My research focuses on the intersection of data analysis, advanced machine learning, and cloud-based software engineering to build highly resilient, automated decision-support systems. As a Principal Investigator and Project Manager, I lead the development of next-generation predictive frameworks that translate complex atmospheric data into actionable insights for critical infrastructure, surface transportation, and renewable energy sectors.

A primary pillar of my work is the modernization and optimization of real-time road weather forecast systems. My current research projects leverage state-of-the-art deep learning architectures—including convolutional neural networks (CNNs), vision transformers, and gradient-boosted systems—to automate hazard detection, downscale precipitation variables, and improve roadway grip and friction sensing during severe winter weather events. By bridging the gap between raw physical observations (such as roadside imagery and NWP guidance) and automated edge/cloud-computing platforms, this work directly enhances public safety and operational cost-efficiency for state Departments of Transportation and national safety coalitions.

Beyond surface transportation, my research interests extend into renewable energy forecasting and the scaling of automated meteorological quality-control workflows. I am dedicated to advancing data integrity by deploying robust machine learning models that screen and cross-validate highly intermittent environmental data. Through close collaboration with project sponsors, federal stakeholders, and Technical Advisory Committees (TACs), my goal is to deliver long-lasting, operationally sound software systems that improve societal resilience to hazardous weather.