Complex networks and deep learning for copper flow across countries

In this paper, by using a lifecycle perspective, four stages related to the extraction, refining and processing of copperwere identified. The different behaviors of countries in the import/export networks at the four stages synthetically reflect their position in the global network of copper production and consumption. The trade flows of four commodities related to the extraction, refining and processing of copper of 142 nations with population above 2millions based on the UN Comtrade website (https:// comtrade.un.org/ data/), in five years from 2017 to 2021, were considered. The observed trade flows in each year have been modelled as a directed multilayer network. Then the countries have been grouped according to their structural equivalence in the international copper flow by using a Multilayer Stochastic Block Model. To put further insight in the obtained community structure of the countries, a deep learning model based on adapting the node2vec to a multilayer setting has been used to embed the countries in an Euclidean plane. To identify groups of nations that play the same role across time, some distances between the parameters obtained in consecutive years were introduced. We observe that 97 countries out of 142 consistently occupy the same position in the copper supply chain throughout the five years, while the other 45 move through different roles in the copper supply chain.

Automated summary

In this paper, the four stages of copper extraction, refining, and processing were identified using a lifecycle perspective. The import/export behaviors of countries at these stages reflect their position in the global copper production and consumption network. Trade flows of four commodities related to copper from 142 countries were analyzed for five years, and a directed multilayer network model was applied. Countries were grouped based on their structural equivalence using a Multilayer Stochastic Block Model, and a deep learning model was used to embed the countries in an Euclidean plane. Out of 142 countries, 97 consistently maintained the same position in the copper supply chain over the five years, while the other 45 had different roles.