Unraveling the Key Drivers of Community Composition in the Agri-food Trade Network (Extended Abstract)

The analysis of the global food trade system holds tremendous significance due to substantial increases in food and agricultural production since the latter half of the 20th century. This growth has been fuelled by factors such as population expansion, economic development, technological advancements, and evolving dietary preferences. Simultaneously, we face challenges arising from the imperative to sustainably nourish a growing global population while safeguarding natural resources and ecosystems. Striking the balance between ensuring food supply and mitigating environmental harm has become a critical dilemma. The agri-food system serves as both an influencer of ecological shifts and a susceptible entity to climate destabilization, underscoring the need for sustainable production practices. Within this framework, network analysis emerges as a valuable instrument for comprehending the dynamics of global food trade. It aids in identifying pivotal stakeholders, trade patterns, vital relationships, and pertinent factors. This analysis regards the structure and evolution of the global food trade network. Remarkable insights have been unveiled in this domain. Research has probed into the attributes and development of the trade network concerning a wide spectrum of agricultural products as well as specific commodities. Investigations into the virtual water networks associated with agricultural products have been conducted, alongside the identification of community structures. Community detection proves invaluable in grasping the intricate framework of the global food trade. Indeed, several papers explored trade patterns, the formation of communities, the dynamics of the global food system, and potential related shocks (for instance, see [1], [6],[7],[11]). Unlike the existing literature, this paper presents a multi-step approach that combines a community detection method with a supervised learning methodology. The purpose is to identify communities within the agri-food trade network and to ascertain the primary drivers influencing the composition of these communities. To this end, we use a dataset sourced from the Food and Agriculture Organization of the United Nations (FAO). The analysis covers the period from 1986 to 2020 and involves creating temporal directed and weighted networks where countries are nodes and directed weighted edges represent trade volumes or monetary values between pairs of countries within a given year. This approach allows for an initial exploration of the evolving topology of the trade network. The analysis considers aggregate total flow across various commodities, providing an overview of global trade patterns and identifying average factors influencing agri-food network behaviour. As a subsequent step, for each year, we apply the InfoMap methodology [10] to identify communities of countries. Differing from conventional modularity maximization, this information-theoretic approach is rooted in flows and is particularly suited to trade contexts where flow patterns play a pivotal role. This partitioning is contingent on the flow established through network connections, providing a representation of the evolution of countries’ interconnections within the global food system. The identification of communities serves as an initial step towards comprehending intricate systems. In the concluding phase, our focus shifts to characterising these communities based on shared attributes among their constituents. Characterisation can be challenging due to potential heterogeneity among system elements. To address this complexity, we follow a multi-step process. Firstly, we associate attributes with nodes, encompassing economic, demographic, social, geographical, and meteorological aspects. Secondly, we employ a random forest methodology [3] to identify variables that explain community composition. Lastly, we merge the InfoMap-derived communities with the pertinent variables identified by the random forest analysis. This combined approach enables measurement of attribute over-expression (see [12]) within communities across different time periods. This methodology allows us to analyse community evolution over time in the global agri-food system and pinpoint primary drivers guiding this evolution.