Machine learning-augmented high-throughput catalyst design for NH3 synthesis

Machine learning-augmented high-throughput catalyst design for NH3 synthesis

Haber–Bosch process is a key industrial advancement in terms of NH3 synthesis. The process involves reaction between N2 and H2 feed streams at high pressure and temperature over Fe-based catalyst. Major thermodynamic incentives of energy efficiency and production economics are driving the research towards the development of novel catalysts which are capable of conducting the reaction at moderate temperatures and pressures. Designing a novel catalyst, to enhance the rate of a chemical reaction, is a challenging task which requires significant experimental work. Conventionally, discovery and optimization of new catalysts is done intuitively with time consuming trail-and-error based approaches. The recent progressions in machine learning and high-throughput platforms have made it possible to rapidly screen broader spectrum of materials and identification of relevant features contributing to the targeted reactions facilitating catalyst design and discovery. Moreover, processing of big volumes of data libraries is now viable, with the improvements in computational algorithms, allowing formulation of predictive models leading to systematic process optimisations and understanding of reaction mechanisms.


The current PhD project overlays a broader perspective from catalyst screening towards process optimisation. The preliminary component of the project requires data generation by a combination of high-throughput screening experiments, characterizations, and data mining from literature. Subsequently, unsupervised machine learning techniques will be utilised to capture unique patterns in the data targeted towards high reactivity of lattice N2 in metal nitrides catalyst structure signifying activity in the reaction. Relevant materials will be sorted and tested for NH3 synthesis with reinforcement learning based optimiser directing the experimentation process to achieve input parameters leading to optimum process efficacy with minimum experimentation runs. Data libraries generated from this study will be extended by mapping with quantum chemistry simulations, and subsequently be used to train machine learning models with enhanced predictive capability aiding further research in this area.



The candidate should have a Bachelor degree (Honours 1 or equivalent) or Master of Science in Computer Science, Computer Engineering, or equivalent from reputable institution, with a solid grasp in machine learning, data mining, mathematical optimization algorithms, language technology, and programming languages such as Python and Java. Students with Chemical Engineering or Materials Science background and expertise in computer science techniques mentioned above are also encouraged to apply. Excellent skills in spoken and written English are an absolute requirement. We expect the candidate to have demonstrated ability to do research, as seen through his/her Honours or MS thesis.



The application should include:

  • a cover letter/email with short description of yourself, your research interests in particular why you would like to apply for this PhD position and any past experiences that maybe relevant to this;
  • Full resume/CV
  • Copies of relevant academic transcripts and  completion certificate
  • Relevant publication (if any)
  • Name and contact info for 2 referees (previous supervisor or employer)



UNSW has a wide range of prestigious scholarships available to assist postgraduate researchers. These scholarships range from tuition fee scholarship, annual stipends ($27,082 per annum - tax free), travel scholarships and supplement/top-up. Candidate must meet a number of eligibility requirements for admission to Higher Research Degree. Step by step instructions on how to apply for admission and scholarships are available from Graduate Research School website.