Industry Space Evolution Study Based on Machine Learning Algorithm and Complex Network Methods

This article provides an in-depth understanding of the concept of industry space. It introduces a novel industrial correlation index, known as the industrial co-agglomeration index, which is based on the Wasserstein distance algorithm and optimization solution method. Our analytical framework for industrial space is built on complex network theory, and it highlights three key aspects: network space parameters, core nodes, and industrial space density indicators. To demonstrate the applicability of our framework, we use the Yangtze River Delta urban agglomeration as a case study. The study period covers the years from 1998 to 2013, and the findings indicate that the spatial structure of the industrial space underwent an “inverted U-shaped” transformation, becoming more centralized before 2008 and then becoming increasingly dispersed. The results of the study also show that the Yangtze River Delta region has experienced a transformation towards a more diverse, high-quality and high-tech industrial structure. The status of labor-intensive industries has declined while the status of technology-intensive and scale economy industries has increased. In conclusion, this article provides valuable insights into the structural form and evolution trend of industrial space, and the proposed analytical framework can serve as a useful tool for future research in this field.