Generation of Granular Deposition Interfaces using conditional Generative Adversarial Network (cGAN)

TL;DR

This paper presents a cGAN-based model to generate 1D granular deposition interfaces, replacing computationally intensive simulations with AI-generated data that accurately captures statistical properties across different fluids.

Contribution

The study introduces a novel cGAN architecture with U-Net and ResNet components for modeling granular interface growth, trained on simulation data for various fluids, enabling efficient interface generation.

Findings

The cGAN accurately reproduces interface statistical features.

The model generalizes across different fluids with consistent hyperparameters.

Generated interfaces match dynamic simulation results closely.

Abstract

This work aims at generating 1D interface profiles of granular deposition by a conditional generative adversarial network (cGAN). Our cGAN model employs a U-Net generator and a ResNet discriminator that, in competition with each other, produce granular interfaces. The network is trained on dynamic simulation data from the LAMMPS granular package. Different fluids (water, acetone, and hexane) were used for the medium of the deposition cell to check the model performance in different growing conditions. The same model with the same hyperparameters was trained on data from different media separately. The ML-generated interfaces are compared with those of dynamic simulations, and a large number of interfaces are then produced to obtain more stable statistical properties of granular deposition. This way, the computationally extensive molecular dynamics simulation is substituted by the AI model. The statistical trend of interface growth is diagrammed, and the generated interfaces are also analyzed in terms of statistical features. Keywords: Conditional Generative Adversarial Networks, ResNet, U-Net, Granular Deposition, Interface Growth.