Heritage. 2024; 7(10):5428-5445., 2024 The introduction of generative AI has the potential to radically transform various fields of research, including archaeology. This study explores the potential of generative AI, specifically ChatGPT, in developing a computer application for analyzing aerial and satellite images to detect archaeological anomalies. The main focus was not on developing the application itself but on evaluating ChatGPT’s effectiveness as an IT assistant for humanistic researchers. Starting with a simple prompt to analyze a multispectral orthophoto, the application was developed through successive iterations, improved through continuous interactions with ChatGPT. Various technical and methodological challenges were addressed, leading to the creation of a functional application with multiple features, including various analysis methods and tools. This process demonstrated how the use of large language models (LLMs) can break down the barriers between humanities and computer science disciplines, enabling researchers without programming skills to develop complex applications in a short time.

Archaeological Prospection, 2024, Volume31, Issue3, July/September 2024, Pages 217-231 Archaeological aerial thermography has traditionally focused on bare ground terrain; however, recent developments in drone technology have prompted a reconsideration of thermal analysis on cultivated fields. This study investigates three different sites using drones equipped with thermal, RGB and multispectral sensors to identify archaeological anomalies. This research challenges the traditional focus of thermal cameras on vegetation-free terrains by investigating cultivated land, where the perceived temperature is influenced by evapotranspiration—a combination of soil evaporation and vegetation transpiration. While agricultural studies have emphasized the ability of thermal sensors to detect varying temperatures in irrigated vegetation, archaeology has mainly used multispectral sensors for vegetated land. The study shows that in wheat-covered fields, thermal analysis outperforms multispectral and RGB sensors in detecting anomalies associated with archaeological features. Unexpectedly, optimal anomaly detection occurs during mid-morning and mid-afternoon flights, challenging traditional ideas about the timing of thermal analysis. The research highlights the need for renewed interest in the use of thermal cameras for archaeological anomaly detection in cultivated fields. However, further comparative studies between thermal and multispectral analyses on different sites are essential to establish the wider effectiveness of thermal sensors. This study challenges established notions of archaeological aerial thermography and argues for a re-evaluation of sensor selection and flight timing to improve the detection of archaeological features in cultivated fields.

Proceedings, 96(1), 2024 During the Ph.D. project titled Flying off-site: new investigation methodologies for the analysis of historical landscapes, QGIS was used as a workspace for the archaeogeographical analysis of the territory of Castronovo di Sicilia (PA). The interaction between native applications and plug-ins developed by third parties showed that this software is the ideal environment for a complete archaeogeographical analysis, as it can integrate archaeological and geographical information of different types. The possibility of using a single software not only reduces research costs and time but also allows for new data to be obtained and a holistic approach to be applied to analyzed landscape.

Drone Systems and Applications Volume 12 , 2024 This study investigates the applicability of drone technology in examining Stracciacappe, a minor archaeological site through low-altitude aerial photography. Using multispectral and thermal sensors mounted on DJI Phantom Multispectral and DJI Mavic Enterprise Advanced drones, several flight missions were conducted in November 2020, May 2021, and April 2022. The effectiveness of analyzing multispectral and thermal raw images was limited by the area's irregular vegetation, which hindered the clear detection of archaeological anomalies. However, microtopographic analysis employing various visualization techniques revealed significant traces, aligning with the site's description found in numerous documentary sources. This includes the identification of two distinct areas within the castrum: the elevated cassarum and the burgus, along with potential traces of defensive structures within these areas. Drone analysis delineated a cassarum comprising a tower, palatium, and defensive walls, while the burgus seemed devoid of buildings, supporting the notion of a village primarily constructed with perishable materials. Thus, the study highlights the importance of using diverse sensor-based drone analyses to enhance archaeological investigations at minor sites.

Archeologia e Calcolatori 34.1, 2023 The area of Castronovo di Sicilia was analysed by integrating different methodologies. In terms of the road network, it was decided to compare information from traditional written sources, such as the Itinerarium Antonini and texts from the Arab geographer al-Idrisi, with the results of the Least-Cost Path Analysis (LCPA) conducted using the QGIS plugin ‘movecost’. The primary objective of this analysis was to evaluate how the centrality of the Castronovo area was determined by environmental factors that made it easily accessible along the main long-distance routes connecting the island. At the same time, the analysis aimed to highlight similarities and differences between the written sources and the LCPA results.

Nuove Tecnologie open source per la gestione dei beni, delle attività culturali e del turismo 16-17 Dicembre 2021, Sala della Fortuna, Museo Nazionale Etrusco Villa Giulia, Roma, 2022 Il campo dell’aerofotografia archeologica è stato rivoluzionato negli ultimi anni dall’introduzione dei droni. Recentemente, la miniaturizzazione dei sensori fotografici termici e multispettrali e la conseguente diminuzione di peso e costo, ha permesso la loro applicabilità sui droni, aprendo nuovissime potenzialità anche nel campo del telerilevamento a bassa quota. Nell’ambito del progetto di dottorato “Flying off-site: nuove metodologie di indagine per l’analisi dei paesaggi storici medievali”, è stato possibile analizzare lo stato dell’arte e testare una serie di nuovi droni commerciali termici e multispettrali, al fine di valutare il potenziale nell’individuazione di elementi archeologici non visibili in superficie.

In ArcheoFOSS XIV 2020. Proceedings of the 14th International Conference 15-17 October 2020, edited by J. Bogdani, R. Montalbano, and P. Rosati, 35–43. Archaeopress. In the first phase of the PhD project ‘Flying off-site. New methodologies for the analysis of historical landscape’ the main goal was to build a workflow to elaborate 3D models and orthophotos by thermographic images taken by drone. In line with the scientific literature outside the archaeological world, a first workflow was developed using proprietary software. The next step consisted in converting this workflow to use exclusively open-source software, aiming both at evaluating an effective possibility of an exclusively open workflow, and also at verifying the pros and cons of open-source solutions compared to proprietary software.

Gabriele Ciccone, Adel Khelifi, and Mark Altaweel Applied Sciences, 2021 Constant detection and monitoring of archaeological sites and objects have always been an important national goal for many countries. The early identification of changes is crucial to preventive conservation. Archaeologists have always considered using service drones to automate collecting data on and below the ground surface of archaeological sites, with cost and technical barriers being the main hurdles against the wide-scale deployment. Advances in thermal imaging, depth imaging, drones, and artificial intelligence have driven the cost down and improved the quality and volume of data collected and processed. This paper proposes an end-to-end framework for archaeological sites detection and monitoring using autonomous service drones. We mount RGB, depth, and thermal cameras on an autonomous drone for low-altitude data acquisition. To align and aggregate collected images, we propose two-stage multimodal depth-to-RGB and thermal-to-RGB mosaicking algorithms. We then apply detection algorithms to the stitched images to identify change regions and design a user interface to monitor these regions over time. Our results show we can create overlays of aligned thermal and depth data on RGB mosaics of archaeological sites. We tested our change detection algorithm and found it has a root mean square error of 0.04. To validate the proposed framework, we tested our thermal image stitching pipeline against state-of-the-art commercial software. We cost-effectively replicated its functionality while adding a new depth-based modality and created a user interface for temporally monitoring changes in multimodal views of archaeological sites.