Osman Mamun

Osman Mamun is a computational researcher at Cornell University's College of Engineering, focusing on integrating machine learning with materials science and catalysis. His work bridges data-driven methods and traditional computational chemistry to optimize materials discovery.

Research Interests include:

• BAYESIAN OPTIMIZATION for materials design
• DEEP GRAPH KERNEL LEARNING for atomic-scale uncertainty quantification
• ALLOY PROPERTY PREDICTION using machine learning
• CATLABRATION AND DATABASE DEVELOPMENT for catalytic systems

Publication Trends (2015-2025) show expertise in computational catalysis, predictive modeling of high-temperature alloys, and development of open-access databases like CatHub and XMAT. His methods emphasize uncertainty quantification, outlier detection, and multi-objective optimization in materials design.