Two distinct and short-lived flooding events of shallow marine waters covered western Amazonia during the Miocene.

Taxonomic resolution is a major challenge in palynology, largely limiting the ecological and evolutionary interpretations possible with deep-time fossil pollen data. We present an approach for fossil pollen analysis that uses optical superresolution microscopy and machine learning to create a quantitative and higher throughput workflow for producing palynological identifications and hypotheses of biological affinity. We developed three convolutional neural network (CNN) classification models: maximum projection (MPM), multislice (MSM), and fused (FM). We trained the models on the pollen of 16 genera of the legume tribe Amherstieae, and then used these models to constrain the biological classifications of 48 fossil Striatopollis specimens from the Paleocene, Eocene, and Miocene of western Africa and northern South America. All models achieved average accuracies of 83 to 90% in the classification of the extant genera, and the majority of fossil identifications (86%) showed consensus among at least two of the three models. Our fossil identifications support the paleobiogeographic hypothesis that Amherstieae originated in Paleocene Africa and dispersed to South America during the Paleocene-Eocene Thermal Maximum (56 Ma). They also raise the possibility that at least three Amherstieae genera (Crudia, Berlinia, and Anthonotha) may have diverged earlier in the Cenozoic than predicted by molecular phylogenies.

The rainforests of Amazonia comprise some of the most biologically diverse ecosystems on Earth. Despite this high biodiversity, little is known about how landscape changes that took place in deep history have affected the assembly of its species, and whether the impact of such changes on biodiversity can still be observed. Here, we present a hypothesis to explain our observation that plants typical of Neotropical coastal habitats also occur in western Amazonia, in some cases thousands of kilometres away from the coast. Evidence on their current distribution, dispersal biology and divergence times estimated from molecular phylogenies suggest that these plants may be the legacy of the large marine‐influenced embayment that dominated the area for millions of years in the Neogene. We hypothesize that coastal plants dispersed along the shores of this embayment and persisted as inland relicts after the marine incursion(s) retreated, probably with the aid of changes in soil conditions caused by the deposition of marine sediments. This dispersal corridor may also have facilitated the colonization of coastal environments by Amazonian lineages. These scenarios could imply an unexpected coastal source that has contributed to Amazonia's high floristic diversity and led to disjunct distributions across the Neotropics. We highlight the need for future studies and additional evidence to validate and shed further light on this potentially important pattern.