Postdoctoral Research Associate at Baylor University
Research
My research develops interpretable and neurosymbolic AI for Advanced Air Mobility (AAM) demand modeling, with a focus on translating forecasts into operational decisions.
At Baylor, I contribute to a NASA University Leadership Initiative (ULI) project by connecting AAM demand forecasts with aircraft assignment and scheduling, distributed optimization, and simulation to evaluate safe, energy-efficient operations and infrastructure needs.
How can emerging air-mobility demand be estimated before mature operating data exists?
I connect travel behavior, infrastructure, energy needs, and service design to support urban and regional AAM planning.
Example paper: Demand forecasting and energy-aware portal siting for Regional Air Mobility.
How can learned models incorporate explicit knowledge and remain understandable?
I combine neural learning with symbolic rules and constraints for more interpretable, robust, and controllable AI.
Example paper: The IJCAI 2025 survey on neurosymbolic AI in Advanced Air Mobility.
How can AI improve planning decisions under uncertainty and operational constraints?
I build transparent forecasting and optimization pipelines for scenario analysis, scheduling, and resilient mobility planning.
Example paper: A neural-network-accelerated genetic algorithm for pre-disaster mobility planning.
Research workflow
A connected workflow turns demand estimates into plans, then tests those plans against operational scenarios.
Estimate where and when travelers may use Advanced Air Mobility.
Behavioral, spatial, and data-driven models
Connect forecasts to portal siting, aircraft assignment and scheduling, and distributed optimization.
Infrastructure, scheduling, and optimization
Compare service and energy outcomes under alternative operating plans.
Service, energy, and scenario analysis
Collaboration
I welcome collaborations involving advanced mobility modeling, interpretable AI, and optimization for resilient transportation systems.
