Applied Mathematics · Symbolic Regression · Scientific Computing
University of Nottingham, UK
Incoming MPhil student in Data Intensive Science at the University of Cambridge

My research lies at the intersection of applied mathematics, scientific computing, and interpretable machine learning, with a particular focus on symbolic regression.

I am interested in discovering compact, analytic, and physically meaningful mathematical representations of complex systems from data, and in developing modeling frameworks that balance predictive accuracy, interpretability, and physical consistency.

Current application areas include:

• Energy systems and refrigeration performance modeling
• Coarse-grained interaction potentials in computational physics
• Data-driven scientific regression under structural and physical constraints

Interpretable Chiller Modeling
Symbolic regression and multi-parameter optimization for modeling chiller COP, with an emphasis on interpretability and generalization.
https://github.com/zeweyer/Interpretable-Chiller-Modeling

CGPM — Coarse-Grained Potential Modeling
Learning analytic coarse-grained interaction potentials from simulation data via symbolic regression.
https://github.com/zeweyer/cgpm

Drop Tower Braking Dynamics
Physics-based modeling and numerical simulation of braking dynamics in drop-tower systems.
https://github.com/zeweyer/drop-tower-braking-dynamics

• Symbolic regression and interpretable modeling
• Optimization and model selection
• Time series analysis
• Numerical simulation and scientific computing

Python · MATLAB · R · Linux
NumPy · SciPy · scikit-learn · PySR · matplotlib

GitHub: https://github.com/zeweyer
Google Scholar: https://scholar.google.co.uk/citations?user=aMrqOe0AAAAJ

This GitHub profile serves as a research-oriented portfolio documenting ongoing work in interpretable and data-driven scientific modeling.