Abstract

Detecting surface potsherds using low-altitude remote sensing is challenging due to severe class imbalance and limited training data. This study develops and validates a semi-automatic detection methodology that adapts threshold-optimized boosting classifiers (AdaBoost, XGBoost) to maximize ceramic detection recall under extreme class imbalance in the Western Megaris archeological landscape, Greece. Models were trained on only 15% of the available data to simulate realistic field conditions. Evaluation emphasized recall-oriented metrics (precision, recall, F1-score, AUC) for the minority class, addressing the accuracy paradox where high overall accuracy masks poor rare-class performance. Threshold optimization enabled AdaBoost and XGBoost to achieve substantially improved recall compared to baseline methods, with detection-to-ground-truth ratios of 2.5 and 3.2, respectively, reflecting deliberate prioritization of recall over precision for exploratory survey purposes. The results demonstrate that this methodological framework provides archeologically interpretable screening tools for identifying high-probability ceramic locations, supporting more efficient field survey design and heritage documentation workflows in Mediterranean landscapes.

Argyrou, A.; Fasson, F.; Farinetti, E.; Papakonstantinou, A.; Alexakis, D.D.; Agapiou, A. Learning from the Rare: Overcoming Class Imbalance in Archaeological Object Detection with Boosting Methods. Heritage 2026, 9, 99. https://doi.org/10.3390/heritage9030099

The presentation took place on 11 and 12 February 2026, at the premises of the Laboratory of Spatial Analysis, GIS and Thematic Mapping, where the CONNECTING project was presented to postgraduate students and research staff. The lecture provided a comprehensive overview of the project, with particular emphasis on the technological architecture of the Cloud Data Centre. It also highlighted the methodologies applied for the management and visualization of 2D and 3D geospatial datasets, as well as the rationale behind key system design decisions, including aspects of data security, interoperability, and performance optimization—especially in relation to sensitive cultural heritage geospatial information relevant to spatial planning and regional development.

The session contributed significantly to the enhancement of participants’ knowledge and fostered constructive academic exchange on emerging approaches in geospatial data management and cultural heritage preservation.

Abstract:  Chatbots have emerged as a promising interface for facilitating access to complex datasets, allowing users to pose questions in natural language rather than relying on specialized technical workflows. At the same time, remote sensing has transformed archaeological practice by producing vast amounts of imagery from LiDAR, drones, and satellites. While these advances have created unprecedented opportunities for discovery, they also pose significant challenges due to the scale, heterogeneity, and interpretative demands of the data. In related scientific domains, multimodal conversational systems capable of integrating natural language interaction with image-based analysis have advanced rapidly, supported by a growing body of survey and review literature documenting their architectures, datasets, and applications across multiple fields. By contrast, archaeological applications of chatbots remain limited to text-based prototypes, primarily focused on education, cultural heritage mediation or archival search. This review synthesizes the historical development of chatbots, examines their current use in remote sensing, and evaluates the barriers to adapting such systems for archaeology. Four major challenges are identified: data scale and heterogeneity, scarcity of training datasets, computational costs, and uncertainties around usability and adoption. By comparing experiences across domains, this review highlights both the opportunities and the limitations of integrating conversational AI into archaeological workflows. The central conclusion is that domain-specific adaptation is essential if multimodal chatbots are to become effective analytical partners in archaeology.

Melillos, N.; Agapiou, A. AI Chatbots and Remote Sensing Archaeology: Current Landscape, Technical Barriers, and Future Directions. Heritage 2026, 9, 32. https://doi.org/10.3390/heritage9010032