Yu Zhang

I develop AI-enabled methods for faster, more reliable skin product formulation design. My PhD research combines probabilistic machine learning, active learning, optimisation, interpretable modelling and automated experimentation with in vitro release and permeation testing.

The long-term goal is an assay-aware digital twin that can learn from limited experimental data, quantify uncertainty, select informative formulations, stop unpromising experiments early and turn data into interpretable scientific knowledge.

Research programme

Current research directions

• Adaptive formulation optimisation - allocating small experimental batches between performance-seeking and information-seeking candidates.
• Early experimental decision-making - forecasting final outcomes from partial IVPT/IVRT trajectories and controlling false stops.
• Interpretable dynamic modelling - embedding physical and mathematical constraints into symbolic regression for drug-release kinetics.
• Scientific LLM systems - extracting traceable formulation and permeation evidence from literature and building reusable research datasets.

Background

I am a PhD researcher in Chemical and Process Engineering at the University of Surrey, supervised by Professor Tao Chen and Dr Dimitrios Tsaoulidis. Before joining Surrey, I completed an MEng in Control Science and Engineering at China University of Petroleum - Beijing and a BEng in Automation at Panzhihua University.

My earlier work addressed industrial process monitoring, few-shot learning, fault diagnosis and operational optimisation. That background now informs my approach to data-scarce formulation science: models should be useful under real experimental constraints, not only accurate on a tidy benchmark.