Geometric morphometrics sheds new light on the identification and domestication status of ‘new glume wheat’ at Neolithic Çatalhöyük

Roushannafas, Tina; Bogaard, Amy; Charles, Michael

doi:10.1016/j.jas.2022.105599

Cited by 14 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By comparing archaeological material to modern collections of reference, GMM and EFT in particular for plants, allowed fine-grained inferences, in particular to document the emergence of new morphological types, reconstruct the dynamics of their diffusion in both time and space, and overall gain insights into the intertwined histories of human societies and domesticated plants (Terral et al, 2004(Terral et al, , 2010(Terral et al, , 2012Burger et al, 2011;Bouby et al, 2013;Ros et al, 2014;Pagnoux et al, 2015;Bonhomme et al, 2017aBonhomme et al, , 2021bWallace et al, 2018;Bourgeon et al, 2018;Tarongi et al, 2021;Jesus et al, 2021;Evin et al, 2022;Roushannafas et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Deep learningversusgeometric morphometrics for archaeobotanical domestication study and subspecific identification

Bonhomme,

Bouby,

Claude

et al. 2023

Preprint

View full text Add to dashboard Cite

Taxonomical identification of archaeological fruit and seed is of prime importance for any archaeobotanical studies. We compared the relative performance of deep learning and geometric morphometrics at identifying pairs of plant taxa. We used their seeds and fruit stones that are the most abundant recovered organs in archaeobotanical assemblages, and whose morphological identification, chiefly between wild and domesticated types, allow to document their domestication and biogeographical history. We used existing modern datasets of four plant taxa (date palm, barley, olive and grapevine) corresponding to photographs of two orthogonal views of their seeds that were analysed separately to offer a larger spectrum of shape diversity. On these eight datasets, we compared the performance of a deep learning approach, here convolutional neural networks (CNN), to that of a geometric morphometric approach, here outline analyses using elliptical Fourier transforms (EFT). Sample sizes were at minimum eight hundred seeds in each class, which is quite small when training deep learning models but of typical magnitude for archaeobotanical studies. Our objectives were twofold: i) to test whether deep learning can beat geometric morphometrics in taxonomic identification and if so, ii) to test which minimal sample size is required. We ran simulations on the full datasets and also on subsets, starting from 50 images in each binary class. For CNN networks, we deliberately used a candid approach relying on pre-parameterised VGG16 network. For EFT, we used a state-of-the art morphometrical pipeline. The main difference rests in the data used by each model: CNN used bare photographs where EFT used (x, y) outline coordinates. This 'pre-distilled' geometrical description of seed outlines is often the most time-consuming part of morphometric studies. Results show that CNN beats EFT in most cases, even for very small datasets. We finally discuss the potential of CNN for archaeobotany, why outline analyses and morphometrics have not yet said their last word by providing quantitative descriptions, and how bioarchaeological studies could embrace both approaches, used in a complementary way, to better assess and understand the past history of species.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learningversusgeometric morphometrics for archaeobotanical domestication study and subspecific identification

Bonhomme,

Bouby,

Claude

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In archaeobotany, GMMs have so far been applied mainly to seeds and fruits (Portillo et al, 2020). The most common objectives are to distinguish close taxonomical levels, from neighbouring species (Bonhomme et al, 2017;Jesus et al, 2021;Roushannafas et al, 2022;Tarongi et al, 2021;Terral et al, 2012;Ucchesu et al, 2017); subspecies (Bonhomme et al, 2020;Gros-Balthazard et al, 2017;Orrù et al, 2013;Ros et al, 2014), especially in domestication studies to differentiate domestic forms from wild ancestors; and groups of cultivated varieties (Pagnoux et al, 2021;Terral et al, 2021Terral et al, , 2010. Nearly all of the studies in archaeobotany use 2D digital images and of outline analyses of the seeds/fruits, mostly using elliptical Fourier transforms (EFT) and polynomial fitting (Evin et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Experimental waterlogging of grape seeds, impact on seed shape and geometrical reversing for morphometric inference

Bouby,

Bonhomme,

Ivorra

et al. 2023

Journal of Archaeological Science: Reports

View full text Add to dashboard Cite

Overview of ‘Biological Resources’ – From Old Debates to Urgent Ecological Dilemmas

Bogaard¹

2023

Handbook of Archaeological Sciences

View full text Add to dashboard Cite

Geometric morphometrics sheds new light on the identification and domestication status of ‘new glume wheat’ at Neolithic Çatalhöyük

Cited by 14 publications

References 44 publications

Deep learningversusgeometric morphometrics for archaeobotanical domestication study and subspecific identification

Deep learningversusgeometric morphometrics for archaeobotanical domestication study and subspecific identification

Experimental waterlogging of grape seeds, impact on seed shape and geometrical reversing for morphometric inference

Overview of ‘Biological Resources’ – From Old Debates to Urgent Ecological Dilemmas

Contact Info

Product

Resources

About