Drs. Kursat Kara and Ryan Paul from the School of Mechanical and Aerospace Engineering at Oklahoma State University are developing a new artificial intelligence framework to improve aircraft safety during Navy ship operations.

The project, titled “Artificial Intelligence for Real-time Wake Inference in Ship Environments,” or AIRWISE, focuses on one of the most challenging environments in aviation: the turbulent airflow that surrounds ships moving through open water.

When manned or unmanned aircraft approach a ship for landing, they encounter complex and unpredictable wind patterns known as airwakes. These turbulent flows are created by the interaction of the relative wind at the ship and the vessel’s structure. The resulting disturbances, which are unsteady and hard to predict, can alter flight paths, increase pilot workload and reduce safety margins.

“Ship airwakes are highly complex and directly affect the safety of flight operations,” said Kara, associate professor for MAE. “This project gives us a path toward efficiently modeling those environments to enhance the fidelity of simulations and increase the quality of decisions made when studying this environment.”

Current naval training simulators rely on simplified wind models that cannot fully capture the dynamic nature of these environments. While high-fidelity computational simulations can represent the physics more accurately, they require enormous computing power and cannot operate fast enough for interactive use.

AIRWISE offers a new approach to overcome those limitations.

The research team is combining advanced computational fluid dynamics simulations with AI to create a modeling framework that delivers detailed shipboard wind environments in near-instantaneous time. By training AI models on validated, high-resolution simulation data, the system can reproduce the essential aerodynamic features of ship airwakes far more efficiently than traditional methods.

“The challenge is keeping the important physics while making the model fast enough to be useful,” Kara said. “Ship airwakes are highly unsteady, three-dimensional, and turbulent. Accurately resolving them normally requires very expensive simulations, so the breakthrough is learning how to capture that behavior at interactive speeds.”

Once trained, the system is expected to generate detailed 3D wind fields in less than 100 milliseconds using graphics processing units. The capability would enable new applications in pilot training, aircraft envelope evaluation and the development of autonomous flight systems.

AI is particularly well-suited to this problem because ship airwakes depend on many interacting variables, including wind conditions, ship speed, heading and vessel geometry. These relationships are highly nonlinear, making them difficult to represent using traditional simplified models.

“Instead of running an entirely new simulation each time conditions change, the AI can rapidly predict how the airflow will behave,” Kara said. “That gives us a way to move from expensive offline analysis toward rapid prediction across many operating conditions.”

Improved modeling of ship airwakes could enhance both training and operational decision-making. By allowing engineers and pilots to test aircraft performance under more realistic conditions, the technology may help identify hazardous environments before they are encountered in real flight.

“Shipboard landing is one of the most challenging operations in aviation,” said Paul, assistant professor for MAE. “Pilots and control systems must guide the aircraft to a very limited landing area with little margin for error while dealing with a highly unsteady flow environment around the ship. Better predictive tools can make a meaningful difference in safety.”

Beyond its operational significance, the project also provides advanced research opportunities for OSU graduate students, who gain hands-on experience in computational fluid dynamics, AI, high-performance computing and data-driven modeling – skills increasingly sought after in aerospace and defense careers, including positions at the Naval Air Warfare Center Aircraft Division.

This effort is further strengthened by an existing connection to NAWC-AD through Paul’s recently graduated Ph.D. student, who participated in the DoW SMART Scholarship program and is now joining the Flight Dynamics Branch, as well as an incoming SMART Scholar who will work with Kara and Paul, prior to an employment commitment at NAWC-AD.

Looking ahead, Kara and Paul envision AIRWISE's impact extending beyond a single tool or application. If successful, the framework could become a trusted approach for analyzing shipboard flight environments and improving Naval Aviation safety, while also demonstrating how interdisciplinary research at OSU can translate advanced theory into practical solutions for real‑world aerospace challenges.