides a foundation for these skills through dedicated courses and cohort activities.
We require at least a II(i) honours degree at BSc or an integrated masters degree (e.g. MPhys, MChem, MSci, MEng etc.) in a physical sciences, mathematics or engineering discipline. We do not accept applications from existing PhD holders.
If you are an overseas candidate please check here that you hold the equivalent grades before applying.
For postgraduate study in HetSys, the term “overseas” or “international” student refers to anyone who does not qualify for UK home fee status. This includes applicants from the European Union (EU), European Economic Area (EEA), and Switzerland, unless they hold settled or pre-settled status under the UK’s EU Settlement Scheme.
If you are a European applicant without UK residency or immigration status that qualifies you for home fees, you will be classified as an overseas student.