COMPUTER SCIENCE APPLIED TO CULTURAL HERITAGE

This course contributes to the educational objectives of the Master’s Degree in Conservation Science and Technology for Cultural Heritage by providing students with theoretical knowledge and applied digital skills for the study, documentation, diagnostics, preservation, management and valorization of cultural heritage.

It is designed for students who will work in interdisciplinary contexts involving conservators, conservation scientists, museums, archives, libraries, archaeological institutions, research laboratories, public administrations, private companies, and digital-heritage professionals. It provides the methodological and practical foundations needed to use computer science responsibly and effectively in cultural heritage projects.

In particular, the course supports the program’s objectives by:
- training students to manage and analyze scientific and cultural-heritage data,
- document objects, sites, materials, and conservation processes through digital tools,
- design reproducible computational workflows,
- understand metadata and interoperability standards,
- use image processing, databases, GIS, 3D documentation, and artificial intelligence in heritage contexts,
- and critically evaluate the ethical, legal, and scientific implications of digital technologies.

The course strengthens students’ ability to contribute to laboratory work, in situ research, internships and thesis projects by transforming data and digital documentation into reliable, reusable and professionally meaningful knowledge. It also prepares students to communicate computational results to both specialist and non-specialist stakeholders involved in cultural heritage conservation and management.

By the end of the course, students will be able to:
- Understand the role of computer science in conservation science, cultural heritage diagnostics, preventive conservation, heritage management, and public communication.
- Identify and interpret the main types of cultural-heritage data, including tabular data, images, spectral data, spatial data, 3D data, textual records, metadata records and linked data.
- Understand the fundamentals of metadata, interoperability, image processing, GIS, 3D documentation, and machine learning as applied to cultural heritage.
- Design basic metadata structures and reproducible digital workflows for cultural-heritage objects, samples, analytical results, images and conservation records.
- Apply basic image-processing, spatial, 3D, and data-analysis techniques to support documentation, diagnostics, monitoring, risk assessment, and interpretation of cultural heritage.
- Test simple artificial intelligence or machine-learning approaches and critically evaluate their performance, limitations and suitability for cultural-heritage applications.
- Choose appropriate digital methods according to the type of heritage problem, available data, scientific objectives, professional constraints, and expected users.
- Present data visualizations, maps, image analyses, database models, metadata structures or digital prototypes in a professional and critically informed way.

- No advanced programming knowledge is required. However, students are expected to have basic computer literacy and to be willing to work with digital tools, datasets, and computational notebooks.
- Students are expected to understand written English in order to use slides, scientific articles, technical documentation, and software manuals provided during the course.
- Students with no previous coding experience will be supported through guided exercises, templates, and introductory materials.

The course program is organized around theoretical concepts and applied laboratories. The contents emphasize critical understanding, interdisciplinary application, research-oriented workflows, and professional relevance.
The main content of the course is the following:
1. Introduction to computer science for cultural heritage.
2. Data management and reproducible workflows.
3. Metadata, standards, and interoperability.
4. Databases and information modeling.
5. Data analysis and visualization for heritage science.
6. Image processing for cultural heritage.
7. 3D documentation and digital models.
8. Geographic Information Systems and spatial analysis for heritage documentation and risk assessment.
9. Machine learning and artificial intelligence in cultural heritage.
10. Digital preservation and repositories.
11. Human-centered digital heritage.

Mandatory texts:
1. Watrall, E., ed., Digital Heritage and Archaeology in Practice: Data, Ethics, and Professionalism, University Press of Florida, 2022, DOI: 10.5744/florida/9780813069302.001.0001, selected chapters provided by the instructor.
2. CIDOC CRM Special Interest Group, The CIDOC Conceptual Reference Model, selected sections provided by the instructor.
3. International Image Interoperability Framework Consortium, IIIF Documentation, selected sections provided by the instructor.
4. UNESCO, Recommendation on the Ethics of Artificial Intelligence, UNESCO, 2021/2022, selected sections relevant to cultural heritage and research practice.

Supplementary texts:
1. Ronchi, A. M., ECulture: Cultural Content in the Digital Age, Springer-Verlag Berlin Heidelberg, 2009, DOI: 10.1007/978-3-540-75276-9.
2. Li, Z., Drew, M. S. and Liu, J., Fundamentals of Multimedia, Springer International Publishing, 2014, DOI: 10.1007/978-3-319-05290-8.
3. Lake, P. and Crowther, P., Concise Guide to Databases, Springer London, 2013, DOI: 10.1007/978-1-4471-5601-7.
4. Remondino, F. and Campana, S., eds., 3D Recording and Modelling in Archaeology and Cultural Heritage: Theory and Best Practices, Archaeopress, 2014.
5. Gonzalez, R. C. and Woods, R. E., Digital Image Processing, Pearson, latest available edition, selected sections.
6. Gilliland, A. J., “Setting the Stage”, in Introduction to Metadata, Getty Research Institute, latest available edition.
7. QGIS Project, QGIS Training Manual, available online.
8. OpenRefine, OpenRefine Documentation, available online.
9. The Carpentries, Software Carpentry lessons on Python, Git and reproducible research, available online.
10 . Selected recent scientific articles and case studies on artificial intelligence, GIS, 3D documentation, digital preservation, image processing and data management in cultural heritage, provided by the instructor during the course.

Learning will be assessed through practical activities and laboratory work developed during the course, as well as a final written exam.
The assessment is designed to verify both the theoretical understanding of the course content and the ability to apply computer science methods to cultural heritage problems.

1. Practical activities and laboratories (30 %)
During the course, students will complete practical activities and laboratory exercises related to the program's main topics. These may include data management, metadata design, database modeling, data visualization, image processing, Geographic Information Systems (GIS) or 3D documentation, and basic evaluation of artificial intelligence or machine-learning approaches.
These activities assess the student’s ability to apply the methods introduced in class, work with cultural-heritage data and digital tools, document procedures, interpret results, and recognize the limitations of computational methods.

2. Final written exam (70 %)
The final written exam assesses the student’s knowledge and understanding of the theoretical, methodological and applied contents of the course.
The exam may include open questions, short theoretical questions, interpretation of practical cases, discussion of digital workflows, critical evaluation of methods, and problem-solving exercises related to cultural heritage data, metadata, image processing, databases, GIS, 3D documentation, digital preservation, and artificial intelligence.
The final written exam verifies the student’s ability to explain the role of computer science in cultural heritage, choose appropriate digital methods for specific heritage problems, critically assess the limitations and implications of digital technologies, and communicate computational approaches using appropriate terminology.

The final grade will be calculated as the weighted average of the practical activities and laboratories and the final written exam.

written

The instructor is responsible for ensuring the authenticity and originality of all examinations and coursework. In cases of suspected academic misconduct, an additional on-site assessment may be required during the exams, which may differ from the standard format.

Grades will be assigned according to the following criteria:
- Scores in the 18–22 range will be awarded when the student demonstrates sufficient knowledge of the main topics of the course and sufficient ability to apply basic digital methods to cultural-heritage data. The work is understandable but may show limited autonomy, partial documentation, weak interpretation, or limited critical awareness of methodological and ethical issues.
- Scores in the 23-26 range will be awarded when the student demonstrates good knowledge of the course topics and adequate ability to apply digital methods to cultural-heritage problems. The work is generally well-organized and well-documented, with a fair interpretation of the results and an adequate use of technical terminology. Some aspects of reproducibility, critical discussion, or professional relevance may remain incomplete.
- Scores in the 27-30 range will be awarded when the student demonstrates very good or excellent knowledge of the course topics and strong ability to apply computational methods to cultural-heritage problems. The work is well structured, reproducible, clearly documented, and critically interpreted. The student shows good or excellent judgment in selecting methods, assessing limitations, and communicating results to specialist and non-specialist audiences.
- 30 cum laude will be awarded when the student demonstrates excellent mastery of theoretical and practical content, outstanding autonomy, rigorous documentation, strong critical judgment, high-quality communication, and an original or particularly professional application of computer science to cultural heritage.

The course combines lectures, applied demonstrations, computer laboratories, case-study discussions, supervised work, and student presentations.
Lectures introduce the theoretical and methodological foundations of computer science applied to cultural heritage. Laboratory sessions allow students to apply these concepts to realistic heritage datasets and digital materials. Case-study discussions connect computational tools to conservation science, diagnostics, documentation, preventive conservation, museum and archive practice, and heritage management.
The teaching approach is strongly practical and research-oriented. Students will work with open-source or widely accessible tools whenever possible, including Python, Jupyter notebooks, OpenRefine, QGIS, ImageJ/Fiji, SQLite, Git or equivalent version-control systems, and selected 3D or image-analysis tools.
Course materials, datasets, instructions, examples, self-study resources, and assignment templates will be provided through the Moodle e-learning platform. Students are expected to use Moodle regularly.

Students are encouraged to connect the practical activities and laboratory exercises with topics, datasets, or case studies from other courses, laboratory experiences, internships, or thesis preparation, whenever possible and appropriate.
The course prioritizes open-source, sustainable, and transferable tools so that students can continue using them after the course in research, conservation laboratories, museums, archives, public institutions, private companies, or doctoral studies.
When specific software is required, installation instructions will be provided in advance. Alternative arrangements will be discussed if technical constraints arise.
Responsible use of artificial intelligence tools is allowed only when explicitly declared and critically documented. AI tools may support coding, data exploration, language editing or prototyping, but students remain fully responsible for the accuracy, originality, interpretation and ethical acceptability of their work. Undeclared or misleading use of AI tools is not acceptable.

This subject deals with topics related to the macro-area "Cities, infrastructure and social capital" and contributes to the achievement of one or more goals of U. N. Agenda for Sustainable Development