← Muhammad Ayan

LSTM Prediction of Air–Sea Interaction

Visiting Researcher (Summer Intern), UT Dallas Flow Turbulence and Dynamics Lab
Advisor: Dr. Kianoosh Yousefi · June – August 2026

Overview

Wind over ocean waves produces turbulent airflow that is difficult to measure and expensive to simulate. Over the summer I trained sequence models to predict air–sea interaction dynamics from turbulent flow time-series data.

Method

Results

Prediction accuracy compared with the baseline MSE models.
MetricBaselineWith DMDChange
Median R²0.660.81+22.7%
Mean R²0.440.64+45.5%
Predicted and measured flow.

After the summer the lab retained me part-time to continue this work; see CNN reconstruction of airflow over waves.

← I-Beam Structural AnalysisCNN Reconstruction of Airflow over Waves →