The use of unmanned aerial vehicles (UAVs, also known as drones or RPA) in archaeology has expanded significantly over the last twenty years. Improvements in terms of the reliability, size, and manageability of these aircraft have been largely complemented by the high resolution and spectral bands provided by the sensors of the different cameras that can be incorporated into their structure. If we add to this the functionalities and improvements that photogrammetry programs have been experiencing in recent years, we can conclude that there has been a qualitative leap in the possibilities, not only of geometric documentation and in the presentation of the archaeological data, but in the incorporation of non-intrusive high-resolution analytics. The work that we present here gives a sample of the possibilities of both geometric documentation, creation of 3D models, their subsequent printing with different materials, and techniques to finally show a series of analytics from images with NGB (Nir + Green + Blue), Red Edge, and Thermographic cameras applied to various archaeological sites in which our team has been working since 2013, such as Clunia (Peñalba de Castro, Burgos), Puig Rom (Roses), Vilanera (L’Escala, Girona), and Cosa (Ansedonia, Italy). All of them correspond to different chronological periods as well as to varied geographical and morphological environments, which will lead us to propose the search for adequate solutions for each of the environments. In the discussions, we will propose the lines of research to be followed in a project of these characteristics, as well as some results that can already be viewed.

This article presents the first results obtained from the use of high-resolution images from the SAR-X sensor of the PAZ satellite platform. These are in result of the application of various radar image-treatment techniques, with which we wanted to carry out a non-invasive exploration of areas of the archaeological site of Clunia (Burgos, Spain). These areas were analyzed and contrasted with other sources from high-resolution multispectral images (TripleSat), or from digital surface models obtained from Laser Imaging Detection and Ranging (LiDAR) data from the National Plan for Aerial Orthophotography (PNOA), and treated with image enhancement functions (Relief Visualization Tools (RVT)). Moreover, they were compared with multispectral images created from the Infrared Red Blue (IRRB) data contained in the same LiDAR points.

Highlights: Some archaeological results obtained using SAR-X images received through the PAZ satellite and applied to a part of what was called Ager Cosanus are shown in this article. The study has been completed with the analysis of multispectral images TripleSAT and Sentinel-2A and the historical aerial photos from 1944 and 1954. The possibilities of using PAZ images treated multi-temporally as a high-resolution panchromatic image applicable to multispectral optical images of the type Sentinel-2 were tested. Some archaeological results are shown in this article, which have been generated from the use of Synthetic Aperture Radar (SAR)-X images obtained from the PAZ satellite and applied to part of what was called Ager Cosanus, that is, the territory of the city of Cosa, which was one of the first maritime colonies of Rome in the heart of Etruscan territory. Our study has been carried out mainly based on previous works in which a set of images was used to improve the quality of the resulting image, reducing the noise caused by the speckle of the radar images and maintaining the quality of the spatial resolution that can be obtained from these images (1.25 m/pixel). More specifically, a set of images obtained between 2019 and 2021 was used. The study has been completed with the analysis of multispectral images TripleSAT and Sentinel-2A, the historical aerial photos taken from 1944 and 1954, and the use of the historical cadastre of Tuscany, prepared at the beginning of the 19th century. As an addition, the Digital Terrain Model (DTM) Light Detection And Ranging (LiDAR) of the Region of Tuscany was used, on which various functions of the Relief Visualization Tool (RVT) programme have been applied, complementing or contrasting the results. It can be confirmed that the multi-temporal treatment of SAR PAZ images provides better results than an individualised analysis of the image. Finally, it is of great interest to verify the results of studies using new technologies, where it was previously possible to resort only to prospecting on the ground and to analogical aerial photography in black and white. In this case, the Sinistra Decumano I (SDI) structure was seen, which Castagnoli observed in the aerial photography, but of which he only located materials on the ground and it was visualised both in individualised PAZ images and in Sentinel-2.

El inesperado desembarco de la inteligencia artificial (IA) generativa en 2023 provocó un movimiento telúrico que ha afectado a todos los ámbitos científicos, docentes y laborales. Este trabajo pretende valorar las aportaciones más recientes de la modelización 3D a través de la IA generativa, sobre todo en un aspecto para el que puede tener un gran potencial, aquel patrimonio destruido del que solo se disponga de unas pocas fotos o ilustraciones. Es decir, un patrimonio perdido, por la incansable evolución-involución urbanística de cualquier ciudad o por la destrucción provocada por los conflictos bélicos, y que han dejado tan solo una escasa documentación gráfica. El artículo pretende evaluar si estamos ante las puertas de un nuevo paradigma en la documentación geométrica que supere en este aspecto los métodos “clásicos”. Un nuevo paradigma que sería aplicable a situaciones en las que no era posible la construcción “tradicional” de modelos 3D, reservada en primera instancia al tratamiento con escáner 3D o a los algoritmos de Structure From Motion (SfM)/Multi-View Stereo (MVS), y a las más recientes aportaciones de los Neural Radiance Fields (NERF). Para realizar la mencionada evaluación se han tomado algunos casos de estudio a los cuales se les han aplicado programas de IA generativa como Google Gemini 2.5 Flash Image y Nano Banana, combinado con Hitem3D, Archsynth, Meshy o Hexagen. El estudio ha incluido, aplicándolo al caso de un elemento patrimonial existente, un análisis de distancias entre superficies mediante funciones del programa CloudCompare, para determinar el nivel de precisión y fiabilidad que podrían proporcionar estos modelos. Asimismo, se propone una adaptación, a partir del uso de la IA generativa, de los procedimientos de documentación que permiten identificar los niveles de autenticidad del modelo 3D generado, en consonancia con los aspectos tratados respecto a esta cuestión en la Carta de Londres y los Principios de Sevilla.