Classification of dinosaur footprints using machine learning

Jones, M, Lallensack, JN, Jarman, I, Falkingham, P and Siekmann, I (2025) Classification of dinosaur footprints using machine learning. Journal of Vertebrate Paleontology. ISSN 0272-4634

Preview

Text CLASSIFICATION OF DINOSAUR FOOTPRINTS USING MACHINE LEARNING.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

Fossilized dinosaur footprints enable us to study the behavior of individual dinosaurs as well as interactions between dinosaurs of the same or different species. There are two principal groups of three-toed dinosaurs, ornithopods and theropods. Determining if a footprint is from an ornithopod or a theropod is a challenging problem. Based on a data set of over 300 dinosaur footprints we train several machine learning models for classifying footprints as either ornithopods or theropods. The data are provided in the form of 20 landmarks for representing each footprint which are derived from images. Variable selection using logistic forward regression demonstrates that the selected landmarks are at locations that are intuitively expected to be especially informative locations, such as the top or the bottom of a footprint. Most models show good accuracy but the recall of ornithopods, of which fewer samples were contained in the data set, was generally lower than the recall of theropods. The Multi-Layer Perceptron (MLP) stands out as the model which did best at dealing with the class imbalance. Finally, we investigate which footprints were misclassified by the majority of models. We find that some misclassified samples exhibit features that are characteristic of the other class or have a compromised shape, for example, a middle toe that points to the left or the right rather than straight ahead.

Item Type:	Article
Uncontrolled Keywords:	0403 Geology; 0602 Ecology; 0603 Evolutionary Biology; Paleontology; 3104 Evolutionary biology; 3705 Geology
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QE Geology > QE701 Paleontology
Divisions:	Biological and Environmental Sciences (from Sep 19) Computer Science and Mathematics
Publisher:	Taylor and Francis Group
Date of acceptance:	4 April 2025
Date of first compliant Open Access:	12 May 2025
Date Deposited:	12 May 2025 14:47
Last Modified:	12 May 2025 15:00
DOI or ID number:	10.1080/02724634.2025.2493157
URI:	https://researchonline.ljmu.ac.uk/id/eprint/26346

View Item