🔬 PhD Student | AI + Materials Enthusiast | Computational Researcher 📍 Department of Chemical and Biomolecular Engineering, Johns Hopkins University 📫 ycao73@jh.edu | 🌐 Personal Website | 🔗 LinkedIn
I'm building first-principles + machine learning frameworks to accelerate the discovery and design of stable, efficient 2D thermoelectric materials, currently focusing on Cr-doped Sb₂Te₃ systems. My goal is to bridge Density Functional Theory (DFT) with Data-Driven Modeling, enabling predictive simulations at scale.
Research sub domains:
- AI4Science (DFT + ML + MD integration) ; Multiscale Modeling and Simulation
- Active learning for ML force field development
- Reinforcement learning for synthesis optimization
- Physics-informed neural networks (PINNs)
- Generative AI for semiconductor materials design
- Transfer learning for small materials datasets
- 💡 Ask me about DFT, AIMD, Boltzmann transport, or building reproducible Python workflows
- 📨 Contact: ycao73@jh.edu 🔗 LinkedIn
- 🌐 Personal Website: yicao-elina
Machine learning · Density functional theory (DFT) · Molecular dynamics (MD) · Python · Quantum ESPRESSO · ASE · pymatgen · MLIP · scikit-learn · PyTorch
2D van der Waals heterostructures · Thermoelectrics · Defect engineering · AI-driven materials discovery