A machine learning approach for the discrimination of theropod and ornithischian dinosaur tracks
A machine learning approach for the discrimination of theropod and ornithischian dinosaur tracks
复制标题
DOI：
10.1098/rsif.2022.0588
复制
发表时间：
2022-11-09
影响因子：
3.9
通讯作者：
Falkingham, Peter L.
中科院分区：
文献类型：
--
作者：
Lallensack, Jens N.;Romilio, Anthony;Falkingham, Peter L.
化石足迹是重要的古生物资料来源。然而，对其形状的定量分析受到其高度可变性和缺乏离散边缘和地标的阻碍。我们在这里提出了第一种使用深度卷积神经网络（DCNNs）来研究化石足迹的方法，克服了以前统计方法的局限性。我们使用DCNN基于1372个轮廓轮廓来区分兽脚亚目和鸟臀目恐龙的足迹。在一个独立的测试集上，DCNN的表现一直优于人类专家。我们还使用DCNN对来自澳大利亚Lark Quarry的大型三趾动物的足迹进行了分类，其身份一直受到激烈争论。所提出的方法只能被认为是机器学习在化石足迹研究中更广泛应用的第一步，这不仅限于分类问题。目前的局限性，如解释性轮廓固有的主观性和信息丢失，可能会在未来通过直接在三维模型上训练神经网络来克服，尽管这需要在该领域的工作人员中增加对数字化的吸收。
Fossil tracks are important palaeobiological data sources. The quantitative analysis of their shape, however, has been hampered by their high variability and lack of discrete margins and landmarks. We here present the first approach using deep convolutional neural networks (DCNNs) to study fossil tracks, overcoming the limitations of previous statistical approaches. We employ a DCNN to discriminate between theropod and ornithischian dinosaur tracks based on a total of 1372 outline silhouettes. The DCNN consistently outperformed human experts on an independent test set. We also used the DCNN to classify tracks of a large tridactyl trackmaker from Lark Quarry, Australia, the identity of which has been subject to intense debate. The presented approach can only be considered a first step towards the wider application of machine learning in fossil track research, which is not limited to classification problems. Current limitations, such as the subjectivity and information loss inherent in interpretive outlines, may be overcome in the future by training neural networks on three-dimensional models directly, though this will require an increased uptake in digitization among workers in the field.