Modern materials discovery and manufacturing face a critical disconnect between digital design and physical execution, leaving production vulnerable to material volatility and supply chain shocks. My research bridges this gap by establishing a cognitive infrastructure that grounds machine intelligence in fundamental physical laws. By integrating multi-scale, physics-informed machine learning with multimodal sensor fusion, I develop high-fidelity digital twins capable of autonomous, real-time control. This framework transforms reactive operations into a self-optimizing ecosystem, securing high-tech supply chains from raw materials to final logistics.

Research topics

1. Upstream Supply Resiliency & Critical Materials Extraction.

Extraction and processing of critical metals, including niobium and rare earth elements (REEs).

2. Multi-Scale, Multi-Physics Modeling & Digital Twin Anchoring.

Bridging electronic, atomic, mesoscale, and device-level phenomena utilizing physics-informed machine learning

3. Precision Nano-Fabrication & Scalable Quantum materials and Quantum Devices

Scalable design and manufacturing of advanced semiconductor and quantum optical devices

4. Closed-Loop Metrology & Non-Destructive Evaluation (NDE)

In-situ non-destructive detection, characterization, and real-time process monitoring.