The issue of carbon emissions in the plastic supply chain has attracted global attention, and relevant countries have formulated and introduced economic policies and measures to reduce plastic carbon emissions. To solve this dilemma, some scholars have proposed the path of empowering the plastic supply chain through digital technology to achieve carbon reduction. However, there are few research results on the mechanism of digital technology empowering the carbon reduction of the plastic supply chain. This paper analyzes the results of carbon reduction research in digitally enabled supply chains through a bibliometric review method. Using the keywords of digitally enabled, plastic supply chain, and carbon footprint, the relevant literature of Web of Science was collected, and the research trends, keyword co-occurrence phenomena, and research hotspots were analyzed by VOSviewer. The findings of this study form six clusters of carbon reduction and digitalization research results in the plastic supply chain, from which we derive six future research directions in the field, such as “carbon emission reduction in the consumer side of the plastics supply chain”, “The development of digital industrialization of carbon emission reduction” etc. The contribution of this article lies in constructing a theoretical framework model for digital technology empowering carbon reduction in the plastic supply chain, which provides a theoretical basis for governments and plastic industry enterprises to promote carbon neutrality.
The global food trade network is a complex system whose resilience is paramount to food security. Forecasting its evolution is critical for anticipating disruptions, yet accurate link prediction remains challenging due to the multi-dimensional nature of trade relationships. We present T-food-ELA, a time-based ensemble learning algorithm that integrates a suite of network similarity metrics within an XGBoost framework to predict link formation. Leveraging UN Comtrade data (2013–2023) for ten major food categories across 50 core nations, we demonstrate that our model significantly outperforms single-metric benchmarks, achieving an out-of-sample AUC of 0.84. Beyond predictive performance, we use model interpretation tools to uncover the fundamental principles governing the network's topology. We identify and characterize three structural effects: a preferential attachment effect reinforcing hub dominance; a saturation effect where an excess of common neighbors inhibits direct trade; and an intermediary effect whereby efficient indirect connections suppress direct links. Finally, we derive a resilience-based hierarchy of trade links, revealing distinct "core-core," "core-periphery," and "marginal" patterns. Our data-driven framework provides a computational foundation for enhancing the robustness of global food systems.