I specialize in reduced-order modeling and advanced data-driven methods, developing custom DMD frameworks for extracting dynamics and patterns from real-world scientific data. My work bridges mathematics with machine learning, deep learning, and data science for impactful solutions in both research and industry.
As an applied mathematician specializing in data-driven analysis, I bring expertise in model- and data-order reduction (Koopman/Dynamic Mode Decomposition, Proper Orthogonal Decomposition, etc.), time-series analysis, and statistical learning. I have developed a custom Dynamic Mode Decomposition (DMD) framework—an unsupervised learning approach—for extracting coherent structures and temporal dynamics from aerospace, oceanographic, and environmental datasets. I further extended this framework for real-time detection by integrating regression-based predictive models.
Ph.D. in Mathematics, 2024
Clarkson University, Potsdam, NY, USA
M.Sc. in Mathematics, 2020
Clarkson University, Potsdam, NY, USA
M.Sc. in Industrial Mathematics, 2013
University of Peradeniya, Sri Lanka
B.Sc. in Physical Science
University of Colombo, Sri Lanka
Core technical expertise for machine learning, data science, and applied mathematics.
Selected professional certifications, awards, and teaching training.
Previous associations that helped to gather experience
impactful journal articles, conference papers, and research outputs in applied mathematics, machine learning, and data science.
MY FANS DON’T FEEL LIKE I HOLD ANYTHING BACK FROM THEM