Intelligent phase-change vision

Liquid vapor phase change involves complex nucleation, interfacial, and transport phenomena occurring at various scales. Such complexities have hindered the development of an in-depth understanding and prediction of phase change phenomena. This research aims to quantify phase change phenomena by developing a deep learning model for droplet segmentation at micro/nano scales. To elaborate further, we have analyzed its contributing factors to high heat transfer performance by utilizing intelligent vision. By leveraging the capabilities of intelligent vision, we can predict condensation phenomena and suggest a surface design rule for enhanced heat transfer performance.