Open AccessA Deep Learning Perspective on Dropwise Condensation (Adv. Sci. 22/2021)
Author(s) -
Suh Youngjoon,
Lee Jonggyu,
Simadiris Peter,
Yan Xiao,
Sett Soumyadip,
Li Longnan,
Rabbi Kazi Fazle,
Miljkovic Nenad,
Won Yoonjin
Publication year - 2021
Publication title -
advanced science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 5.388
H-Index - 100
ISSN - 2198-3844
DOI - 10.1002/advs.202170153
Subject(s) - condensation , mass transfer , perspective (graphical) , heat transfer , nanotechnology , computer science , statistical physics , artificial intelligence , materials science , physics , meteorology , thermodynamics
Dropwise Condensation The relationship between droplet statistics and heat and mass transfer has long remained unclear due to the challenge in quantifying the overwhelming number of rigorous physical descriptors embodied in dropwise condensation. By developing a vision‐based strategy utilizing artificial intelligence, Nenad Miljkovic, Yoonjin Won, and co‐workers show in article number 2101794 that there exists a quantifiable tradeoff between droplet size and density that can be harnessed to develop optimal surface guidelines for achieving stable dropwise condensation. The illustration shows an artificially intelligent droplet that represents the decades‐old statistical mysteries of dropwise condensation. The droplet is opening to reveal the data‐driven relationships between droplet statistics and heat and mass transfer.