Projection-Based Classification of Chemical Groups for Provenance Analysis of Archaeological Materials

Abstract

In provenance analysis, identifying the origin of the archaeological artifacts plays a significant role. Usually, this problem is addressed by discovering natural groups in data measured with spectroscopic techniques. Then, principal component and classical partitioning cluster analysis are employed to reveal the groups that supposedly define the origin of the investigated artefacts. However, this work shows that maximizing the variance and searching for specific cluster structures can be misleading because it fails to discriminate clearly the different archeological sources. In contrast, the new methodology reveals several acknowledged geological sources present in the materials through the exploitation of emergence and swarm intelligence without prior assumptions about the data structures. A combination of unsupervised and semi-supervised machine learning and chemometric is applied on samples of Mesoamerican geological sources and obsidian artefacts collected from the archaeological site of Xalasco in Mexico. The analysis of the artifacts showed a preference of Xalasco inhabitants to local obsidian deposits. The results show that this approach, in terms of robustness, is suitable for handling unbiased quantitative spectral analysis of archaeological materials revealing the natural groups of archeological data.

Conventional displays of structures in data compared with interactive projection-based clustering (IPBC)

“…The topographic map looks like a 3D landscape and can be presented either as a top view in 2.5D or interactively rotated in 3D. The additional information encoded on top of the 2D display has been proven to be informative and useful [47,59,60].…”

Use and Misuse of Machine Learning in Anthropology

“…To date, ML has been applied in a number of lithic studies addressing a wide variety of anthropological questions: identifying heat-treated raw material nodules, a practice employed to improve the ease of working raw nodules into stone artifacts [15]; identifying the materials worked by a stone tool according to the classification of the use-wear created on its edge [16], [17]; predicting the original flake mass from variables on the striking platform in order to quantify the degree of resharpening (and thus the length of its use-life as a tool) [18]; predicting site formation conditions from the surface alteration of the site's lithic artifacts [19]; creating more quantitatively rigorous approaches to the creation of typologies for studying artifact shape through time and space [20], [21]; predicting the raw material of the stone tool from the cut marks produced by the edge [22]; identifying the geochemical signatures of geological sources of lithic raw materials as a means of studying prehistoric mobility and material selection criteria [23], [24]; distinguishing the flake products from different reduction strategies for exploiting the volume of a core [25]; distinguishing chronological manifestations of lithic behavior between the Middle and Late Stone Age in Africa through the presence vs. absence of types within assemblages [26]; developing virtual knapping software [27]; and quantifying lithic knapping skill acquisition for studying the evolution of human cognition [28].…”

“…A majority of the papers we reviewed suffered from issues of reproducibility. Many papers (e.g., [17], [23]) had inadequate or confusing textual explanations of the ML methods, making comprehension of the appropriateness of the ML application difficult. Access to raw data and code enables the reader to clarify such confusions.…”

“…Unfortunately complete data and code were frequently not available, so we were not always able to verify with certainty the exact ML methods that were used and the mistakes that were made. Of the papers cited in this review, the citations that share no, or incomplete data, and/or no code include [2]- [9], [11], [12], [17]- [20], [22], [23], [25], [29], [30], [40].…”

Künstliche Intelligenz

“…Auf diese Weise konnte die Herkunft der Werkzeuge geklärt werden. Die meisten waren aus einem Material in der Nähe des Fundorts gefertigt, einige jedoch stammten aus weiter entfernt liegenden Quellen und belegen damit, dass zu dieser Zeit an diesem Ort bereits eine Kultur des Austauschs und Handels bestand[25]. ben-Theorems[2] im allgemeinen Wissenschaftsblatt Scientific American publiziert.…”