Bridging AI and Materials Science
for Next-Generation 2D Electronics

I am a doctoral candidate at Johns Hopkins University specializing in computational materials science with expertise in DFT, molecular dynamics, and machine learning. My research focuses on understanding and designing novel 2D thermoelectric materials for sustainable energy harvesting, combining first-principles calculations with data-driven approaches to advance materials discovery and optimization.

Recent Work

Self-Healing Perovskites

Self-Healing Perovskites

Uncovered low-energy pathways for defect migration in CsPbBr₃, contributing to enhanced solar cell stability.

View Publication Linkedin Post
ML-Enhanced Thermoelectrics

ML-Enhanced Thermoelectrics

Developing machine-learned interatomic potentials for Cr-doped Sb₂Te₃ thermoelectrics.

View Project

Van der Waals Engineering

Exploring dopant-mediated gap modulation for high-temperature thermoelectric applications.

Knowledge Extraction & Explanable Model

Apply machine learning techniques to develop trustworthy and human-readable design rules for AI-aided materials discovery.

2025 Yi Cao. This work is licensed under CC BY-NC-SA 4.0.

Work Experience

Viva Biotech

Computational Drug Design Intern

Viva Biotech | Shanghai, China | Jun - Jul 2024

Conducted Computer-Aided Drug Design (CADD) research using co-solvent MD simulations, optimizing drug discovery through protein-ligand interaction analysis.

Learn More
iGEM Competition

Scientific Advisor

Fudan iGEM Team | Shanghai, China | Dec 2022 - Nov 2023

Guided experimental design and scientific documentation. Led brainstorming sessions resulting in Gold Medal and Best Environmental Project.

View Project
Boehringer Ingelheim

Quality Culture Intern

Boehringer Ingelheim | Shanghai, China | Dec 2022 - Feb 2023

Led a team in developing a white paper on quality culture through research and interviews, resulting in improved company-wide quality guidelines.

Company Website
Teaching

Science Communication & Teaching

Conference Talks, Posters, and More

Selected for PHM Society Doctoral Symposium 2025, presented at MRS Fall Meeting 2024, and completed JHU Teaching Institute certification.

View All

Vision for AI-Accelerated Materials Discovery

Hover or click to expand; click again to collapse.

What is your long-term goal?
Build a closed-loop system linking AI + simulations + experiments.

My long-term goal is to bridge the gap between computational simulations and experimental materials science, enabling a closed-loop design process. With prior wet-lab training in biomaterials, I’ve seen how tedious trial-and-error methods are.

My vision is to build systems that minimize experiments by learning from past data and simulations—so materials discovery becomes faster, deeper, and smarter.

▲ Collapse
What is your mission as a simulation researcher?
Use ML to extract maximum insight from minimal experiments.

I aim to merge simulation data and historical experiments using advanced ML techniques like active learning and transfer learning to uncover hidden patterns. This allows us to optimize material design with fewer experiments, while gaining more knowledge—accelerating understanding of atomic-level interactions and enabling better materials in fewer cycles.

▲ Collapse
How do you understand Machine Learning?
ML is not a black box—it’s a transparent, evolving partner in science.

To me, ML is not magic—it’s a dynamic tool that gains strength when guided by domain knowledge. With strong grounding in materials science, I see ML as a transparent, explainable collaborator. CPUs and GPUs are extensions of human thought. AI and humans co-evolve, inspiring each other.

As Marie Curie once said, "Nothing in life is to be feared, it is only to be understood." Through interdisciplinary research in ML and materials, I hope to help people understand—and therefore face—the world with greater confidence and curiosity.

▲ Collapse

Get In Touch

I'm always interested in discussing computational materials science, machine learning applications in materials discovery, and potential collaborations. Feel free to reach out if you'd like to connect!

  • Address

    3400 N. Charles Street
    Baltimore, MD 21218
    United States

  • Phone

    +1 (443) 278-3766

  • Email

    ycao73@jh.edu