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

TL;DR

This paper introduces two computational approaches, graph grammars and Physics Informed Neural Networks, for simulating pollution propagation in Longyearbyen, demonstrating their application and discussing their benefits and limitations.

Contribution

It presents a novel combination of graph grammar-based mesh generation and PINNs for pollution simulation in a specific geographic setting.

Findings

Graph grammar method effectively models mesh refinement for pollution simulation.

PINNs successfully compute pollution dissipation along the valley.

Both methods have distinct advantages and limitations in this context.

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.