Mammalian faunas, ecological indices, and machine-learning regression for the purpose of paleoenvironment reconstruction in the Miocene of South America

Thumbnail Image



Journal Title

Journal ISSN

Volume Title

Repository Usage Stats


Citation Stats


© 2019 Elsevier B.V. Reconstructing paleoenvironments has long been considered a vital component for understanding community structure of extinct organisms, as well as patterns that guide evolutionary pathways of species and higher-level taxa. Given the relative geographic and phylogenetic isolation of the South American continent throughout much of the Cenozoic, the South American fossil record presents a unique perspective of mammalian community evolution in the context of changing climates and environments. Here we focus on one line of evidence for paleoenvironment reconstruction: ecological diversity, i.e. the number and types of ecological niches filled within a given fauna. We propose a novel approach by utilizing ecological indices as predictors in two regressive modeling techniques—Random Forest (RF) and Gaussian Process Regression (GPR)—which are applied to 85 extant Central and South American localities to produce paleoecological prediction models. Faunal richness is quantified via ratios of ecologies within the mammalian communities, i.e. ecological indices, which serve as predictor variables in our models. Six climate/habitat variables were then predicted using these ecological indices: mean annual temperature (MAT), mean annual precipitation (MAP), temperature seasonality, precipitation seasonality, canopy height, and net primary productivity (NPP). Predictive accuracy of RF and GPR is markedly higher when compared to previously published methods. MAT, MAP, and temperature seasonality have the lowest predictive error. We use these models to reconstruct paleoclimatic variables in two well-sampled Miocene faunas from South America: fossiliferous layers (FL) 1–7, Santa Cruz Formation (Early Miocene), Santa Cruz Province, Argentina; and the Monkey Beds unit, Villavieja Formation (Middle Miocene) Huila, Colombia. Results suggest general concordance with published estimations of precipitation and temperature, and add information with regards to the other climate/habitat variables included here. Ultimately, we believe that RF and GPR in conjunction with ecological indices have the potential to contribute to paleoenvironment reconstruction.





Published Version (Please cite this version)


Publication Info

Spradley, JP, BJ Glazer and RF Kay (2019). Mammalian faunas, ecological indices, and machine-learning regression for the purpose of paleoenvironment reconstruction in the Miocene of South America. Palaeogeography, Palaeoclimatology, Palaeoecology, 518. pp. 155–171. 10.1016/j.palaeo.2019.01.014 Retrieved from

This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.



Richard Frederick Kay

Professor of Evolutionary Anthropology

I have two areas of research:1) the evolution of primates in South America; and 2) the use of primate anatomy to reconstruct the phylogenetic history and adapations of living and extinct primates, especially Anthropoidea.

1) Evolution of primates and mammalian faunal evolution, especially in South America. For the past 30 years, I have been engaged in research in Argentina, Bolivia The Dominican Republic, Peru, and Colombia with three objectives:a) to reconstruct the evolutionary history and adaptive patterns of South America primates and other mammals; b) to establish a more precise geologic chronology for the mammalian faunas between the late Eocene and middle Miocene (between about 36 and about 15 million years ago); and c) to use anatomy and niche structure of modern mammals as a means to reconstruct the evolution of mammalian niche structure in the Neotropics.

2) Primate Anatomy. I am working to reconstruct the phylogeny of primates based (principally) on anatomical evidence; and to infer the adaptations of extinct primates based mainly on cranial and dental evidence.

Field activities
Current fieldwork is focused on the study of terrestrial biotic change in Patagonia through the 'mid-Miocene Climate Optimum' when global climate was moderate and the subtropical zone, with primates and other typically tropical vertebrates, extended their ranges up to 55 degrees of South latitude.

In this collaborative research undertaking with colleagues at University of Washington and Boise State University, the geochronology of the Santa Cruz Formation at in extreme southern Argentina is being refined using radiometric dating. Stratigraphically-controlled collections have been made of vertebrates and plant macro- and microfossils. Climate change and its impact on the biota is assessed 1) using biogeochemical analysis of stable isotopes in fossil mammalian tooth enamel; 2) by documenting changes in mammalian community structure (richness, origination and extinction rates, and ecological morphology); and 3) by documenting changes in vegetation and floral composition through the study of phytoliths. These three independent lines of evidence in a refined geochronologic framework will then be compared with similar evidence from continental sequences in the Northern Hemisphere and oceanic climatic records to improve our understanding of the timing and character of climatic change in continental high latitudes during this temporal interval.

A second field project project in its early stages is the study of the fossil vertebrates of the Amazon Basin. The latter is a collaborative effort of biologists and geologists across schools at Duke (Nicholas School) and among six North American universities. My role is to direct the vertebrate paleontology component of this project in Brazil and Amazonian Peru. The hope is to recover primates from the Oligocene through Early Miocene. New material will shed light on the phylogenetic status of African Paleogene anthropoids, one of which may be the platyrrhine sister-taxon. Also, new remains of fossil primates will help to refine hypotheses about the origins of the modern families and subfamilies of platyrrhines, all of which trace back to an Early Miocene (17-21 Ma) common ancestor. Finally, new fossil primates may further constrain the time of entry of platyrrhines into South America.

Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.