Introducing a Generative Adversarial Network Model for Lagrangian Trajectory Simulation
This work addresses particle trajectory simulation in a specific fluid dynamics domain, representing an incremental application of existing GAN methods to new data.
The authors tackled the problem of simulating 3D Lagrangian particle motion in a buoyancy-opposed flame using a GAN model, achieving results where the discriminator could not distinguish simulated trajectories from ground truth, with performance benchmarked against statistical analysis for accuracy and generalization.
We introduce a generative adversarial network (GAN) model to simulate the 3-dimensional Lagrangian motion of particles trapped in the recirculation zone of a buoyancy-opposed flame. The GAN model comprises a stochastic recurrent neural network, serving as a generator, and a convoluted neural network, serving as a discriminator. Adversarial training was performed to the point where the best-trained discriminator failed to distinguish the ground truth from the trajectory produced by the best-trained generator. The model performance was then benchmarked against a statistical analysis performed on both the simulated trajectories and the ground truth, with regard to the accuracy and generalization criteria.