Recently, Artificial intelligence has turned out to be increasingly integrated into cultural heritage management, enabling innovations in digital preservation, virtual reconstruction, and more advantageous interactive visitor experiences. However, despite its contributions, its use faces many challenges and also raises numerous ethical concerns. This research aims to Analyze AI ethical concerns related to cultural heritage and develop solutions to the most serious concerns. This study employs a multi-method approach, integrating both qualitative and quantitative approaches. The research focuses on the major challenge of ethical considerations when using AI in cultural heritage management. The research proposed an Ethical framework for using AI in cultural heritage management, Twenty-four Ethics in eight groups, which are considered to be the foundation of an ethical reference that has ensuring a balance between risks and opportunities before risks overtake regulations. The findings indicate that context-sensitive ethical frameworks significantly improve the legitimacy, inclusiveness, and long-term sustainability of AI applications in heritage.
The coastal archaeological site of Carthage in Tunisia (36 degrees 51 ' 16 '' N, 10 degrees 20 ' 06 '' E) is a valuable cultural heritage that requires conservation efforts. The presence of salt-related decay in the baths of Antoninus ruins (162 AD) is threatening their aesthetic appearance and structural stability. The buildings show various aspects of deterioration: honeycombs and black crusts. We provide a characterization of the deterioration mechanism caused by salt using X-ray diffraction, ion chromatography, inductively coupled plasma emission spectroscopy, digital and scanning electron microscopy with EDS analysis, helium porosimetry, and analysis with an optical microscope. The results indicate that the building material is calcarenite, heavily contaminated by halite, gypsum, and traces of nitrates. These contaminants originate from sea spray, dry and wet deposits of atmospheric pollutants, and saline groundwater via capillary rise. Under a seasonally variable Mediterranean climate, they contribute significantly to the physical and chemical limestone masonry deterioration.
To overcome the limitations of expert-dependent and conventional methods in Ming-Qing ceramic chronology analysis, we propose an enhanced ResNet50 model that integrates dual attention mechanisms (channel and self-attention) to amplify discriminative visual features. A reliable dataset of Ming and Qing ceramics was constructed for training and evaluation. Experimental results show that the improved “Ours” model achieves 94.75% accuracy on the test set, a 2.88% improvement over ResNet50, and outperforms advanced models such as VGG16, DenseNet121, and MobileNetV2. Cross-dataset validation indicates that the method shows excellent generalizability for both ceramic type classification and the chronological categorization of other archaeological artifacts. These findings demonstrate that the integration of both channel and self-attention mechanisms effectively resolves the visual feature differences in Ming and Qing ceramics, providing reliable technical support for the digital preservation of cultural heritage. The source code is publicly available at https://github.com/ZhouAlone/ceramic/.
In 1903, the Berlin Museum of Ethnology commissioned Alfredo Jahn Hartman to conduct archaeological excavations in the Lake Valencia basin in Venezuela. Jahn explored two sites, Camburito and El Zamuro, where he unearthed pre-Columbian artefacts and human burials and subsequently sent them to Berlin. More than a century later, we digitised this collection following a detailed protocol to obtain scans with submillimetre accuracy reproducing the geometry and textures of the physical crania. The significance of this work extends beyond the technical digitisation of bioarchaeological samples. These three-dimensional models offer a rare opportunity to revisit and recontextualise this collection. It enables in-depth studies of intentional cranial modification in pre-Columbian societies, enhancing our understanding of the prehistory of the region. Furthermore, it helps preserve these fragile physical samples for future generations. To continue fostering open access and collaboration among specialists, a selection of the digitised collection is available in an online repository.
For the first time, chemical analyses by XRF of all Byzantine copper alloy doors in Italy from the 11th and 12th centuries are presented, compared, and interpreted. Three main alloying groups were detected for the eight doors: leaded bronze (Montecassino), leaded brass (Monte Sant’Angelo, Amalfi, San Paolo fuori le mura, Venice SC), and quaternary alloys (Atrani, Salerno, Venice MD). This leads to the conclusion that Byzantine workshops used different alloys for their production. The different alloying groups cannot be associated with specific, single workshops in Byzantium; also, we cannot exclude the production of specific doors in the same workshop. Together with the ability to date some of the doors by means of inscriptions or historical records this allows new hypotheses to be formulated regarding workshop processes. This research also presents, for the first time, color illustrations of the figuratively decorated backs of the Montecassino door.
Between the 16th and 18th centuries, Spanish and Indigenous people produced millions of colonial documents in diverse calligraphic styles in Latin American territories. Accessing their rich information requires specialised palaeographic skills and often indigenous language expertise. Recent advancements in Machine Learning offer promising solutions to these challenges. This study developed two computational methods: (1) a historical document classifier using Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs), and (2) Handwritten Text Recognition (HTR) models trained on 16th- and 17th-century Spanish manuscripts via Transkribus. The classifier achieved high accuracy, with F1 scores over 90% for most calligraphic styles, while HTR models produced competitive Character Error Rates, notably 5.25% for Redonda, 8.92% for Itálica Cursiva and 14.15% Procesal Simple. These automated tools are now allowing us to transform previously “unreadable” archives into accessible data. This means that soon, Latin American archives and libraries will be able to unlock centuries of historical information.
This study evaluates the accuracy and precision of color measurements obtained from digital images captured using smartphone cameras, validated against standard color cards under controlled lighting conditions. RGB (Red, Green, Blue) and HSV (Hue, Saturation, Value) parameters were extracted using the Colorimeter application (app) on an iPhone and the PineTools program on a computer. Both methods demonstrated high precision, as indicated by small standard deviations in repeated measurements. Significant deviations from Pantone reference values were also observed in the overestimation of S and underestimation of V values. Notably, the Color Grab app on an Android phone exhibited superior accuracy in extracting H and V values compared to the iPhone. Additionally, the CIELAB parameters measured by the Android app were comparable to those obtained from a portable colorimeter. These findings underscore the utility of smartphone colorimetry for precise on-site color classification, with significant potential applications in cultural heritage and archaeology.
The shells of freshwater mussels, commonly found at archaeological sites associated with the Kodjadermen-Gumelnita-Karanovo VI human groups (5th millennium BCE, Romania and Bulgaria), were a significant dietary component for this population. The organic matrix of these ancient shells is often well-preserved and can be analysed using stable isotopes. This study establishes the empirical relationship between the isotopic composition of the acid-insoluble shell organic matrix (AIM) and the soft tissues of modern Unio tumidus. A quality criterion for AIM (C:N ratio 3.6 (3.3-<3.8)) was defined, and isotopic offsets (Delta N-15(AIM-defatted body )= +0.95 parts per thousand, Delta C-13(AIM-defatted body )= +0.93 parts per thousand for soft tissues; Delta N-15(AIM-muscle )= +1.7 parts per thousand, Delta C-13(AIM-muscle )= +0.3 parts per thousand for the adductor muscle) were determined. Our data suggest that the Gumelnita mussels were omnivorous, with a similar trophic level to carp and pond turtles, sourced from diverse water bodies (rivers, lakes & mldr;) based on delta C-13 values. [GRAPHICS] .
Isotopic analysis of archaeological charred plant remains is a useful tool to infer past agricultural practices. However, debate continues over whether charred seeds should be untreated or pretreated before analysis, to counteract any residual contamination and retrieve the "true" isotopic signature of the seed. This paper presents a case study examining whether archaeobotanical remains from Croatia and northern Serbia should be pretreated before isotopic analysis with the aim to provide a pragmatic technique for wider application. A small subset was first examined with an ATR-FTIR and then four different protocols were examined: water rinse only, two different acid-only methods and ABA (acid-base-acid). The results were inconsistent, displaying variability in the effect each protocol had on the isotopic values. Overall, it was concluded that the slight differences between untreated and pretreated sub-samples should not impact the archaeological interpretation, removing the need for pretreatment of the remaining archaeobotanical material.
Virtual reality and databases are two technological domains employed in many scientific fields. In archeology, several works are being developed along these lines. This paper presents the workflow for the creation of an executable virtual reality: it integrates a virtualization of the archaeological site of Venta Micena (Granada, Spain) and a database of some of the most relevant archaeological remains from that site. The strength and novelty of this project are that it allows any user or researcher to walk through the archaeological site, pick up and put down any of the remains found there, access the database of the archaeological remains from any place and time, and visualize them in stereoscopic mode, which could unveil new information and conclusions. This document moreover discusses the contributions and possible limitations of this type of technology, as well as key concepts and the significance of archaeological excavation.
In this study we show the successful deployment of Ground Penetrating Radar (GPR) together with Electrical Resistivity Surveys (ERS) in guiding the archeological excavations at Ashdod-Yam (southern coast of Israel). This approach enabled the precise identification of excavation targets relating to an Early Byzantine ecclesiastical complex located in a residential neighborhood of the modern city of Ashdod. Applied over the course of five years, the combined use of GPR and ERS, interspersed with phases of archeological excavation, not only facilitated an efficient exploration but also ensured the preservation of valuable historical structures. The geophysical data, corroborated by drone images of the post-excavation site, revealed a striking correlation between excavation and non-intrusive survey data. This study not only charts a successful excavation journey but serves as a methodological blueprint for future archeological explorations. The techniques and strategies detailed here have broader implications for the preservation and public presentation of historical sites.
Potsherds from Phra Mahathat Woramahawihan, a revered Buddhist temple in Thailand’s Nakhon Si Thammarat Province, were studied in the context of maritime Southeast Asia and local craftsmanship during the thirteenth–fourteenth century. The CIE L*a*b* and CIE L*C*h* colors of fine- and coarse-paste wares were analyzed using unsupervised and supervised machine learning algorithms. An illustrative example demonstrated the classification capability and cluster prediction. The example showed that supervised machine learning algorithms effectively discriminated between classes with similar characteristics, making colorimetry classification feasible. The kNN classifier achieved an overall accuracy of 87.10%, with high precision measurements (0.90). The supervised approach outperformed in color recognition and classification accuracy for the L*C*h* and combination of L*a*b* and L*C*h*. This strong inter-site discrimination capability is valuable in pottery research. The significantly lower color values of potsherds from Phra Mahathat Woramahawihan temple suggest multiple earthenware production sites in peninsular Thailand during the thirteenth–fourteenth century.
This article presents a novel approach to classifying archaeological artefacts using machine learning, specifically deep learning, rather than relying on traditional, time-consuming human-based methods. By employing Convolutional Neural Networks (CNNs), this approach aims to expedite and enhance the identification process, making it more accessible to a wider audience. The study focuses on two types of artefacts- Roman Lusitanian amphorae (2nd-5th centuries) and Portuguese faience (16th-18th centuries)- chosen for their diversity. While Lusitanian amphorae lack decoration, Portuguese faience poses challenges with subtle colour variations. The study demonstrates the potential of this approach to overcome these hurdles. The paper outlines the methodology, dataset creation, and model training, emphasizing the importance of extensive data and computational resources. The ultimate objective of this research is to develop a mobile application that utilizes image classification techniques to accurately classify ceramic sherds and bring about a significant transformation in archaeological classification.
A methodological proposal was developed for the study of prehistoric siliceous artefacts which includes the use of smartphone photography as an analytical tool. Different kinds of materials (cherts, rock crystal and quartzite) were sampled from the lithic assemblage of La Calvera rock-shelter (Camaleno, Spain), chosen as a case study. Each sample was photographed with a smartphone and colour features were compared with portable and non-destructive standardised techniques including visible spectrophotometry, Raman, diffuse reflectance Fourier transform infrared spectroscopy and portable X-ray fluorescence. The obtained results suggest that smartphone image analysis is a reliable approach to characterise siliceous rocks and that it can be a valuable, cheap and fast method especially suitable for the first screening of large lithic assemblages.
Early Iron Age pottery from central Italian regions has so far largely been studied with a particular emphasis on typological and stylistical features. However, an analytical approach to ancient ceramic technology can reveal a wealth of data on the know-how of early Iron Age central Italian craftspeople and their production choices. With this aim we conducted archaeometric analyses of forty vessels from one of the main protohistoric cemeteries of Vetulonia, coupled with geological surveys of the territory around the settlement and the collection of raw materials. The occurrence of a ceramic fabric marked by fragments of metasedimentary rocks, as opposed to a fabric tempered with flint fragments, indicates the existence of separate traditions, characterised by distinct processes and the addition of specific tempers, probably reflecting different technological practices. The significance of our findings is briefly discussed within the historical and social scenario of early Iron Age Vetulonia, at the dawn of urbanisation.
Archaeological research at Hoeke, a Late Medieval outer harbour of Bruges (Belgium), has revealed large quantities of iron slags, fuel and other remains of iron working. Archaeometrical study has provided an enhanced insight into the historic iron working process, a craft activity which had up till now remained completely unknown in one of the largest economic hubs of medieval Europe. Several petrological, mineralogical and geochemical analytical methods have been applied for this purpose. The metallographic analysis was performed using reflected light optical microscopy, while the mineralogical composition of the slags was characterized X-ray Diffraction (XRD) Spectrometry. Macroscopic identification of plano-convex bottom slag and hammerscales, combined with the geochemical data pointed out that the examined slag is indicating smithing activity, while no traces for iron ore melting were discovered. [GRAPHICS]
The origin of Ireland's fauna is an unresolved issue in the history of the island. Although researchers once considered Ireland's mammals to have spread to Ireland during the early postglacial from 11,700 cal BP, research has increasingly suggested humans translocated many of these species to Ireland. However, due to sparse evidence, the origin of Ireland's purported native mustelid species remains unanswered. In this study, we shed light on the history of otter and badger in Ireland by directly dating suspected early examples of these species from Derragh, Co. Longford, a late Mesolithic campsite. The results demonstrate that both of these species have been present in Ireland for at least 7000-8000 years. It is not clear if they represent self-colonisers or Mesolithic anthropogenic translocations. Although these finds do not rule out local extinction and later reintroduction, they show that we can no longer assume they are solely late Holocene introductions.{GRAPHICAL ABSTRACT}
During the Middle and Late Woodland periods in the American Midwest some small-scale societies transitioned from grit to limestone as the primary clay temper. Limestone offers experimentally demonstrated benefits to vessel manufacture, including decreased wall thickness, but given the society-wide changes in mobility and exchange that also occurred, we investigated whether the use of limestone temper resulted in a different vessel weight relative to an analogous grit-tempered vessel. Our analyses demonstrated a significant difference: post-firing, limestone-tempered vessels were 4.5% lighter than grit-tempered ones. The combination of reduced weight and other benefits could help explain why limestone became the predominant temper type throughout much of the Midwest. These issues have direct analogs in the biological realm, and we use three concepts from evolutionary biology - modularity, mosaic evolution, and constraint - to investigate the role limestone temper played not only in vessel weight but also in other aspects of vessel production and use.
This paper investigates the landscapes of Neolithic communities found within Costa da Morte (Coast of Death), Galicia. Its goal is to uncover whether or not the megalithic monuments of a particular and coherent area of the south-eastern side of the Atlantic Façade are situated in relation to complex locational variables. In particular, in this paper, we explore the entirety of their surrounding horizon. For the very first time, we were able to demonstrate that very specific natural landscapes surrounding the dolmens of this region in Iberia were likely selectively drawn upon, expanding our understanding of the Neolithic of this area and the people's relationship with their natural world.
