Articles by Paolo Rosati

Detecting archaeological features from satellite images is an increasingly vital tool in archaeology, offering a non-invasive means to discover and protect ancient structures. Among these, nuraghes, which are tower-shaped stone structures from the Bronze Age unique to Sardinia (Italy), present a significant challenge due to their varied sizes, forms, and environmental contexts. This paper introduces a pioneering approach employing an Artificial Intelligence (AI) driven method for detecting nuraghes in satellite images, specifically employing a Deep Learning (DL) model based on Vision Transformers (ViT), which is an advanced neural network architecture that excels in processing image data. The system, called ‘Artificial Intelligence Operator for Heritage’ (AIOH), is trained on custom data retrieved for this work: the dataset, NuragAI, includes thousands of satellite images from Google Maps with manually annotated nuraghe presence. It is designed to train the model to identify subtle and complex characteristics of nuraghe structures. The effectiveness of this approach was quantitatively assessed through extensive validation, with very high results on the training and testing set and interesting results also on data, detecting nuraghes in various terrains and under different lighting conditions. A preliminary on-site field campaign, to test results, was also carried out, confirming the model efficiency.

The institutional goal of studying and mapping archaeological potential in SITAR in recent years has been to create an efficient tool to support urban planning and cultural heritage management: The Archaeological Potential Map of Rome. The Soprintendenza of Rome plays a key role in this effort, being responsible for the safeguarding and promotion of the city’s archaeological heritage. By developing a robust model of archaeological potential, the Soprintendenza can better anticipate and mitigate the impact of construction and development projects on archaeological sites. This proactive approach ensures that significant archaeological resources are identified and preserved before they are damaged or destroyed. The tool will facilitate informed decision-making in urban planning, helping to balance the needs of modern development with the preservation of historical sites. Moreover, it will support the regulatory framework that mandates archaeological assessments in high-potential areas, rationalisation of administrative processes and improving compliance with heritage protection regulations. Overall, the creation of an efficient archaeological potential model by the Soprintendenza of Rome underlines the commitment to preserving the city’s cultural heritage while accommodating its continuous urban evolution.

The purpose of the paper is to introduce a QGIS plugin named ArcheoloGIS. It is developed in PYQGIS and tested by the community of Una Quantum Inc. (Italy). It consists of a decorator algorithm named Tabula Peutingeriana, that outputs points at a regular distance, every one Roman mile, along a given path. The article shows its use, the construction of a possible dataset and its evolution, as well as a case study of its application.

This article offers an example for a quick and smart procedure for geo-referencing archaeological stratigraphy and managing it digitally in a GIS environment, through the open source software QGIS and pyArchInit. Specifically, the authors propose two ways of obtaining a geo-referenced survey of the archaeological features identified: 1) a handmade manual survey carried out with triangulation measurements; 2) a digital survey through Structure from Motion algorithms.

The project involves the setting up of a virtual tour for the Museum of the Origins, namely the Museum of Prehistory and Protohistory at the Sapienza University of Rome Museum Pole. The virtual tour has been developed through open source technologies: a low-cost approach was pursued to provide a work-flow example for other museum sites wishing to acquire this promotion tool. The final product was designed both for museum use (in-site) and for a web spread (web-site).