https://www.um.edu.mt/library/oar/handle/123456789/132918 Thu, 09 Apr 2026 16:23:27 GMT 2026-04-09T16:23:27Z https://www.um.edu.mt/library/oar/handle/123456789/140517 Title: From object detection to archaeological object detection developing a model for amphora identification of a Punic wreck site using object recognition AI Abstract: The last years have seen an increase in the use of object detection methodologies in land archaeology during surveys, the study of archaeological assemblages, reconstruction of archaeological materials, and taphonomic studies. The advances of these methods in maritime archaeology have been more limited. This study explores how AI object detection can help identify archaeological materials underwater. It aims to explain the issues that the underwater environment presents for automated detection, to bridge the knowledge gap that exists between the practical application of this computer vision technique to maritime archaeology, and to provide a practical example of its application on the underwater assemblage of Xlendi Archaeological Park, one with which to evaluate the possibilities that the use of such methodology presents for archaeological research. We trained, classified and named a total of seventy-two detection models based on three differentiating factors. The Progressive Complexity Index (PCI) divides them into groups based on their level of complexity and the amount of archaeological information embedded in their predictive process. The Parameter of Archaeological Identification (PAI) specifies the archaeological framework used during training to teach subjective information. Finally, the models are also different in the version and size of model they use. To fulfill the goals of this project, we used these differences to interpret the results of a series of comparatives tests made on data not seen by the algorithm during training, thus recreating a real-world situation in which to evaluate the technique. The result is the division of the models into three progressively complex groups: nature models, state models and typological models. Nature models focus on the assessment of underwater archaeological assemblages by the nature of the materials to be found in them, classifying them based on them being ceramic, litter, modern elements, or part of the natural background. On their best iterations, these achieved an average precision of identification of 87.8%. State models, on the other hand, focus on the state of preservation of those materials. Their best iteration’s average precision, while lower at 75.2%, still produced very usable models on a real-world scenario. Finally, typological models focus on ceramic materials based on their typology. Their best iteration, while not being field-ready with an average precision of 61.1%, offers a lot of potential for improvement. This dissertation has demonstrated how subjective archaeological information can be integrated into YOLO models to develop detection models tailored to specific archaeological questions. By analyzing and comparing these models, it has outlined the technique’s fundamental applications, limitations, and future potential for studying underwater archaeological assemblages. Description: M.A.(Melit.) Wed, 01 Jan 2025 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/140517 2025-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/140515 Title: A faunal assemblage from a harbor, Salina Bay : animals in maritime foodways and zooarchaeological analysis from an underwater context in Malta Abstract: This dissertation investigates the integration of zooarchaeological analysis within underwater archaeology, focusing on the submerged harbor archaeological site of Salina Bay, Malta, dated primarily to Late Antiquity (250–750 CE). The study addresses the methodological challenges and interpretive potential of analyzing faunal remains from underwater contexts, an area often underrepresented in underwater archaeological research. By examining the faunal assemblage recovered during the 2019 archaeological campaigns, this research explores taxonomic diversity, butchery cut mark patterns, and diet involving animal meat and by-products. Additionally, it evaluates taphonomic processes—both anthropogenic and biogeochemical—that influence the preservation and state of faunal remains recovered from an underwater archaeological site. Primary data collection involved elemental and taxonomic category classification using comparative osteological collections. Further data collection included age estimation through epiphysial fusion, and tooth eruption and wear stages. Key findings reveal an assemblage (NSP = 145) dominated by domesticated genus groups such as Bos, Sus, and Ovicaprids. Examination of cut marks related to primary butchery practices, including the dismemberment at articulation joints and defleshing from bones. Taphonomic analysis highlighted the distinct preservation challenges posed by submerged environments, offering new perspectives on the site formation process observed in the Salina Bay archaeological site in an archaeofaunal assemblage marked by surface abrasion and fragmentation. This interdisciplinary study bridges gaps between zooarchaeology and underwater archaeology by demonstrating the value of faunal analyses in reconstructing human-animal interactions within maritime cultural landscapes. It underscores the importance of implementing standardized methodologies throughout the project plan design of an underwater archaeological campaign in order to contribute to zooarchaeological and taphonomic research. Description: M.A.(Melit.) Wed, 01 Jan 2025 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/140515 2025-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/140513 Title: Predictive modeling of aviation crash sites located within Tunisia, Algeria, and Morocco waters during a World War Two wartime context Abstract: The dissertation’s aim was to predict underwater aircraft crash sites off the coast of North Africa and Southern Sicily through examination of archival research, various credible sources, and spatial analysis of data. The focused chronology of the dissertation was specifically during World War II’s Operation Torch and Operation Husky. A good understanding was established through the historical context of both of these operations. The study looked at many different variables in order to explain how and why crash sites were occurring, as well as accumulating within specific areas (both operations landing areas). Collected data was implemented into Geographical Information Systems (GIS) and was specifically used to predictive model, which would in turn, furthered the understanding of accumulations of crash sites. Once the landing areas were determined to have a significant amount of high-probability of crash sites, supported by the research and collected data, they were analyzed in order to prove the value of surveying them. Once those distinctions were made, the dissertation shifted its focus to showing how these areas could be feasibly surveyed through underwater investigation techniques. The results of the desk-based research, methodology, and digitizing of the data was thoroughly presented and discussed. The dissertation concludes with further research, limitations, and the importance of locating the underwater crash sites. The goal that was reached within the dissertation was to not only find areas that have a high probability of discovering unknown crash sites but also to provide further research of aviation studies, underwater aviation studies, and ultimately aid in the hope of locating missing servicemen. Description: M.A.(Melit.) Wed, 01 Jan 2025 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/140513 2025-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/140512 Title: The role of the seagrass ‘Posidonia oceanica’ in underwater archaeological site formation : a comparative study of objects from Salina and Mellieħa Bays (Malta) Abstract: This research project explores the post-depositional alterations of late Roman ceramics recovered from two underwater archaeological sites in Malta: Salina Bay and the Mortar Wreck in Mellieħa Bay. The study documents significant degradation observed in ceramics, particularly changes in texture, coloration, and structural integrity, potentially linked to the environmental conditions created in part by Posidonia oceanica. Through a combination of non-destructive analytical methods, including hand specimen analysis, photography, microscopy, and Mohs hardness testing, this research investigated the chemical and microbial processes influencing ceramic preservation. Key findings suggest that certain ceramics from Salina Bay exhibit surface discoloration and loss of structural integrity, while those from Mellieħa Bay demonstrated more extensive degradation, including a widespread presence of chalky textures and loss of material integrity. The analysis proposes that microbial activity, fluctuating pH levels, and sulfate reduction in the environment may be responsible for the observed changes. This study highlighted the complex interplay between marine ecology and ceramic preservation, providing possible insights into the post-depositional effects of seagrass P. oceanica possibly have on submerged cultural heritage. This thesis also calls for further research into seagrass and microbial influences, geochemical interactions, and the development of conservation strategies to mitigate possible postdepositional alteration to submerged cultural heritage. Description: M.A.(Melit.) Wed, 01 Jan 2025 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/140512 2025-01-01T00:00:00Z