Affiliation:
1. History, Human Sciences and Education, University of Sassari
2. Cultural Heritage, University of Padova
3. Classical Archaeology, University of Augsburg
Abstract
Abstract
This chapter will focus on state-of-the-art applications of remote sensing and Artificial Intelligence (AI) for the archaeological investigation of the mountain environment. It will provide introductory knowledge on the most relevant passive and active sensors mounted on drone, aerial, and satellite platforms. Particularly, the chapter will consider visible RGB photography, multi- and hyperspectral imaging, LiDAR data and visualizations, and Synthetic Aperture Radar. After a general introduction on the principles of earth observation, the major challenges of its application in montane regions will be thoroughly discussed, including high gradients and rugged morphology, dense afforestation, remoteness, weather conditions, and climate change. Moreover, a general overview and critical assessment of automated image-classification techniques and AI approaches employed in mountain archaeology will be provided. By scrutinizing these methodologies, the chapter aims to discern the most promising trends that hold significant potential for shaping the future of archaeological investigations in mountainous terrains. Through this exploration, readers will gain insights into the evolving synergy between remote sensing, AI, and mountain archaeology, paving the way for advancements and innovations in this interdisciplinary field.
Reference107 articles.
1. Satellite Image Classification Methods and Techniques: A Review;International Journal of Computer Applications,2015
2. Landscape and Biocultural Diversity;Biodiversity and Conservation,2015
3. ARCTIS—A MATLAB® Toolbox for Archaeological Imaging Spectroscopy;Remote Sensing,2014
4. Synthetic Aperture Radar Interferometry;Inverse Problems,1998
5. Besold, Tarek R., Artur d’Avila Garcez, Sebastian Bader, Howard Bowman, Pedro Domingos, Pascal Hitzler, et al. 2021. ‘Neural-Symbolic Learning and Reasoning: A Survey and Interpretation’. In Neuro-Symbolic Artificial Intelligence: The State of the Art. Mantova: SAP. https://doi.org/10.3233/FAIA210348.