cv Download PDF
Research experience, education, selected outputs and technical expertise.
Basics
| Name | Yu Zhang |
| Label | PhD Researcher and Research Fellow |
| yu.zhang@surrey.ac.uk | |
| Url | https://yurbro.github.io |
| Summary | PhD researcher in Chemical and Process Engineering at the University of Surrey, working at the interface of AI, digital twins and data-driven engineering. Research spans data-efficient formulation and drug-delivery design, uncertainty-aware modelling, scientific evidence extraction and reproducible machine learning with real-world clinical data. Also contributes to battery intelligence research through data processing, computational algorithms and research software. |
Work
- 2026.09 - Present
Research Fellow — Advanced Battery Intelligence and Technology Development
Advanced Technology Institute (ATI), Guildford, UK
University of Surrey
Work with Dr Kai Yang on an EPSRC IAA project in battery intelligence, contributing data processing, algorithm development and research software workflows.
- Process and organise experimental datasets for computational analysis.
- Contribute to algorithm development and data-driven research workflows.
- Develop research software to support analysis and workflow automation.
- 2026.06 - Present
Research Assistant — Clinical Machine Learning
Guildford, UK
University of Surrey
Work with Dr Xilu Wang (University of Surrey) and Dr Mingkun Tan (University of Münster, Germany) on reproducible machine-learning workflows for real-world clinical data in assisted reproduction and IVF.
- Define clinically meaningful outcomes and construct analysis-ready features from heterogeneous, longitudinal treatment records.
- Address incomplete records and outcome availability when preparing data for patient-level outcome modelling.
- Design patient-aware and time-aware validation to reduce information leakage and assess model generalisation.
- Maintain auditable workflows with attention to confidentiality, data provenance and reproducibility.
- 2024 - Present
Teaching Assistant
Guildford, UK
University of Surrey
Teaching support across engineering systems, science principles and advanced pharmaceutical formulations.
- ENG2128 Engineering Systems and Management (2024–25) · Lecturer: Dr Lei Xing
- ENG1080 Science Principles for Engineers (2025–26) · Lecturer: Prof. Madeleine Bussemaker
- CHEM042 Advanced Pharmaceutical Formulations (2025–26 and 2026–27) — Teaching support in formulation science, pharmaceutical product design and advanced delivery systems. · Lecturer: Prof. Tao Chen
- 2023.09 - Present
PhD Researcher — Machine Learning and Digital-Twin Modelling
Guildford, UK
University of Surrey
Data-efficient modelling and experimental decision-making for pharmaceutical formulation and drug delivery.
- Develop Gaussian-process surrogate models, Bayesian optimisation and active-learning workflows for adaptive and multi-objective experimental design.
- Model drug-release and permeation behaviour using domain-knowledge-constrained symbolic regression and temporal prediction from partial experimental trajectories.
- Develop reproducible LLM-enabled workflows for scientific evidence extraction and dataset construction.
- 2021.05 - 2021.06
Technical Lead — Big Data AI Analysis System for Shale Gas Trading Market
China
External client project
Python software for energy-market data collection, analysis and visualisation.
- Built automated collection and analysis of real-time and historical market data.
- Delivered executable software to an external client.
- 2020.12 - 2022.07
Research Assistant — Data-Driven Reservoir Simulation Analysis
Beijing, China
China University of Petroleum - Beijing
Data-driven analysis of numerical reservoir-simulation outputs.
- Used PCA/MPCA, Hotelling's T², SPE and self-organising maps to extract spatial and temporal features.
- Classified dominant flow regimes from simulation outputs.
- 2020.12 - 2021.10
Research Assistant — Intelligent Monitoring of Electric Submersible Pump Systems
Beijing, China
National Key R&D Programme of China project
Data-driven condition monitoring, fault classification and early warning from multivariate operational and process data.
- Applied PCA/SFA, regression, clustering and SVM methods to operational sensor and process data.
- Implemented Python-based analytical software for condition monitoring and fault diagnosis.
Education
-
2026.06 - 2026.08 Kraków, Poland
Visiting PhD Researcher
Jagiellonian University Medical College
Faculty of Pharmacy, Department of Social Pharmacy · Non-degree research placement under COST Action CA21108 (NETSKINMODELS)
Host: Prof. Barbara Wiśniowska · Collaborator: Dr Laura Krumpholz
- Research visit: 15 June – 14 August 2026; home PhD institution: University of Surrey.
- SkinPhysio-Extract: LLM-assisted extraction, provenance auditing and verification of quantitative skin physiology evidence.
-
2023.09 - Present Guildford, UK
PhD
University of Surrey
Chemical and Process Engineering
Supervisors: Prof. Tao Chen , Assoc. Prof. Dimitrios Tsaoulidis
- Expected thesis submission: late 2026 / early 2027.
- Digital twin and AI methods for topical formulation design
-
2020.09 - 2023.07 Beijing, China
MEng
China University of Petroleum - Beijing
Control Science and Engineering, College of Artificial Intelligence
Supervisor: Prof. Xiaoyong Gao
Research focus: Data-driven fault monitoring and diagnosis of electric submersible pumps under nonlinear dynamics and limited fault samples.
- Developed LPP-enhanced dynamic kernel PCA for nonlinear process monitoring and fault identification.
- Developed improved conditional GAN-based data augmentation for fault diagnosis using extremely limited samples.
- Investigated optimisation-based semi-supervised learning for multi-class fault diagnosis using unlabeled industrial data.
Related publications: The Canadian Journal of Chemical Engineering (2023) · Journal of the Franklin Institute (2024)
-
2015.09 - 2019.07 Sichuan, China
Publications
-
2026 A modelling-based comparison of IVRT and synthetic-membrane permeation for early formulation screening
RSC Pharmaceutics
Quantifies alignment between IVRT and synthetic-membrane permeation assays.
-
2026 Confidence-Bound Early Stopping of Experiments with Sequential Calibration
Chemical Engineering Research and Design, 230, 756-766
Early stopping with calibrated control of the false-stop rate.
-
2026 Autonomous AI-Driven Design for Skin Product Formulations
Advanced Intelligent Discovery, e70100
A roadmap for assay-aware, closed-loop and increasingly autonomous skin formulation development.
-
2026 Active learning-based adaptive optimisation for developing dermal drug formulations
Chemical Engineering Research and Design, 232
Adaptive batch allocation between expected-improvement and information-seeking formulation candidates.
-
2026 Domain Knowledge Constrained Symbolic Regression for Optimising Dermal Drug Formulations
Pharmaceutical Research
Domain-knowledge-constrained symbolic regression for interpretable modelling and optimisation of dermal drug formulations.
-
2026 Optimisation of Topical and Transdermal Pharmaceutical Formulations: Methods, Challenges and Opportunities
SmartSys, 2(4), e70047
Yongrui Xiao, Yu Zhang, Chunlin Chen, Dimitrios Tsaoulidis, Kai Yang and Tao Chen. Published online on 6 November 2026. Review of statistical design, machine learning, Bayesian optimisation and emerging autonomous laboratories for topical and transdermal formulations.
-
2026 SkinMiner: LLM-powered data mining to accelerate formulation design for skin products
SSRN preprint (under review at International Journal of Pharmaceutics)
Yu Zhang, Xilu Wang, Dimitrios Tsaoulidis and Tao Chen. LLM-powered extraction, verification and structuring of dermal formulation evidence. Preprint; peer review ongoing.
-
2026 A Spectral-Continuity-Guided Bayesian Learning Framework for Infrared Spectroscopy-Based Soft Sensor Modeling
Measurement
Pengcheng Wu, Tao Chen, Yu Zhang, Xiaobo Zou and Haoran Li. Collaborative manuscript on spectral-continuity-guided Bayesian learning for infrared spectroscopy-based soft sensor modelling. Published online in Measurement in 2026.
-
2025 An early decision-making algorithm for accelerating topical drug formulation optimisation
Computers & Chemical Engineering, 201, 109224
Probabilistic early decisions from partial IVPT trajectories.
-
2024 Data augmentation using improved conditional GAN under extremely limited fault samples and its application in fault diagnosis of electric submersible pump
Journal of the Franklin Institute, 361(4), 106629
Virtual sample generation for fault diagnosis under extreme data scarcity.
-
2023 Improved dynamic kernel PCA based on local preserving projections and its application for electric submersible pump fault diagnosis
The Canadian Journal of Chemical Engineering, 101(8), 4539-4554
Local-structure-preserving nonlinear dynamic process monitoring.
-
2022 Green scheduling optimization of shuttle tanker route considering carbon emissions
Chemical Industry and Engineering, 39(2), 23-31
Multi-objective route scheduling with carbon-emission considerations.
Presentations
- 24 Aug 2026
LLM-powered multimodal agentic data mining for dermal formulation science
Zhang, Y.; Tsaoulidis, D.; Chen, T.
28th International Congress of Chemical and Process Engineering (CHISA 2026) · Prague, Czech Republic
Oral presentation.
Projects
- 2026.09 - Present
Battery Intelligence
Data processing, computational algorithms and research software for an EPSRC IAA battery intelligence project at Surrey's Advanced Technology Institute, working with Dr Kai Yang.
- Experimental data processing
- Algorithm development
- Research software
- 2024 - 2026
Adaptive Batch Optimisation
Active learning for formulation optimisation under a limited per-batch experimental budget.
- Gaussian process regression
- Expected improvement
- Hypervolume contribution
- 2023 - 2025
Early Decision-Making Algorithm
Forecasting final permeation outcomes from partial IVPT trajectories.
- Uncertainty quantification
- Probability of exceedance
- Experimental resource saving
- 2025 - Present
Domain-Constrained Symbolic Regression
Interpretable dynamic modelling and optimisation of dermal drug release.
- Domain constraints
- Dynamic modelling
- Interpretable optimisation
- 2026 - Present
SkinMiner
LLM-powered extraction and verification of dermal formulation evidence. SSRN preprint available; under review at International Journal of Pharmaceutics.
- Scientific LLMs
- Evidence provenance
- Structured datasets
- 2026.06 - Present
Clinical Machine Learning for Assisted Reproduction
Ongoing research on reproducible outcome-modelling workflows for real-world IVF data.
- Outcome definition and feature construction
- Patient-aware and time-aware validation
- Data provenance and reproducibility
Awards & Grants
- 2026.06
Short-Term Scientific Mission and Mobility Funding
COST STSM, UK Turing Scheme and FEPS
€2.8K COST STSM, £1K UK Turing Scheme and £1K FEPS funding for a June–August 2026 research placement at Jagiellonian University, Poland. Hosted by Prof. Barbara Wiśniowska and Dr Laura Krumpholz
- 2025.01
UK Turing Scheme Research Placement
UK Turing Scheme
£1K mobility funding for a January-March 2025 research placement at West China Hospital, Sichuan University.
- 2023.09
China Scholarship Council - University of Surrey Award
China Scholarship Council and University of Surrey
Full-time PhD scholarship, September 2023-September 2027. Grant No. 202306440060.
- 2022
Outstanding Graduate Student (优秀研究生)
Beijing Automation Society (北京自动化学会)
Awarded the 2022 Outstanding Graduate Student distinction.
Skills
| Machine Learning and Modelling | |
| Gaussian processes | |
| Random forests | |
| SVR / SVM | |
| Neural networks | |
| PCA / MPCA | |
| Slow feature analysis | |
| Self-organising maps |
| Optimisation and Decision-Making | |
| Bayesian optimisation | |
| Active learning | |
| Uncertainty quantification | |
| Temporal prediction | |
| NSGA-II | |
| Symbolic regression |
| Clinical Data and Validation | |
| Data-quality auditing | |
| Outcome definition | |
| Feature construction | |
| Longitudinal data | |
| Patient-aware and time-aware validation |
| Formulation and Experiments | |
| Dermal drug delivery | |
| IVRT | |
| IVPT | |
| Formulation design | |
| Digital twins | |
| Automated experimentation |
| LLMs and Scientific Evidence | |
| Multimodal and agentic data mining | |
| Evidence extraction | |
| Scientific workflow automation | |
| Evidence provenance |
| Scientific Computing | |
| Python | |
| PyTorch | |
| TensorFlow | |
| MATLAB | |
| pandas | |
| scikit-learn | |
| SciPy | |
| Matplotlib | |
| Git / GitHub | |
| Reproducible research |
Languages
| Chinese | |
| Native speaker |
| English | |
| Professional working proficiency |
Interests
| Research interests | |
| AI for engineering and science | |
| Digital twins | |
| Formulation and drug delivery | |
| Clinical machine learning | |
| Scientific data mining | |
| Process monitoring and fault diagnosis |
Certificates
| Microsoft Certified: Azure AI Fundamentals | ||
| Microsoft | 2021 |
Memberships
- Institution of Chemical Engineers (IChemE) · Affiliate member
- Chinese Association of Automation (CAC) · Member
- Chemical Industry and Engineering Society of China (CIESC) · Member
Academic Service
Journal peer review
- Journal of Automation and Intelligence — 6 completed reviews recognised for October 2025 – September 2026.
- Franklin Open — 7 completed reviews recognised for October 2025 – April 2026.
Conference reviewing
- China Automation Congress (CAC) — Reviewer recognition in 2023, 2024 and 2025.