PhD in Machine Learning for In Situ Materials Characterisation

About the project

About the Project Doctor of Philosophy (PhD) in Machine Learning for In Situ Materials Characterisation Host: Department of Materials Science and Engineering, Monash University Location: Clayton campus, Melbourne, Australia Duration: 3.5 years, full time Supervisor: Dr Yuxiang Wu ( yuxiang.wu@monash.edu ) Start: 2027, flexible by agreement Stipend: AUD 41,100 per annum, tax free (2027 rate) Course code: 3291 Doctor of Philosophy (PhD) Scholarship status: Fully funded PhD scholarship available for an outstanding domestic or international candidate. Project overview We are seeking an outstanding PhD candidate to develop machine learning methods for advanced and in situ materials characterisation . Modern characterisation techniques generate increasingly complex datasets describing microstructure, crystallography, phase evolution, chemistry and morphology . This project will investigate how machine learning can learn physically meaningful representations directly from these data and help understand how materials evolve during processing and phase transformation. The candidate will work with experimental datasets from techniques such as electron microscopy, EBSD, X-ray diffraction, X-ray imaging and in situ characterisation . Depending on the candidate's background and research direction, approaches may include computer vision, representation learning, graph neural networks, multimodal learning and scientific machine learning . A central aim is to develop quantitative relationships linking: processing → material evolution → microstructure → properties Applications will focus primarily on metals, phase transformations and materials processing, including emerging low-emission metallurgical processes. Research environment The candidate will join the Metallurgy and Corrosion Research Cluster in the Department of Materials Science and Engineering at Monash University and work in a multidisciplinary environment spanning materials science, advanced characterisation, computational modelling and artificial intelligence. Monash provides extensive facilities for electron microscopy, X-ray characterisation, in situ materials analysis, high-temperature experimentation and scientific computing . Candidate profile Applicants should have a background in Materials Science, Metallurgical Engineering, Mechanical Engineering, Physics, Computer Science, Data Science, Chemical Engineering , or a closely related discipline. Candidates should demonstrate: Strong interest in machine learning, materials characterisation or computational materials science. Strong quantitative and problem-solving skills. Capacity for independent, self-motivated research. Excellent communication and teamwork skills. Previous experience with machine learning, computer vision, graph neural networks, Python, SEM/EBSD, XRD, image analysis, microstructure characterisation or materials modelling is desirable. Candidates are not expected to already be experts in both machine learning and materials science. Strong candidates from either background who are interested in working across the interface are encouraged to apply. Note: Applicants who already hold a PhD degree will not be considered. How to apply Before submitting an Expression of Interest, please email Dr Yuxiang Wu at yuxiang.wu@monash.edu with your CV, academic transcripts and a brief description of your research interests.

Research areas