Prediction of the morphological evolution of a splashing drop using an encoder-decoder

Abstract

The impact of a drop on a solid surface is an important phenomenon that has various implications and applications. However, the multiphase nature of this phenomenon causes complications in the prediction of its morphological evolution, especially when the drop splashes. While most machine-learning-based drop-impact studies have centred around physical parameters, this study used a computer-vision strategy by training an encoder-decoder to predict the drop morphologies using image data. Herein, we show that this trained encoder-decoder is able to successfully generate videos that show the morphologies of splashing and non-splashing drops. Remarkably, in each frame of these generated videos, the spreading diameter of the drop was found to be in good agreement with that of the actual videos. Moreover, there was also a high accuracy in splashing/non-splashing prediction. These findings demonstrate the ability of the trained encoder-decoder to generate videos that can accurately represent the drop morphologies. This approach provides a faster and cheaper alternative to experimental and numerical studies.

arXiv comment25 pages, 14 figures

References in corpus (15)

• Auto-Encoding Variational Bayes
• TensorFlow: A system for large-scale machine learning
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Machine Learning for Fluid Mechanics
• Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation
• Drop Impact Printing
• Drop impact on a solid surface: short time self-similarity
• Dynamics of drop impact on solid surfaces: evolution of impact force and self-similar spreading
• Unsupervised machine learning of topological phase transitions from experimental data
• The role of drop shape in impact and splash
• Stress distribution and surface shock wave of drop impact
• Droplet impact of blood and blood simulants on a solid surface: Effect of the deformability of red blood cells and the elasticity of plasma
• Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders
• Image features of a splashing drop on a solid surface extracted using a feedforward neural network
• Machine Learning Inference of Molecular Dipole Moment in Liquid Water