Planktonic foraminiferal species identification is central to many paleoceanographic studies, from selecting species for geochemical research to elucidating the biotic dynamics of microfossil communities relevant to physical oceanographic processes and interconnected phenomena such as climate change. However, few resources exist to train students in the difficult task of discerning amongst closely related species, resulting in diverging taxonomic schools that differ in species concepts and boundaries. This problem is exacerbated by the limited number of taxonomic experts. Here we document our initial progress toward removing these confounding and/or rate-limiting factors by generating the first extensive image library of modern planktonic foraminifera, providing digital taxonomic training tools and resources, and automating species-level taxonomic identification of planktonic foraminifera via machine learning using convolution neural networks. Experts identified 34,640 images of modern (extant) planktonic foraminifera to the species level. These images are served as species exemplars through the online portal Endless Forams (endlessforams.org) and a taxonomic training portal hosted on the citizen science platform Zooniverse (zooniverse.org/projects/ahsiang/ endless-forams/). A supervised machine learning classifier was then trained with~27,000 images of these identified planktonic foraminifera. The best-performing model provided the correct species name for an image in the validation set 87.4% of the time and included the correct name in its top three guesses 97.7% of the time. Together, these resources provide a rigorous set of training tools in modern planktonic foraminiferal taxonomy and a means of rapidly generating assemblage data via machine learning in future studies for applications such as paleotemperature reconstruction.

The Himalayan-sourced Ganges-Brahmaputra river system and the deep-sea Bengal Fan represent Earth’s largest sediment-dispersal system. Here we present detrital zircon U-Pb provenance data from Miocene to middle Pleistocene Bengal Fan turbidites, and evaluate the influence of allogenic forcing vs. autogenic processes on signal propagation from the Himalaya to the deep sea. Our data record the strong tectonic and climatic forcing characteristic of the Himalayan system: after up to 2500 km of river transport, and >1400 km of transport by turbidity currents, the U-Pb record faithfully represents Himalayan sources. Moreover, specific U-Pb populations record Miocene integration of the Brahmaputra drainage with the Asian plate, as well as the rapid Plio-Pleistocene incision through, and exhumation of, the eastern Himalayan syntaxis. The record is, however, biased towards glacial periods when rivers were extended across the shelf in response to climate-forced sea-level fall, and discharged directly to slope canyons. Finally, only part of the record represents a Ganges or Brahmaputra provenance end-member, and most samples represent mixing from the two systems. Mixing or the lack thereof likely represents the fingerprint of autogenic delta-plain avulsions, which result in the two rivers delivering sediment separately to a shelf-margin canyon or merging together as they do today.

No abstract

Widely regarded as an imminent threat to our oceans, ocean acidification has been documented in all oceanic basins. Projected changes in seawater chemistry will have catastrophic biotic effects due to ocean acidification hindering biogenic carbonate production, which will in turn lead to substantial changes in marine ecosystems. However, previous attempts to quantify the effect of acidification on planktonic calcifying organisms has relied on laboratory based studies with substantial methodological limitations. This has been overcome by comparing historic plankton tows from the seminal HMS Challenger Expedition (1872-1876) with the recent Tara Oceans expedition material (2009-2016). Nano CT-scans of selected equatorial Pacific Ocean planktonic foraminifera, have revealed that all modern specimens had up to 76% thinner shells than their historic counterparts. The "Challenger Revisited" project highlights the potential of historic ocean collections as a tool to investigate ocean acidification since the early Industrial Revolution. Further analyses of such biotic archives will enable researchers to quantify the effects of anthropogenic climate change across the globe.