Our work combines carefully controlled laboratory experiments with artificial intelligence (AI) tools to better understand these processes. Using a custom wind–wave tunnel, we created detailed measurements of airflow over surface waves. We then trained an AI model to recognize patterns in the turbulent flow and to link them with wave properties that can be measured more easily. This approach allows us to reconstruct the small-scale turbulence that drives air–sea exchanges. By capturing this missing piece, our work opens a pathway to more accurate forecasts of weather and climate, while also helping us understand how the ocean and atmosphere interact at their boundary.