Holt, Emily  ORCID: https://orcid.org/0000-0002-2300-2610, Lugli, Federico, Schirru, Davide, Gigante, Melania, Faillace, Katie, Millet, Marc-Alban ORCID: https://orcid.org/0000-0003-2710-5374, Andersen, Morten ORCID: https://orcid.org/0000-0002-3130-9794 and Madgwick, Richard ORCID: https://orcid.org/0000-0002-4396-3566
2025.
Comparing machine learning isoscapes of 87Sr/86Sr ratios of plants on the island of Sardinia: Implications for the use of isoscapes for assessing the provenance of biological specimens.
Science of the Total Environment
989
, 179880.
10.1016/j.scitotenv.2025.179880
|
Preview |
PDF
- Published Version
Available under License Creative Commons Attribution. Download (14MB) | Preview |
Abstract
Strontium isotope analysis is widely used to evaluate the provenance and mobility of biological specimens. Frequently applied in archaeology, palaeontology, ecology, forensics, and food science, strontium isotope analysis compares the 87Sr/86Sr ratio of a specimen against a strontium isoscape – a representation of expected 87Sr/86Sr ratios across a landscape – to identify areas that are more and/or less likely to be the source of the specimen. Strontium isoscapes are built using different methods, but all approaches start with empirical 87Sr/86Sr ratios sampled from areas with known coordinates and use them to assign likely 87Sr/86Sr ratios to unknown areas. Following the publication of Bataille et al., 2018 and Bataille et al., 2020, machine learning using a random forest algorithm has become a common method of producing strontium isoscapes. Despite the recognition that this method requires training with local ratios, especially in geologically complex regions, very little work has evaluated machine learning isoscapes' accuracy. This study compares and evaluates two previously published machine learning isoscapes of Sardinia against new empirical data provided by the project ZANBA. The ZANBA data is then used to create a third machine learning map of Sardinia, which is tested against previously published empirical data. The three isoscapes show different levels of predictive accuracy, with more primary data points leading to more correct predictions. However, a densely sampled landscape did not create an isoscape that gave substantially more accurate predictions than a moderately densely sampled landscape when tested against primary data from outside the original sampling areas. Areas of an isoscape with low root mean squared error (RMSE), which is often interpreted as indicating accuracy, did not necessarily give more correct predictions. Finally, a machine learning isoscape of Sardinia that incorporates both new and previously published empirical data is presented.
| Item Type: | Article |
|---|---|
| Date Type: | Publication |
| Status: | Published |
| Schools: | Schools > Earth and Environmental Sciences Schools > History, Archaeology and Religion |
| Subjects: | C Auxiliary Sciences of History > CC Archaeology |
| Publisher: | Elsevier |
| ISSN: | 0048-9697 |
| Date of First Compliant Deposit: | 14 June 2025 |
| Date of Acceptance: | 8 June 2025 |
| Last Modified: | 18 Jun 2025 13:45 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/179078 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions