Artificial intelligence in rock art research: limits, possibilities, and challenges of an uncertain evolution
DOI:
https://doi.org/10.26754/ojs_salduie/sald.2025212652Keywords:
prehistoric art, machine learning, automatic detection, supervised models, image processingAbstract
The recent development of artificial intelligence (AI) has opened new possibilities for the documentation and analysis of rock art. This article critically examines the potential and the limits of using open machine learning (ML) models for the automatic detection of pictorial motifs. After reviewing the state of the art and outlining the principles of ML as applied to archaeology, we empirically evaluate an open model (Roboflow 3.0 Object Detection) on four rock art panels from the Iberian Peninsula. The results show acceptable performance only in well-preserved contexts, while accuracy decreases notably in the presence of faded pigments or irregular rock surfaces. We conclude that ML can support archaeological research but cannot replace expert interpretation, and that progress in this field depends on standardized public repositories and coherent expert annotations.
Downloads
References
Bellat, M., Orellana, J. D., Tennie, C. y Scholten, T. (2025). Machine learning applications in archaeological practices: A review. ArXiv. 2501.03840v3. https://doi.org/10.48550/arXiv.2501.03840
Bevan, A. (2015). The data deluge. Antiquity 89(348): 1473-1484. https://doi.org/10.15184/aqy.2015.102
Bonald, L., Mützenberg, D., Krempser, E. y Verhagen, P. (2024). Predicting rock art sites in the Pajeú watershed, Brazil. Digital Applications in Archaeology and Cultural Heritage 35. e00372.
Bruno, F., Bruno, S., De Sensi, G., Luchi, M. L., Mancuso, S. y Muzzupappa, M. (2013). From 3D reconstruction to virtual reality: A complete methodology for digital archaeological exhibition. Journal of Cultural Heritage 11(1): 42-49.
Bruseker, G., Carboni, N. y Guillem, A. (2017). Cultural heritage data management: The role of formal ontology and CIDOC CRM. En Vincent, M. L., López-Menchero Bendicho, V. M., Ioannides, M. y Levy, T. E. (eds.): Heritage and archaeology in the digital age: Acquisition, curation, and dissemination of spatial cultural heritage data (pp. 93-131). Springer, Cham.
Casillo, M., F. Colace, R. Gaeta, A. Lorusso y M. Pellegrino (2024). Artificial intelligence in archaeological site conservation: Trends, challenges, and future directions. Journal of Computer Applications in Archaeology 8(1): 224-241. https://doi.org/10.5334/jcaa.207
Chen, Y., Mancini, M., Zhu, X. y Akata, Z. (2024). Semi-supervised and unsupervised deep visual learning: A survey. arXiv. 2208.11296v1. https://doi.org/10.48550/arXiv.2208.11296
Chollet, F. (2021). Deep learning with Python (2nd ed.). Manning, Shelter Island.
Cioni, D., Berlincioni, L., Becattini, F. y Del Bimbo, A. (2023). Diffusion based augmentation for captioning and retrieval in cultural heritage. arXiv. 2308.07151v1. https://doi.org/10.48550/arXiv.2308.07151
Consejería de Educación, Cultura y Deportes de Castilla-La Mancha. https://cultura.castillalamancha.es/
De Lara, H. (2025). Manifestaciones rupestres prehistóricas en el sur de Europa y el norte de África: el entorno del estrecho de Gibraltar [Tesis doctoral]. UNED, Madrid. https://e-spacio.uned.es/entities/publication/1115c451-df2c-4621-b2ce-9d32f1ed56fc
De Lara, H., Mas, M. y Solís, M. (2025). Chronocultural proposal for the Atlanterra Cave (Cadiz, Spain). Rock Art Research 42(2): 213-233.
https://rockartresearch.com/index.php/rock/article/view/686
Dell’unto, N., Landeschi, G., Apel, J. y Poggi, G. (2016), Experiencing ancient buildings from a 3D GIS perspective: A case drawn from the Swedish Pompeii project. Journal of Archaeological Method and Theory 23(1): 73-94.
Fiorucci, M., Khoroshiltseva, M., Pontil, M., Traviglia, A., Del Bue, A. y James, S. (2020). Machine learning for cultural heritage: A survey. Pattern Recognition Letters 133: 102-108.
Goodfellow, I., Bengio, Y. y Courville, A. (2016). Deep learning. MIT Press, Cambridge (MA).
Guo, C., Pleiss, G., Sun, Y. y Weinberger, K. Q. (2017). On calibration of modern neural networks. arXiv. 1706.04599v2. https://doi.org/10.48550/arXiv.1706.04599
Harth, A. (2024). The study of pigments in cultural heritage: A review using machine learning. Heritage 7(7): 3664-3695. https://doi.org/10.3390/heritage7070174
He, K., Gkioxari, G., Dollár, P. y Girshick, R. (2017). Mask R-CNN. arXiv. 1703.06870v3. https://doi.org/10.48550/arXiv.1703.06870
Historic England (2017). Photogrammetric applications for cultural heritage. Historic England Publishing, Swindon.
Horn, C., Ivarsson, O., Lindhé, C., Potter, R., Ashely, G. y Ling, J. (2022). Artificial intelligence, 3D documentation, and rock art—Approaching and reflecting on the automation of identification and classification of rock art images. Journal of Archaeological Method and Theory 29: 188-213. https://doi.org/10.1007/s10816-021-09518-6
Huo, D., Yang, S. y Hou, M. (2025). Using the improved YOLOv7-Seg model to segment symbols from rock art images. npj Heritage Science 13. 16. https://doi.org/10.1038/s40494-025-01620-2
Jalandoni, A., Zhang, Y. y Zaidi, N. A. (2022). On the use of machine learning methods in rock art research with application to automatic painted rock art identification. Journal of Archaeological Science 144. 105629. https://dx.doi.org/10.1016/j.jas.2022.105629
Kowlessar, J., Keal, J., Wesley, D., Moffat, I., Lawrence, D., Weson, A., Nayinggul, A. y Mimul Land Management Aboriginal Corporation (2021). Reconstructing rock art chronology with transfer learning: A case study from Arnhem Land, Australia. Australian Archaeology 87: 115-126. https://doi.org/10.1080/03122417.2021.1895481
Lecun, Y., Bengio, Y. y Hinton, G. (2015). Deep learning. Nature 521(7553): 436-444. https://doi.org/10.1038/nature14539
Liu, Y., Wang, Y. y Liu, C. (2023). A deep-learning method using auto-encoder and generative adversarial network for anomaly detection on ancient stone stele surfaces. arXiv. 2308.04426v1. https://doi.org/10.48550/arXiv.2308.04426
Museo de la Valltorta. https://museudelavalltorta.gva.es/es
Pan, S. J. y Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22(10): 1345-1359. https://doi.org/10.1109/TKDE.2009.191
Redmon, J., Divvala, S., Girshick R. y Farhadi, A. (2016). You only look once: Unified, real-time object detection. arXiv. 1506.02640v5. https://doi.org/10.1109/CVPR.2016.91
Roboflow Universe, 2024, RMR Computer Vision Model. https://universe.roboflow.com/manifestaciones-y-figuras-rupestres/rmr/model/1
Schmarje, L., Santarossa, M., Schröder, S. M. y Koch, R. (2020). A survey on semi-, self- and unsupervised learning for image classification. arXiv. 2002.08721v5. https://doi.org/10.48550/arXiv.2002.08721
Shorten, C. y Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data 6(1). 60. https://doi.org/10.1186/s40537-019-0197-0
Sokolovska, A. (2024). Artificial intelligence and prospects for its use in the study of Upper Palaeolithic rock art. Vita Antiqua 15: 127-135. https://doi.org/10.1186/s40537-019-0197-0
Steels, L. y Wahle, B. (2020). Perceiving the focal point of a painting with AI: Case studies on works of Luc Tuymans. En Rocha, A., Steels, L. y van den Herik, J. (eds.): Proceedings of the 12th International Conference on Agents and Artificial Intelligence (ICAART), Vol. 2 (pp. 895-901). ScitePress, Setúbal.
Suhaimi, M. S., Zainuddin, K., Ghazali, M. D., Marzukhi, F., Samad, A. M. y Majid, Z. (2023). Comparison of one-stage and two-stage strategies of machine learning model for rock art object detection. En 2023 IEEE 13th International Conference on System Engineering and Technology (ICSET) (pp. 215-220). IEEE, Piscataway.
Turner-jones, R. N., Tuxworth, G., Haubt, R. A. y Wallis, L. (2024). Digitising the deep past: Machine learning for rock art motif classification in an educational citizen science application. Journal on Computing and Cultural Heritage 17(4): 1-19.
Veggi, M. (2025). State of the art on artificial intelligence resources for interaction media design in digital cultural heritage. arXiv. 2504.13894v1. https://doi.org/10.48550/arXiv.2504.13894
Wilkinson, M., Dumontier, M., Aalbersberg, I. et al. (2016). The FAIR Guiding Principles for scientific data management and stewardship. Scientific Data 3. 160018. https://doi.org/10.1038/sdata.2016.18
Yang, X., Song, Z., King, I. y Xu, Z. (2021). A survey on deep semi-supervised learning. arXiv. 2103.00550v2. https://doi.org/10.48550/arXiv.2103.00550
Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H. y He, Q. (2019). A comprehensive survey on transfer learning. arXiv. 1911.02685v3. https://doi.org/10.48550/arXiv.1911.02685
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Salduie
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
SALDUIE retains the copyright of the published articles, authorizing the use, dissemination, transmission and public display of their content, provided that the authorship, url and journal are cited, and that they are not used for commercial purposes. The right to reproduce the articles in hard copy, portable document format (.pdf) or HTML editions of JoS is also reserved. The authors agree with the license of use used by the journal, as well as with the conditions of self-archiving and its open access policy.
