Graph grammars and Physics Informed Neural Networks for simulating of pollution propagation on Spitzbergen

TL;DR

Two computational methods for performing simulations of pollution propagation described by advection-diffusion equations are presented and the Physics Informed Neural Networks method is used to calculate the dissipation of the pollution along the valley in which the city of Longyearbyen is located.

Abstract

In this paper, we present two computational methods for performing simulations of pollution propagation described by advection-diffusion equations. The first method employs graph grammars to describe the generation process of the computational mesh used in simulations with the meshless solver of the three-dimensional finite element method. The graph transformation rules express the three-dimensional Rivara longest-edge refinement algorithm. This solver is used for an exemplary application: performing three-dimensional simulations of pollution generation by the coal-burning power plant and its propagation in the city of Longyearbyen, the capital of Spitsbergen. The second computational code is based on the Physics Informed Neural Networks method. It is used to calculate the dissipation of the pollution along the valley in which the city of Longyearbyen is located. We discuss the instantiation and execution of the PINN method using Google Colab implementation. We discuss the benefits and limitations of the PINN implementation.

Figures (21)

• Figure 1: The Town of Longyearbyen at Spitsbergen, the location of the Diesel power plant, with the computational domain for PINN simulations of thermal inversion (black rhombus.
• Figure 2: Longest edge refinement for 3D tetrahedral elements.
• Figure 3: Graph representation of a 3D tetrahedron.
• Figure 4: Mapping the tetrahedral faces into the vertices of a graph.
• Figure 5: Left-hand side of the graph-grammar production P1.