Artificial Intelligence and Ontologies for the Management of Heritage Digital Twins Data

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The article presents a study on the potential of artificial intelligence in support of Heritage Digital Twins, based on extensive semantic knowledge graphs and empowered by ontologies. This perspective is presented as the future of data-driven cultural digital twin systems and, consequently, as a significant advancement in the field of cultural heritage data management. In this sense, the study is developed by extending, with new classes and properties, the Reactive Heritage Digital Twin Ontology (RHDTO), a model previously introduced by the researchers. Therefore, the article is particularly relevant because it presents an original study resulting from an investigative trajectory that is also demonstrated in this work through a case study. Furthermore, the text is well structured and explanatory, as it presents a relevant theoretical and conceptual basis for understanding not only the research itself, but also this field of study. Thus, the work is particularly valuable for facing the complexities and challenges of what it also signals as an emerging paradigm called the Cognitive Digital Twin associated with the field of Cultural Heritage.

For a broader appreciation of the research carried out, especially the applied part, it might be interesting to provide more details about the case study, especially the results of the knowledge extraction process described (p. 16-17, lines 763-767) and the processes outlined in the ontological representation (p. 18-19, lines 841-851). For example, to discuss the difficulties encountered in these processes and the ways to overcome them. In order to motivate even more interest in following these studies, the future perspectives for the continuation of the research could perhaps be spelled out a little more (p. 19, lines 876-889).

Author Response

Dear Reviewer 1,

Thank you very much, we sincerely appreciate the time and effort you dedicated to reviewing our manuscript and for offering thoughtful and constructive feedback. Your comments have greatly contributed to enhancing the clarity and overall quality of our work. Please, find the detailed responses to your suggestions below, and the corresponding revisions/corrections in track changes in the re-submitted file.

Comments 1: For a broader appreciation of the research carried out, especially the applied part, it might be interesting to provide more details about the case study, especially the results of the knowledge extraction process described (p. 16-17, lines 763-767) and the processes outlined in the ontological representation (p. 18-19, lines 841-851). For example, to discuss the difficulties encountered in these processes and the ways to overcome them.

Response 1: Thank you so much for the thoughtful suggestion, which has helped us clarify key aspects of our work. We have expanded section 7.1 (pp. 16-17, lines 836-862 in the revised version of the paper) to provide further details on the case study, including hints on some preliminary tests carried out to perform knowledge extraction and the implementation of the ontological representation processes. Additionally, we now discuss some of the challenges faced during these steps and solutions applied to address them.

Comments 2: In order to motivate even more interest in following these studies, the future perspectives for the continuation of the research could perhaps be spelled out a little more (p. 19, lines 876-889).

Response 2: We also thank you for this valuable suggestion, which has allowed us to better outline the future directions of our research. We extended the Conclusions (p. 20, lines 981-996 in the revised version of the paper) to provide a more detailed description of the planned activities of the next research period and future work for testing and training custom AI systems to further enhance their performance and efficiency.
 

 

Reviewer 2 Report

Comments and Suggestions for Authors

This paper provides an exploration of integrating AI and ontologies within the framework of Heritage Digital Twins, emphasizing their role in cultural heritage management. It analyses the potential of AI-enhanced digital twins for data analysis, predictive modeling, and decision-making, supported by detailed descriptions of the RHDTO ontology and its extensions. The inclusion of a case study illustrates practical applications. While the content is well-structured and insightful, minor grammatical issues and occasional verbosity slightly detract from its clarity. Overall, it is a valuable contribution to advancing digital heritage preservation.

Minor issues to be addressed before publication follow:

- On page 11 the sentence "...learning from data and adapting to new conditions while making informed." is incomplete...possibly needs the word  "decisions."

- On page 13 in the description of "HP21 relies on" the verb "models" should be "model".

- On page 14 in the sentence "designed and created in the late 13th century by Arnolfo di Cambio, a notable Italian architect and sculptor, to serves as a symbol of the city's civic power." the correct verb should never be "to serve". 

- On page 17 the sentence "to analyse and classifying seismic events according to their intensity and distance." should change to "to analyze and classify seismic events...."

- There is an issue in the Language consistency as the text transitions from British to American English. Please go through the whole document and correct the English usage.

Conclusion

The paper’s contributions, while relevant, valuable and meaningful, are primarily evolutionary rather than revolutionary. Its novelty lies in the incremental refinement and extension of the existing RHDTO ontology to incorporate AI components, alongside a practical demonstration of their applicability through a cultural heritage case study. The conceptual proposal of Cognitive Digital Twins (CDTs) although forward-looking, it remains undeveloped in this work. The paper’s value lies in synthesizing AI, ontologies, and digital twins for cultural heritage management, providing a solid framework for future advancements rather than introducing fundamentally new theories or technologies. Nevertheless, since incremental advances like these are critical in scientific research the value of this paper remains significantly high.

Author Response

Dear Reviewer 2,
        
Thank you very much for your thorough and constructive review of our manuscript. We sincerely appreciate the time and attention you dedicated to identifying areas for improvement, particularly regarding the minor textual corrections and the issue of language consistency. All the suggested revisions have been addressed, and the corresponding changes are highlighted in track changes within the re-submitted document.

Comments 1: Minor issues to be addressed before publication (list of issues).

Response 1: Thank you for your detailed feedback and for pointing out these minor issues. All the suggested changes have been implemented. Please, find them in the revised version of the paper.

Comments 2: There is an issue in the Language consistency as the text transitions from British to American English. Please go through the whole document and correct the English usage.

Response 2: Thank you for highlighting this issue as well. We have thoroughly reviewed the entire text and ensured that the English usage is consistent throughout. Specifically, we have aligned the text to follow the British English conventions. All the modifications have been tracked in the revised version of the paper.