Edited by Peter R. Crane, Yale University, Upperville, VA, and approved September 25, 2020 (received for review April 25, 2020)
We demonstrate that combining optical superresolution imaging with deep learning classification methods increases the speed and accuracy of assessing the biological affinities of fossil pollen taxa. We show that it is possible to taxonomically separate pollen grains that appear morphologically similar under standard light microscopy based on nanoscale variation in pollen shape, texture, and wall structure. Using a single pollen morphospecies, Striatopollis catatumbus, we show that nanoscale morphological variation within the fossil taxon coincides with paleobiogeographic distributions. This new approach improves the taxonomic resolution of fossil pollen identifications and greatly enhances the use of pollen data in ecological and evolutionary research.
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.
Author contributions: I.C.R., S.K., and S.W.P. designed the research; I.C.R., S.K., C.C.F., M.A.U., and S.W.P. performed the research; I.C.R., C.J., F.O.-I., C.D., and S.W.P. analyzed the data; I.C.R., S.K., and S.W.P. wrote the paper; I.C.R. and M.A.U. contributed images; I.C.R., C.J., F.O.-I., and C.D. provided fossil specimens; I.C.R., C.J., and C.D. provided palynological assessments; and S.K. and C.C.F. designed the CNN models.
The authors declare no competing interest.
This article is a PNAS Direct Submission.
This article contains supporting information online at https://www.pnas.org/lookup/suppl/doi:10.1073/pnas.2007324117/-/DCSupplemental.
Log in using your username and password
Log in through your institution
You may be able to gain access using your login credentials for your institution. Contact your library if you do not have a username and password.
If your organization uses OpenAthens, you can log in using your OpenAthens username and password. To check if your institution is supported, please see this list. Contact your library for more details.
You may purchase access to this article. This will require you to create an account if you don’t already have one.