Assessing the condition of artworks is a critical step in cultural heritage conservation that traditionally involves manual damage mapping, which is time-consuming and reliant on expert input. This study, conducted within the ChemiNova project, explores the automation of edge detection using both classical image processing techniques (Canny, Sobel, and Laplacian) and a deep learning model (DexiNed). The methodology integrates interdisciplinary collaboration between conservation professionals and computer scientists, applying these algorithms to artworks affected by environmental damage, including flooding. Preprocessing and post-processing techniques were used to enhance detection accuracy and reduce noise. The results show that while traditional methods often yield higher precision and recall scores, they are also sensitive to texture and contrast variations. These findings suggest that automated edge detection can support conservation efforts by streamlining condition assessments and improving documentation.

A global survey was conducted in 2022 with the aim of identifying what professionals in the cultural and creative industries (CCIs) expect from collection-based organisations (CBOs) and what their contribution to their preservation, management, and/or use could be. A total of 151 responses were obtained from the five UNESCO regions, the majority of whom were between 31 and 50 years of age, which is convenient when analysing the responses as they are active and belong to different creative sectors. The results are very positive, demonstrating that museum collections are didactic materials through which design students and CCI stakeholders learn to approach the past critically and creatively, create meaning, and co-create their future heritage. Likewise, the alliance of CBOs with the SDGs represents a key tool to experiment with and call for action to achieve the goals of the 2030 Agenda. The results enable CCIs to identify and bridge gaps in their role as creative developers, strengthening their collaboration with heritage organisations. This paper aims to show the results of the survey and the first actions aimed at developing meaningful, inclusive arts- and culture-based interventions to support sustainable development.

The Gender Equality Index allows analyzing and measuring the progress of gender equality in the EU and, therefore, the relation between men and women in different domains, such as Health, Work or Money. Even though the European Institute for Gender Equality has created some visualizations that are useful to look at the data, this website does not manage to make graphs that allow for observing the spatiotemporal variable. This article enhances the understanding of the index with spatiotemporal visualizations, such as cartograms, heatmaps and choropleth maps, and some strategies focusing on analyzing the evolution of the countries over the years in an open-access environment. The results show how the application created may be used as an addition to the EIGE website.

The digitisation of cultural heritage has transformed how GLAM (Galleries, Libraries, Archives and Museums) institutions manage and share collections. Digital catalogues are indispensable for documenting and granting public access to cultural assets. However, integrating spatial data remains challenging due to the ambiguity, uncertainty, granularity, and heterogeneity of historical data. This study addresses these issues through a case study on the Museo de América’s “Place of Provenance” data, proposing a methodology for data cleaning and evaluating geocoding accuracy using Nominatim, ArcGIS, and GeoNames APIs. We assess these APIs by quantifying geocoding errors through a “balance sheet” method, identifying instances of over-representation, under-representation, or neutral results for geographical regions. The effectiveness of each API is analysed using confusion matrices and interactive cartograms, offering insights into misallocations. Our findings reveal varying accuracy among the APIs in processing heterogeneous historical spatial data. Nominatim achieved a 40.91% neutral result in correctly geocoding countries, underscoring challenges in spatial data representation. This research provides valuable methodological experiences and insights for researchers and GLAM institutions working with cultural heritage datasets. By enhancing spatial dispersion visualisation, this work contributes to understanding cultural circulations and historical patterns. This interdisciplinary work was developed as part of the ClioViz project, integrating Data Science, data Visualisation, and art history.