Physics-Inspired Spatial Temporal Graph Neural Networks for Predicting Industrial Chain Resilience
This work addresses the problem of analyzing resilience in complex industrial networks for economic sustainability, representing an incremental improvement in data-driven methods for this domain.
The paper tackles predicting industrial chain resilience by proposing a physics-inspired neural symbolic approach that integrates physical entity dynamics into spatiotemporal graph neural networks, achieving better and more accurate predictions with practical significance.
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.