Dr Tanu Tiwari
- Post Doctoral Research Associate
Contact
Connect
About
- 2026–Present: Postdoctoral Research Associate, ADAPT-EAF Programme, University of Cambridge
- 2025–2026: Machine Learning Engineer, Zyomax Ltd, London
- 2025–2026: Research Collaborator, Queen Mary University of London
- 2022–2026: Doctoral Researcher, Brunel University London
- 2023–2024: Masters Data Science, ExcelR Institute
- 2020–2021: MSc Materials Science and Engineering, University of Birmingham
- 2015–2019: BTech Materials and Metallurgical Engineering, MANIT Bhopal
Dr Tanu Tiwari is a Postdoctoral Research Associate working at the interface of materials science, machine learning, and sustainable steel manufacturing. Her research focuses on AI-driven alloy design, steel recycling optimisation, and probabilistic computational modelling for sustainable metals processing. Her research experience includes the development of machine learning frameworks, digital twins, and optimisation tools for steel and alloy recycling, process modelling, and materials property prediction using industrial and experimental datasets. She has worked on computational approaches for predicting the effects of scrap composition, residual elements, and processing conditions on alloy performance and processability.
Dr Tiwari has expertise in machine learning, artificial intelligence, Bayesian optimisation, scientific programming, and computational materials engineering using Python, MATLAB, and Thermo-Calc. Her current research interests include sustainable steelmaking, EAF steel optimisation, residual element prediction in recycled steels, computational metallurgy, and integrated AI frameworks for advanced structural materials design.
Research
Research interests
- Sustainable Steelmaking
- EAF Steel Production
- Steel Recycling
- Aluminium Recycling
- Data-Driven Alloy Recycling
- Computational Metallurgy
- Materials Informatics
- Machine Learning for Materials Science
- Probabilistic Modelling
- Alloy Design
- Residual Element Prediction in Steels and Aluminium Alloys
- Data-Driven Materials Design
- Structural Steels
- Aluminium Alloys
- Process–Microstructure–Property Relationships
- Digital Twins for Manufacturing
- Bayesian Optimisation
- Thermodynamic and CALPHAD Modelling
- AI for Sustainable Manufacturing
- Circular Economy Materials Processing
My research focuses on the development of data-driven and probabilistic computational frameworks for sustainable steel and aluminium alloy recycling. This includes integrating industrial and experimental datasets containing alloy composition, processing parameters, microstructural information, and mechanical properties to enable predictive modelling of alloy performance and processability. My current work within the ADAPT-EAF programme focuses on AI-assisted optimisation of recycled steels for electric arc furnace (EAF) production. This involves modelling the influence of residual elements and scrap-based feedstocks on steel properties using machine learning, Bayesian optimisation, and computational metallurgy approaches. The research aims to support the development of sustainable structural steels through integrated computational and experimental alloy design. In parallel, my previous research has involved the development of machine learning frameworks, digital twins, and optimisation tools for aluminium alloy recycling and sustainable manufacturing applications. My work combines materials science, computational modelling, and interpretable AI to support circular economy approaches in advanced alloy systems.
