Ruminants (Giraffidae and Bovidae) from Kanapoi

African bovid tribe classification using transfer learning and computer vision

Objective analytical identification methods are still a minority in the praxis of paleobiological sciences. Subjective interpretation of fossils and their modifications remains a nonreplicable expert endeavor. Identification of African bovids is a crucial element in the reconstruction of paleo-landscapes, ungulate paleoecology, and, eventually, hominin adaptation and ecosystemic reconstruction. Recent analytical efforts drawing on Fourier functional analysis and discrimination methods applied to occlusal surfaces of teeth have provided a highly accurate framework to correctly classify African bovid tribes and taxa. Artificial intelligence tools, like computer vision, have also shown their potential to be objectively more accurate in the identification of taphonomic agency than human experts. For this reason, here we implement some of the most successful computer vision methods, using transfer learning and ensemble analysis, to classify bidimensional images of African bovid teeth and show that 92% of the large testing set of images of African bovid tribes analyzed could be correctly classified. This brings an objective tool to paleoecological interpretation, where bovid identification and paleoecological interpretation can be more confidently carried out.

The environments of Australopithecus anamensis at Allia Bay, Kenya: A multiproxy analysis of early Pliocene Bovidae

Australopithecus anamensis, among the earliest fully bipedal hominin species, lived in eastern Africa around 4 Ma. Much of what is currently known about the paleoecology of A. anamensis comes from the type locality, Kanapoi, Kenya. Here, we extend knowledge of the range of environments occupied by A. anamensis by presenting the first multiproxy paleoecological analysis focusing on Bovidae excavated from another important locality where A. anamensis was recovered, locality 261-1 (ca. 3.97 Ma) at Allia Bay, East Turkana, Kenya. Paleoenvironments are reconstructed using astragalar ecomorphology, mesowear, hypsodonty index, and oxygen and carbon isotopes from dental enamel. We compare our results to those obtained from Kanapoi. Our results show that the bovid community composition is similar between the two fossil assemblages. Allia Bay and Kanapoi bovid astragalar ecomorphology spans the spectrum of modern morphologies indicative of grassland, woodland, and even forest-adapted forms. Dietary reconstructions based on stable isotopes, mesowear, and hypsodonty reveal that these bovids' diet encompassed the full C₃ to C₄ dietary spectrum and overlap in the two data sets. Our results allow us to confidently extend our reconstructions of the paleoenvironments of A. anamensis at Kanapoi to Allia Bay, where this pivotal hominin species is associated with heterogeneous settings including habitats with varying degrees of tree cover, including grasslands, bushlands, and woodlands.