Image features of a splashing drop on a solid surface extracted using a feedforward neural network

TL;DR

This study uses a feedforward neural network to identify key image features, notably the contour height of impacting drops, that distinguish splashing from nonsplashing drops, revealing nonintuitive insights into drop impact dynamics.

Contribution

The paper introduces a novel application of neural network visualization to identify the contour height as a key feature in drop splashing behavior, a previously unreported insight.

Findings

Neural network achieved over 96% classification accuracy.

Contour height of the main drop body is a crucial feature for splashing prediction.

Contour height remains important even when secondary ejected droplets are excluded.

Abstract

This article reports nonintuitive characteristic of a splashing drop on a solid surface discovered through extracting image features using a feedforward neural network (FNN). Ethanol of area-equivalent radius about 1.29 mm was dropped from impact heights ranging from 4 cm to 60 cm (splashing threshold 20 cm) and impacted on a hydrophilic surface. The images captured when half of the drop impacted the surface were labeled according to their outcome, splashing or nonsplashing, and were used to train an FNN. A classification accuracy higher than 96% was achieved. To extract the image features identified by the FNN for classification, the weight matrix of the trained FNN for identifying splashing drops was visualized. Remarkably, the visualization showed that the trained FNN identified the contour height of the main body of the impacting drop as an important characteristic differentiating between splashing and nonsplashing drops, which has not been reported in previous studies. This feature was found throughout the impact, even when one and three-quarters of the drop impacted the surface. To confirm the importance of this image feature, the FNN was retrained to classify using only the main body without checking for the presence of ejected secondary droplets. The accuracy was still higher than 82%, confirming that the contour height is an important feature distinguishing splashing from nonsplashing drops. Several aspects of drop impact are analyzed and discussed with the aim of identifying the possible mechanism underlying the difference in contour height between splashing and nonsplashing drops.