Machine learning helping to re-assess the "Mawson Collection" fossils

• Grant number: 25/08219-9
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date: August 01, 2025
• End date: January 26, 2026
• Field of knowledge: Biological Sciences - Zoology - Paleozoology
• Principal Investigator: Max Cardoso Langer
• Grantee: Felipe de Sena Dias Urpia
• Supervisor: Paul Michael Barrett
• Host Institution: Faculdade de Filosofia, Ciências e Letras de Ribeirão Preto (FFCLRP). Universidade de São Paulo (USP). Ribeirão Preto , SP, Brazil
• Institution abroad: Natural History Museum, London, England
• Associated to the scholarship: 24/16852-0 - Archosaur fossils from the 'Mawson Collection', Ilhas Group, Recôncavo graben, Eocretaceous of Bahia, BP.MS

Abstract

The fossils collected between the end of the 19th century and the beginning of the 20th century in the nowadays metropolitan area of Salvador-BA are probably among the historically oldest records of Mesozoic archosaurs in Brazil. One of the main collectors of such fossils was the amateur palaeontologist Joseph Mawson, a railway engineer responsible for the construction of the Bahia to São Francisco Railway at the time. During the works, Mawson identified several outcrops of what is currently considered part of the Ilhas Group, collecting fossils that would become part of the "Mawson Collection". Over the years, some of the archosaur remains of the "Mawson Collection" have been reevaluated on the light of updated knowledge, with crocodile teeth redescribed as pterosaur teeth and, more recently, megalosaurid vertebrae and phalanges reassigned to Spinosauridae. In this context, the main objective of this project is to reevaluate (describe and taxonomically position) the "Mawson Collection" teeth utilizing machine learning methods.