Machine learning for flow field measurements: a perspective

Abstract Advancements in machine-learning (ML) techniques are driving a paradigm shift image processing. Flow diagnostics with optical is not an exception. Considering the existing and foreseeable disruptive developments flow field measurement techniques, we elaborate this perspective, particularly focused to of particle velocimetry. The forces for advancements ML methods measurements recent years reviewed terms preprocessing, data treatment conditioning. Finally, possible routes further highlighted.