How does an AI classify images of splashing and non-splashing drops?

What is it about?

Splashing occurs when a drop falls and impacts a surface at a velocity high enough which causes the drop to break up and eject secondary droplets. By using a high-speed camera, we collected images of splashing and non-splashing drops. By using the collected images, we trained an AI to classify splashing and non-splashing drops. After the AI learnt to classify images of splashing and non-splashing drops accurately, we checked how the AI perform the classification. As expected, the main characteristics that the AI checks are the breaking up of the drop's main body and the ejection of the secondary droplets. Remarkably, the AI also checks the contour of the drop’s main body. In other words, if the contour is high, the AI will classify the drop as a splashing drop. The difference in the contour height between splashing and non-splashing drops has not been reported prior to our study.

Featured Image

Photo by ANIRUDH on Unsplash

Photo by ANIRUDH on Unsplash

Why is it important?

Usually, an AI that can accurately classify images is quite complicated and it is almost impossible to understand how it works. However, in our study, we managed to train a simple AI to accurately classify images of splashing and non-splashing drops and to understand the classification process of the AI. As a result, the AI helped us to discover a difference between splashing and non-splashing drops that have not been reported before, that is the contour of a splashing drop is higher than that of a non-splashing drop. Therefore, by understanding how an AI works, we can use it to observe physical phenomena and find new perspectives from it.

Perspectives