Covariate-informed latent interaction models: Addressing geographic & taxonomic bias in predicting bird-plant interactions

Climate change and reductions in natural habitats urge that we better understand species' interconnection and how biological communities respond to environmental changes. However, ecological studies of species' interactions are limited by their geographic and taxonomic focus which can lead to severe under-representation of certain species and distort our understanding of interaction dynamics. We illustrate that ignoring the studies' focus can result in poor performance. We develop an approach for predicting species' interactions that (a) accounts for errors in the recorded interaction networks, (b) addresses the geographic and taxonomic biases of existing studies, (c) is based on latent factors to increase flexibility and borrow information across species, (d) incorporates covariates in a flexible manner to inform the latent factors, and (e) uses a meta-analysis data set from 85 individual studies. We focus on interactions among 232 birds and 511 plants in the Brazilian Atlantic Forest, and identify 5% of pairs of species with an unrecorded interaction, but posterior probability that the interaction is possible over 80%. Finally, we develop a permutation-based variable importance procedure for latent factor network models and identify that a bird's body mass and a plant's fruit diameter are important in driving the presence of species interactions, with a multiplicative relationship.