Physics-Inspired Spatial Temporal Graph Neural Networks for Predicting Industrial Chain Resilience

TL;DR

This paper introduces a physics-inspired neural symbolic network that models the dynamics of industrial chains to improve resilience prediction, combining physical information with deep learning for better accuracy.

Contribution

It proposes a novel neural symbolic approach integrating physical dynamics into spatiotemporal graph neural networks for industrial resilience prediction.

Findings

Model achieves higher prediction accuracy.

Effectively captures industrial chain elasticity.

Demonstrates practical significance for industry development.

Abstract

Industrial chain plays an increasingly important role in the sustainable development of national economy. However, as a typical complex network, data-driven deep learning is still in its infancy in describing and analyzing the resilience of complex networks, and its core is the lack of a theoretical framework to describe the system dynamics. In this paper, we propose a physically informative neural symbolic approach to describe the evolutionary dynamics of complex networks for resilient prediction. The core idea is to learn the dynamics of the activity state of physical entities and integrate it into the multi-layer spatiotemporal co-evolution network, and use the physical information method to realize the joint learning of physical symbol dynamics and spatiotemporal co-evolution topology, so as to predict the industrial chain resilience. The experimental results show that the model can obtain better results and predict the elasticity of the industry chain more accurately and effectively, which has certain practical significance for the development of the industry.