We develop and apply mathematical and probabilistic models, machine learning algorithms, and optimization routines to make data-driven predictions, decisions, and policies in diverse contexts within chemical engineering.

• Bayesian optimization for the adaptive design of experiments to efficiently discover and synthesize molecules and materials
• Bayesian statistical inference to solve physical inverse problems with quantified uncertainty while incorporating prior information
• Computational design of arrays of nanoporous materials for gas sensing and machine learning to interpret their response patterns
• Stochastic schedules for mobile robots, equipped with chemical or radiation sensors, to efficiently and unpredictably patrol an environment for anomalies