Encoding and decoding illegal wildlife trade networks reveals key airport characteristics and undetected hotspots

The illegal wildlife trade is a key driver of biodiversity loss and a barrier to desired transformations in socio-environmental systems. It is known to exploit licit networks, such as the global airline flight network, yet the ability of science to support efforts to reduce the illegal wildlife trade remains underdeveloped. Research on the illegal wildlife trade relies on biased aggregate counts of observed incidents, leading to potential policy misguidance. Here we utilize centrality analysis and predictive modeling to encode and decode illegal wildlife trade flight networks to improve sensemaking with implications for sustainable futures. Methods advance existing analyses by revealing traffickers prioritize airports with high centrality in the global airline flight network, high incidence of flora crimes, and a limited level of non-state actor oversight. Machine learning models identify airports likely to be involved in the illegal wildlife trade not currently implicated in seizure data, including in the United States. Machine learning methods enable the discovery of previously hidden illegal wildlife trade hotspots within global flight networks among high centrality airports.