The Cave of Altamira (Spain), a UNESCO World Heritage site, contains one of the most fragile and inaccessible Paleolithic rock-art environments in Europe, where geomatics documentation is constrained not only by severe spatial, lighting and safety limitations but also by conservation-driven restrictions on time, access and operational procedures. This study applies a confined-space UAV equipped with LiDAR-based SLAM navigation to document and assess the stability of the vertical rock wall leading to “La Hoya” Hall, a structurally sensitive sector of the cave. Twelve autonomous and assisted flights were conducted, generating dense LiDAR point clouds and video sequences processed through videogrammetry to produce high-resolution 3D meshes. A Mask R-CNN deep learning model was trained on manually segmented images to explore automated crack detection under variable illumination and viewing conditions. The results reveal active fractures, overhanging blocks and sediment accumulations located on inaccessible ledges, demonstrating the capacity of UAV-SLAM workflows to overcome the limitations of traditional surveys in confined subterranean environments. All datasets were integrated into the DiGHER digital twin platform, enabling traceable storage, multitemporal comparison, and collaborative annotation. Overall, the study demonstrates the feasibility of combining UAV-based SLAM mapping, videogrammetry and deep learning segmentation as a reproducible baseline workflow to inform preventive conservation and future multitemporal monitoring in Paleolithic caves and similarly constrained cultural heritage contexts.

When researchers sign an article, they reference all the institutions they belong to, writing one or more affiliations containing them. Researchers sign in many different ways, and different journals also have varying standards in this regard. In this article we will focus on the Institution Name Disambiguation (IND) problem, also known as Organization Name Disambiguation (OND). Common issues associated to IND problem arise because researchers may write the name of the institution differently in various publications, and different researchers from the same institution will certainly write it differently as well. On the other hand, a researcher may be affiliated with several centers simultaneously or at different stages of their professional life, which introduces the factor of time as an additional variable to consider. As a result, analyzing and linking scientific work from different areas for various institutions is challenging. Databases like Web of Science collect articles from various journals across different fields. In this article, we will propose a method named 3 Steps Affiliation (3SA) based on, firstly, preprocessing the information, secondly, candidate extraction via localization and classification type of the institutions and, thirdly, on entity linking to extract the institutions from affiliations downloaded from Web of Science articles using an edit distance. We use a world-wide open source database with more than 100k institutions to solve the Institution Name Disambiguation problem. We show that the proposed method has a state-of-art performance by comparing it with other methods. Additionally, we evaluate the impact of different edit distance metrics within our method to identify which yields the best results.

The cave of Altamira (Spain), a UNESCO World Heritage site, contains one of the most fragile and inaccessible Paleolithic rock-art environments in Europe, where conventional geomatics workflows are limited by severe spatial, lighting, and safety constraints. This study applies a confined-space UAV equipped with LiDAR-based SLAM navigation to document and assess the stability of the vertical rock wall leading to “La Hoya” Hall, a structurally sensitive sector of the cave. Twelve autonomous and assisted flights were conducted, generating dense LiDAR point clouds and video sequences processed through videogrammetry to produce high-resolution 3D meshes. A Mask R-CNN deep learning model was trained using manually segmented images to automatically detect cracks under variable illumination and viewing conditions. The results reveal active fractures, overhanging blocks, and sediment accumulations located on inaccessible ledges, demonstrating the capacity of UAV-SLAM workflows to overcome the limitations of traditional surveys in confined subterranean environments. All datasets were integrated into the DiGHER digital twin platform, enabling long-term storage, multitemporal comparison, and collaborative annotation. The study confirms the feasibility of UAV-based SLAM mapping combined with videogrammetry and deep learning segmentation as a robust approach for structural assessment and preventive conservation in Paleolithic caves and similarly constrained cultural heritage contexts.