Determining the origins of Phoenician silver
Exploring the potential of machine learning for lead isotope analysis
Bibliographic Data
| ID | 7476502 |
|---|---|
| Authors | Evgeny Shnyr (University of Haifa, corresponding author), Tsvi Kuflik (0000-0003-0096-4240, University of Haifa), Karan Desai (0000-0003-2325-7880, University of Haifa), Tzilla Eshel (0000-0003-0976-0877, University of Haifa) |
| Year | 2026 |
| Volume | 188 |
| Pages | 106499-106499 |
| Publication date | 2026-02-12 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Journal of Archaeological Science (JOURNAL) |
| Journal identifiers | ISSN: 0305-4403 • E-ISSN: 1095-9238 |
| Publisher | Elsevier BV (PUBLISHER) |
| DOI | 10.1016/j.jas.2026.106499 |
| OpenAlex | W7128697197 |
| Language | EN |
| References cited | 32 |
This study investigates the provenance of Phoenician silver hoards through the integration of machine learning algorithms with lead isotope analysis (LIA). Utilizing an extensive isotopic database of ores, advanced clustering techniques (DBSCAN) enabled the identification of distinct groups within the data. Outliers were removed, and dataset imbalances were addressed using the SMOTE algorithm, thereby enhancing the prediction accuracy. An efficient and robust machine learning model (XGBoost) was employed to classify isotopic signatures and assign probable ore sources with high confidence. To test the model, endmembers from the previously published Southern Levantine Iron Age silver hoards of Tel Dor, ʿAkko, ʿEin Hofez, and ʿArad were defined by using a new automated algorithm for endmember selection. The algorithm applies principal component analysis (PCA) aligned with the geological age model (geochron) to define isotopic endmembers in a structured and reproducible way, moving beyond purely visual identification. Although exploratory in nature, and with some manual adjustments still required, this approach offers a more systematic framework for provenance studies. Our findings support previous interpretations regarding early Phoenician endeavors to Sardinia and Anatolia, highlight the role of Iberian silver, and introduce new possible connections to the Aegean. Overall, this research demonstrates the potential of combining automated endmember identification with machine learning to provide new insights into ancient Mediterranean trade networks. • Machine learning applied to Phoenician silver lead isotope analysis. • DBSCAN clustering used to detect outliers and subgroup patterns. • SMOTE balancing and XGBoost improved provenance classification. • Endmember identification reveals composite metal source scenarios. • Transparent scalable framework for future provenance studies in archaeometallurgy
Cluster analysis · Endmember · Identification (biology · Outlier · Phoenician · Principal component analysis · Provenance · Support vector machine · Archaeology and ancient environmental studies · Cultural Heritage Materials Analysis · Mineralogy and Gemology Studies
An analysis of variance test for normality (complete samples)
A Cluster Separation Measure
The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance
Approximation of terrestrial lead isotope evolution by a two-stage model
Smote
Greedy function approximation
Silhouettes
Rome'S Rise to Power. Geochemical Analysis of Silver Coinage from the Western Mediterranean (Fourth to Second Centuries BCE)
LIA of Prehistoric Metals in the Central Mediterranean Area
A miner's perspective on Pb isotope provenances in the Western and Central Mediterranean
A new algorithm for using Pb isotopes to determine the provenance of bullion in ancient Greek coinage
Bullion mixtures in silver coinage from ancient Greece and Egypt
A database of lead isotopic signatures of copper and lead ores for Europe and the Near East
Stable lead isotope studies of central taurus ore sources and related artifacts from eastern mediterranean chalcolithic and bronze age sites
Metal provenance of Iron Age Hacksilber hoards in the southern Levant
Narrowing provenance for ancient Greek silver coins using Ag isotopes and Sb contents of potential ores
The Macro‐Regional Scale of Silver Production in I beria During the First Millennium BC in the Context of Mediterranean Contacts
The Sources of Mycenaean Silver and Lead
Cycladic Lead and Silver Metallurgy
Retracing Magna Graecia's silver
A Geological Perspective on the Use of Pb Isotopes in Archaeometry
A ‘match–no match‘ numerical and graphical kernel density approach to interpreting lead isotope signatures of ancient artefacts
From commodity to money
From Iberia to the Southern Levant
Levantine Hacksilber and the flow of silver in early Mediterranean commerce
From Iberia to Laurion
| Citation velocity | historical |
|---|---|
| Highly cited | No |