AI-Driven Computational Modeling for Biophotonics
Inverse Modeling and Uncertainty-Aware AI for Biophotonic Systems
My research focuses on mathematically grounded AI methods for inverse modeling, multimodal integration, and uncertainty quantification in biophotonic data analysis.
Research Vision
AI-driven computational modeling of biophotonic measurement systems under uncertainty
Biophotonics generates complex, high-dimensional data governed by physical measurement principles. Extracting reliable biological insight requires models that integrate physics, statistics, and machine learning.
My research develops inverse modeling frameworks, multimodal data integration strategies, and uncertainty-aware AI methods to enhance the reliability and interpretability of optical biomedical technologies.
Research Directions
Core Research Areas in Inverse Modeling, Uncertainty-Aware AI, and Biophotonic Systems
Inverse & Physics-Informed Modeling
Development of AI-based and physics-informed approaches for solving inverse problems in optical imaging and spectroscopy, enabling robust signal reconstruction and quantitative estimation of biological properties.
Multimodal & Cross-Scale Data Integration
Integration of optical measurements with complementary data modalities, including molecular and omics data (e.g., genomics, RNA-seq), to enable cross-scale understanding of biological systems.
Uncertainty Quantification & Trustworthy AI
Design of statistical and probabilistic frameworks that quantify model uncertainty and improve reliability and support trustworthy decision-making in biomedical AI systems.
AI-Assisted Scientific Reasoning
Exploration of large language models and multi-agent systems to support structured scientific reasoning, automated analysis workflows, and hypothesis generation in biophotonic research, with emphasis on reproducible analysis workflows.
Access Publications
Access the full list of publications and research outputs in biophotonics, inverse modeling, and uncertainty-aware AI on the Publications Page.
Collaborate on Research
Collaboration is welcome in inverse modeling, multimodal biomedical data integration, uncertainty quantification, and AI-driven analysis of biophotonic systems.
When reaching out, please include the data type and collaboration goal.