Designing physics-informed modeling frameworks for materials, measurement systems, and advanced manufacturing.
Materials Science × Experimental Systems × Applied AI
We build computational representations of physical systems across:
The objective is reliable, physically grounded decision support.
Systems-oriented modeling engineer at the interface of physical experimentation and computational intelligence.
Transforming experimental response into structured state representations.
Enabling structure-property mapping and frequency-domain system modeling across material families.
Developing interpretable, uncertainty-aware models grounded in physical laws.
Prediction is treated as constrained state estimation rather than purely statistical regression.
Building deployable modeling layers that support R&D optimization, measurement enhancement, and laboratory-to-industry integration.
DMA-Based Structure-Property Modeling
A prototype system predicting storage modulus at 25 °C from dynamic mechanical response and microstructural descriptors.
Modeling Approach
Validation Strategy
Cross-validation across material families to test generalization.
This case validates the feasibility of physics-informed state modeling in real material systems.
Prediction across held-out material families.
Enabling structure-property prediction across material families
Cross-family generalization
Knowledge retention in R&D pipelines
Enhancing interpretation of frequency-domain response
State modeling from dynamic response
Physically consistent data encoding
Intelligent post-processing layers
Supporting process-structure-performance mapping
Experimental feedback integration
Parameter optimization under constraints
Uncertainty-aware decision support