The oriental architecture present in the north-eastern cusp of Sicily is an expression of a mixed-race culture. This hybridization is evident in religious architecture. These buildings have the typological imprint of Catholic churches with Latin cross plans and towered facades, but preserve Arabic traces in the structure of the domes and connections, while also exhibiting Eastern Byzantine traditions in their masonry and rich decorations. The objective of this research is to automate the process of recognizing and segmenting bricks in wall structures to support the analysis of wall fabrics, a crucial task in archaeology and architectural restoration. Our approach processes a point cloud extracted from a facade to identify the wall texture. The results of segmentation can provide statistical information, documenting average brick size, mortar thickness, identification of homogeneous areas, and recognition of masonry sections built with different bricks. Alongside the numerical and abstract information, it is possible to identify the standard morphology of the brick, which also constitutes a sort of digital fingerprint of the church. The size of the bricks influences the geometry and layout of religious architecture. For example, the lateral facades are decorated with intertwined arches entirely composed of bricks. The spacing of the arches, their regularity, and the overall morphology are determined by the size and arrangement of the bricks. Bricks placed on the beds in different ways (stretcher, rowlock stretchers, or heading) determine the repetition or alteration of the geometric-formal modules reiterated in the elevations.
The Influence of Data Quality in Supervised ML-AI Classification Approaches for Historical Heritage
In recent years, the automatic segmentation and classification of digital survey data has been experimented with in built heritage studies. Despite the encouraging progress in the use of Machine and Deep Learning techniques, the semantic segmentation of point clouds is more complex, especially for the historic environment for which, due to the heterogeneity of shapes, it is more difficult to recognize homogeneous regions with similar properties. Given the need to process a large volume of already annotated data for the training and recognition of new scenes, the type and quality of the initial data play a fundamental role in the classification process, as they influence the subdivision into predefined categories that are not always consistent with a decomposition into architectural elements and sub-elements shared by the scientific community. This is an interpretative problem that already emerges from traditional manual labelling, which, being highly subjective, reduces the reproducibility of the results. The paper focuses on understanding to what extent the recognition of homogeneous regions is influenced by factors such as: manual labelling carried out by annotators with different specializations; density value of the point clouds; and type of data acquired depending on the acquisition sensor. These evaluations were conducted by employing the Random Forest algorithm on specific pre-processed point cloud datasets, with reference to the typology of the Franciscan cloister, in order to make the recognition flows more controlled and less ambiguous, aiming at an advancement towards more efficient modelling and management of the existing architectural heritage.
The Use of the Imagematching Software and Other AI Tools for the Automatic Recognition of Similar Images: Some Theoretical Considerations
The article discusses the new digital research methodologies to investigate the concept of image similarity, taking as a case study the Lyon16ci database project. Developed in collaboration with the Visual Geometry Group at the University of Oxford, this project investigates how AI-driven image recognition can enhance scholarly analysis of visual material in the humanities. The focus is on the use of VISE software, designed to automatically retrieve visually similar images based on geometric and compositional features. The article provides a critical evaluation of the strengths and limitations of this tool in the context of art historical and visual culture research. It discusses how VISE facilitates new interpretative approaches by uncovering visual relationships and how it can effectively enhance traditional comparative methods. The author provides an overview of the advantages and constraints of using the VISE AI software to automatically retrieve similar images, presenting some of the theoretical considerations and the research possibilities provided by image recognition tools. The Lyon16ci case offers insights into the broader potential of machine vision in redefining the scope and scale of such image-based humanities research.
Exploring Cistercian Abbeys: A Synergistic Approach of Architectural Analysis and Machine Learning
This paper presents an integrated methodology for the survey and semantic analysis of the Fossanova Abbey complex, combining architectural survey, laser scanning, UAV photogrammetry, LiDAR acquisition, and machine learning techniques for semantic segmentation of point clouds. The study investigates how supervised learning algorithms, particularly Random Forest, can support the classification and decomposition of complex architectural heritage datasets. The research also discusses the relationship between geometric interpretation, semantic annotation, and multiscale architectural representation, highlighting the potential of AI-assisted workflows for cultural heritage documentation and analysis.
Evaluation of Annotation Ambiguity in Common Supervised Machine Learning Classification Approaches for Cultural Heritage
The paper investigates the impact of annotation ambiguity on supervised machine learning classification processes applied to cultural heritage data. Focusing on semantic segmentation of 3D point clouds, the study highlights how manual annotations—used as training data—are inherently subjective and influenced by the annotator’s background, expertise, and interpretation of architectural elements. Through an experimental framework involving multiple annotators, the research quantifies variability in labeling using metrics such as Intersection over Union (IoU), revealing significant discrepancies in the definition of semantic classes (e.g., columns, arches, moldings). The work proposes integrating uncertainty-aware approaches, such as semantic maps, to encode annotation ambiguity and improve the robustness, interpretability, and interoperability of AI-based classification systems for heritage documentation.
Hybrid Construction of Knowledge Graph and Deep Learning Experiments for Notre-Dame De Paris’ Data
After the fire that destroyed part of the cathedral Notre-Dame de Paris, a working group specialized in digital data coordinated a scientific project that would allow the management of all the digital data produced by scientific research activi-ties along with restoration operations. The ERC advanced grant “nDame Heritage” project combines digital humanities with computer science and artificial intelli-gence to create a collaborative knowledge system that analyzes multiple views from different experts on the same cultural heritage objects. In this work, we designed a hybrid artificial intelligence workflow based on both knowledge graphs and deep learning models for semantic segmentation of 2D images. We show that this hybrid approach can help experts to process, integrate, and enrich Notre-Dame’s data.
AI for Archaeological Heritage Applications
Lo studio propone una metodologia basata sull’integrazione di algoritmi di intelligenza artificiale e algoritmi generativi per supportare la ricostruzione di manufatti archeologici frammentari. Attraverso tecniche di image generation (GAN, Transformer), semantic segmentation e modelli computazionali parametrici, il sistema consente di analizzare frammenti, riconoscerne l’appartenenza tipologica e generare ipotesi ricostruttive tridimensionali. L’approccio viene validato tramite un workflow iterativo che combina dataset visivi, classificazione geometrica e ottimizzazione tramite algoritmi genetici, con verifica finale da parte di esperti.
Artificial Intelligence for Space Weather Prediction
This paper reviews the application of artificial intelligence methods for space weather prediction, with a focus on solar flare forecasting. It contrasts physics-based and data-driven approaches, highlighting how machine learning models trained on large datasets of solar magnetograms and flare records can provide probabilistic predictions. While AI methods represent the current state-of-the-art, challenges remain in terms of data imbalance, feature selection, and model interpretability.
Hybrid AI-Based Annotations of the Urban Walls of Pisa for Stratigraphic Analyses
This paper proposes a hybrid methodology for the semantic annotation and stratigraphic analysis of architectural heritage, combining supervised machine learning techniques with photogrammetric 3D modeling. The research aims to support the interpretation of complex masonry structures by integrating 2D image-based classification with 3D spatial representations.
The workflow involves the acquisition of photogrammetric datasets, followed by supervised classification of images using a Random Forest algorithm trained on manually annotated samples. As illustrated in the workflow diagram (Fig. 2, p. 783), semantic information related to lithotypes and construction layers is first propagated across the entire image set and subsequently transferred to the 3D point cloud through 2D–3D reprojection. This process enables the creation of semantically enriched 3D models, preserving the relationship between geometric data and interpretative annotations.
Results, shown in the classification outputs (Figs. 4–6, pp. 786–788), demonstrate that the method effectively identifies different construction phases and material layers, particularly in cases with clear colorimetric variation. However, limitations arise in areas with homogeneous textures, where classification accuracy decreases. The study highlights the potential of hybrid AI-based annotation systems to enhance stratigraphic analysis and heritage documentation, while emphasizing the need to integrate additional geometric features to improve robustness.
The Role of Semi-Automatic Classification Techniques for Mapping Landscape Components. The Case Study of Tratturo Magno in Molise Region
This paper investigates the use of semi-automatic classification techniques applied to multispectral satellite imagery for the mapping and recognition of historical landscape structures. The research focuses on the Tratturo Magno, a traditional transhumance route, aiming to evaluate different image-processing approaches to detect its path and spatial influence within the territory.
The methodology integrates vegetation indices (NDVI, EVI), unsupervised clustering, and supervised machine learning classification (Random Forest), combined with GIS tools and Google Earth Engine for temporal and spatial analysis. Multitemporal Sentinel-2 imagery is analyzed to identify optimal seasonal conditions for feature detection, highlighting the tratturo as a linear green corridor during autumn and winter. Results show that supervised classification methods provide the most reliable identification, although challenges remain in distinguishing the tratturo from similar landscape elements. The study demonstrates the potential of AI-supported geospatial analysis to enhance landscape interpretation, while emphasizing the need for further refinement to achieve precise and unique feature extraction.