The use of canid tooth marks on bone for the identification of livestock predation

Abstract

Historically wolves and humans have had a conflictive relationship which has driven the wolf to extinction in some areas across Northern America and Europe. The last decades have seen a rise of multiple government programs to protect wolf populations. Nevertheless, these programs have been controversial in rural areas, product of the predation of livestock by carnivores. As a response to such issues, governments have presented large scale economic plans to compensate the respected owners. The current issue lies in the lack of reliable techniques that can be used to detect the predator responsible for livestock predation. This has led to complications when obtaining subsidies, creating conflict between landowners and government officials. The objectives of this study therefore are to provide a new alternative approach to differentiating between tooth marks of different predators responsible for livestock predation. Here we present the use of geometric morphometrics and Machine Learning algorithms to discern between different carnivores through in depth analysis of the tooth marks they leave on bone. These results present high classification rates with up to 100% accuracy in some cases, successfully differentiating between wolves, dogs and fox tooth marks.

A Hybrid Geometric Morphometric Deep Learning Approach for Cut and Trampling Mark Classification

“…BSM analysis remains to be a very important component of taphonomic studies, whereby their identification and in-depth analysis can reveal multiple components regarding early hominin populations [11][12][13][14][15], their development [6,7,23], and their associated paleoecologies [14,24,28]. Nevertheless, issues imposed by equifinality have led to complications in their identification and interpretation [1][2][3][4][5], requiring more objective and empirical methods that can be used for BSM classification and characterization [21][22][23][24][25][26][27]30,58].…”

“…The implementation of Geometric Morphometric studies has been able to reveal a means of inferring different tool use [21] as well as raw material management [21][22][23] through cut mark morphologies. Moreover, when applied to the carnivore induced BSMs, analysts have been able to differentiate between carnivore agents based on tooth mark morphologies [24][25][26][27]. The innovative introduction of Artificial Intelligence (AI) in taphonomy [26][27][28][29][30][31] has additionally been able to overcome multiple barriers imposed by subjectivity [32].…”

“…Moreover, when applied to the carnivore induced BSMs, analysts have been able to differentiate between carnivore agents based on tooth mark morphologies [24][25][26][27]. The innovative introduction of Artificial Intelligence (AI) in taphonomy [26][27][28][29][30][31] has additionally been able to overcome multiple barriers imposed by subjectivity [32]. This presents a powerful tool for the construction of classification models, presenting a series of efficient tools for the processing of complex data.…”

Obtaining new resolutions in carnivore tooth pit morphological analyses: A methodological update for digital taphonomy

“…In archaeology/palaeontology, a possible response to this situation has been the collection and pooling of morphometric datasets via online resources [104, 105 inter alia], while some datasets are available through supplementary materials [e.g. [56][57][58][59]. Nevertheless, pooling of data from different sources is often conflictive, and induced errors are likely to increment if data collection is not strictly controlled [67].…”

“…Each of these samples were originally studied by Yravedra et al [58], identifying significant differences in tooth pit morphology for the identification of livestock predation in Europe. These bone surface modifications can thus be used as a control sample considering how morphological variations are already known in detail.…”