AI-accelerated Nazca survey nearly doubles the number of known figurative geoglyphs and sheds light on their purpose
Edited by Joyce Marcus, University of Michigan, Ann Arbor, MI; received April 17, 2024; accepted July 30, 2024
Significance
This paper demonstrates how AI accelerates discoveries in archaeology, even in a region as well known as the United Nations Educational, Scientific and Cultural Organization (UNESCO) World Heritage site of Nazca. Our vastly improved account of relief-type figurative geoglyphs reveals that they differ from line-type figurative geoglyphs beyond their style and size. The line type and relief type also differ in the motifs they depict, their distribution, and their relation to the meshwork of winding trails and the ceremonial network of linear/trapezoidal geoglyphs. Taken together, this makes a compelling case for different nature and purposes of relief-type and line-type figurative geoglyphs: the former sharing information about human activities with individuals or small groups and the latter built and used by the community for ceremonial purposes.
Abstract
It took nearly a century to discover a total of 430 figurative Nazca geoglyphs, which offer significant insights into the ancient cultures at the Nazca Pampa. Here, we report the deployment of an AI system to the entire Nazca region, a UNESCO World Heritage site, leading to the discovery of 303 new figurative geoglyphs within only 6 mo of field survey, nearly doubling the number of known figurative geoglyphs. Even with limited training examples, the developed AI approach is demonstrated to be effective in detecting the smaller relief-type geoglyphs, which unlike the giant line-type geoglyphs are very difficult to discern. The improved account of figurative geoglyphs enables us to analyze their motifs and distribution across the Nazca Pampa. We find that relief-type geoglyphs depict mainly human motifs or motifs of things modified by humans, such as domesticated animals and decapitated heads (81.6%). They are typically located within viewing distance (on average 43 m) of ancient trails that crisscross the Nazca Pampa and were most likely built and viewed at the individual or small-group level. On the other hand, the giant line-type figurative geoglyphs mainly depict wild animals (64%). They are found an average of 34 m from the elaborate linear/trapezoidal network of geoglyphs, which suggests that they were probably built and used on a community level for ritual activities.
Data, Materials, and Software Availability
All non-restricted data used in this paper is included in the manuscript. The precise location data of the geoglyphs that were used for training the AI model is available in reports on previous NASCA surveys (43–45). We don’t have permission to make this data accessible in a public database, but legitimate users may request it from the Peruvian Ministry of Culture. Data created by us on the geoglyphs are available upon request to Masato Sakai: [email protected], if permission is granted by the Peruvian Ministry of Culture and other organizations. Software used in this article is available from the following public GitHub repositories (46, 47).
Acknowledgments
This work was carried out under the permit: RD 187-2022-DGPA-VMPCIC-MC in 2022-2026, granted by the Peruvian Ministry of Culture. We thank Kazuo Aoyama, Renzo Barreto, Luis Delgado, Yunis Elguera, Ariadna Gomez, Kaoru Honda, Takeshi Inomata, Yuko Ito, Katsuko Kondo, Masayuki Kuronuma, Lisa Lu, Frank Medina, Jason Nesbitt, Sergio Saez, Joel Salhuana, and Kevin Vaughn. Finally, we thank Solomon Assefa (IBM Research) for his leadership in supporting this work. This work was supported by the Japan Society for the Promotion of Science KAKENHI (grant no. 20H00041) and Yamagata University YU-COE(S)(S-4). This work was also generously supported by IBM Research through a Joint Study agreement. C.M.A. has been additionally supported by the Helmholtz Association through the Framework of HelmholtzAI, grant ID: ZT-I-PF-5-01–Local Unit Munich Unit @Aeronautics, Space and Transport.
Author contributions
M.S., A.S., S.L., C.M.A., H.F.H., and M.F. designed research; M.S., S.L., J.O., C.M.A., H.F.H., and M.F. performed research; M.S., A.S., S.L., J.O., C.M.A., H.F.H., and M.F. analyzed data; and M.S., A.S., S.L., J.O., C.M.A., H.F.H., and M.F. wrote the paper.
Competing interests
The authors declare no competing interest.
Supporting Information
Appendix 01 (PDF)
- Download
- 3.10 MB
References
1
T. Mejía Xesspe, “Acueductos y caminos antiguos de la hoya del Río Grande de Nasca” in Actas y Trabajos Cientificos del 27 Congreso Internacional de Americanistas (Lima, 1939) (Librería e Imprenta Gil, S. A., Lima, 1940), vol. 1.
2
A. L. Kroeber, D. Collier, The Archaeology and Pottery of Nazca, Peru: Alfred L. Kroeber’s 1926 Expedition (AltaMira Press, Walnut Creek, 1998).
3
K. Lambers, “The geoglyphs of Palpa (Peru): Documentation, analysis, and interpretation,” Doctoral Dissertation, University of Zurich (Zurich, 2004).
4
M. Reiche, Mystery on the Desert (Editora Medica Peruana, Lima, 1949).
5
M. Reiche, Contribuciones a la geometría y astronomía en el antiguo perú (Asociación María Reiche para las Líneas de Nasca, Lima, 1993).
6
P. Kosok, Life, Land, and Water in Ancient Peru (Long Island University Press, Brooklyn, 1965).
7
J. Reinhard, The Nazca Lines: A New Perspective on Their Origin and Meaning (Editorial Los Pinos EIRL, Lima, 1987).
8
L. G. Lumbreras, Formulación de los lineamientos para la elaboración de un Plan de manejo de las líneas de Nasca 1: contexto arqueológico (Instituto Nacional de Cultura del Perú & UNESCO, Lima, 2000).
9
E. Herrán, Geoglifos de Nazca: Clásicos y Nuevos Hallazgos (Nasca, 2014), [Self-published e-book].
10
E. Herrán, Líneas de Nasca: De los hombres que dibujaron el desierto (Universidad de San Martín de Porres, Fondo Editorial, Lima, 2018).
11
M. Sakai, Nasca Geoglyphs: Spatial Distribution Rule, Purpose of Construction, and Protection (in Japanese) (Embassy of the Republic of Peru in Japan, Tokyo, 2023).
12
A. F. Aveni, Ed., The lines of Nazca (American Philosophical Society, Philadelphia, 1990).
13
H. Silverman, The archaeological Identification of an ancient Peruvian pilgrimage center. World Archaeol. 26, 1–18 (1994).
14
D. W. Johnson, D. A. Proulx, S. B. Mabee, “The correlation between geoglyphs and subterranean water resources in the Río Grande de Nazca drainage” in Andean Archaeology II, H. Silverman, W. Isbell, Eds. (Kluwer Academic/Plenum Publishers, New York, 2002), pp. 307–332.
15
C. Stanish, H. Tantaleán, B. T. Nigra, L. Griffin, A 2,300-year-old architectural and astronomical complex in the Chincha Valley, Peru. Proc. Natl. Acad. Sci. U.S.A. 111, 7218–7223 (2014).
16
C. Stanish, H. Tantaleán, The Chincha lines. Ñawpa Pacha 38, 77–107 (2018).
17
H. Silverman, D. A. Proulx, The Nasca (Blackwell, Malden, Mass, 2002).
18
K. Lambers, “Walking and marking the desert: Geoglyphs in arid South America” in A Human Environment: Studies in Honour of 20 Years Analecta Editorship by Prof. Dr. Corrie Bakels, V. Klinkenberg, R. Van Oosten, C. Van Driel-Murray, Eds. (Sidestone Press, Leiden, 2020), pp. 89–106.
19
M. Sakai, J. Olano, “Lines and figures of the pampa de Nazca” in Nasca, C. Pardo, P. Fux, Eds. (Asociación Museo de Arte de Lima, Lima, 2017), pp. 124–131, 366–368.
20
T. Ingold, Lines: A Brief History (Routledge, 2007).
21
M. Sakai, J. Olano, Y. Matsumoto, H. Takahashi, Centros de líneas y cerámica en las Pampas de Nasca, Perú, 2010 (Yamagata University Press, Yamagata, 2014).
22
M. Sakai, J. Olano, H. Takahashi, Centros de líneas y cerámica en las Pampas de Nasca, Perú, hasta el año 2018 (Yamagata University Press, Yamagata, 2019).
23
M. Sakai, J. Olano, H. Takahashi, Líneas y cerámica en las Pampas de Nasca, Perú, 2011–2013 (Yamagata University Press, Yamagata, 2021).
24
W. H. Isbell, The prehistoric ground drawings of Peru. Sci. Am. 239, 140–153 (1978).
25
P. H. Carmichael, Nasca origins and Paracas progenitors. Ñawpa Pacha 36, 53–94 (2016), https://doi.org/10.1080/00776297.2016.1239874.
26
M. Reindel, J. Isla, K. Koschmieder, Vorspanische Siedlungen und Bodenzeichnungen in Palpa, Südperu/Asentamientos prehispánicos y geoglifos en Palpa, costa sur del Perú. Beiträge zur Allgemeinen und Vergleichenden Archäologie 19, 313–381 (1999).
27
M. Sakai et al., Accelerating the discovery of new Nasca geoglyphs using deep learning. J. Archaeol. Sci. 155, 105777 (2023), https://doi.org/10.1016/j.jas.2023.105777.
28
J. Achiam et al., Gpt-4 technical report. arXiv [Preprint] (2023). https://doi.org/10.48550/arXiv.2303.08774 (Accessed 15 March 2023).
29
A. Voulodimos, N. Doulamis, A. Doulamis, E. Protopapadakis, Deep learning for computer vision: A brief review. Comput. Intel. Neurosci. 2018, 7068349 (2018), https://doi.org/10.1155/2018/7068349.
30
S. Khan et al., “Transformers in vision: A survey” in ACM Computing Surveys (CSUR) 54.10s, A. Zomaya, Ed. (ACM New York, NY, 2022).
31
I. Berganzo-Besga et al., Hybrid MSRM-based deep learning and multitemporal Sentinel 2-based machine learning algorithm detects near 10k archaeological Tumuli in North-western Iberia. Remote Sens. 13, 4181 (2021), https://doi.org/10.3390/rs13204181.
32
C. M. Albrecht et al., “Learning and recognizing archeological features from LiDAR data” in IEEE International Conference on Big Data (2019), pp. 5630–5636, https://doi.org/10.1109/BigData47090.2019.9005548.
33
D. S. Davis, G. Caspari, C. P. Lipo, M. C. Sanger, Deep learning reveals extent of Archaic Native American shell-ring building practices. J. Archaeol. Sci. 132, 105433 (2021).
34
A. Argyrou, A. Agapiou, A review of artificial intelligence and remote sensing for archaeological research. Remote Sens. 14, 6000 (2022), https://doi.org/10.3390/rs14236000.
35
K. He, X. Zhang, S. Ren, J. Sun, “Deep residual learning for image recognition” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, New York, 2016), https://doi.org/10.1109/CVPR.2016.90.
36
J. Deng et al., “ImageNet: A large-scale hierarchical image database” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, New York, 2009), https://doi.org/10.1109/CVPR.2009.5206848.
37
H. Silverman, Cahuachi in the Ancient Nasca World (University of Iowa Press, Iowa City, 1993).
38
M. Sakai et al., Climatic anthropogenic hazards to the Nasca World heritage: Application of remote sensing, AI, and flood modelling. arXiv [Preprint] (2024). https://doi.org/10.48550/arXiv.2405.11814 (Accessed 20 May 2024), 2024 IGARSS, accepted for publication.
39
L. J. Klein et al., “PAIRS: A scalable geo-spatial data analytics platform” in IEEE International Conference on Big Data (IEEE, New York, 2015), pp. 1290–1298, https://doi.org/10.1109/BigData.2015.7363884.
40
M. Buchhorn et al., Copernicus Global land service: Land cover 100m: Collection 3: Epoch 2019: Globe (2020), https://zenodo.org/record/3939050.
41
J. A. Clark, Pillow (PIL Fork) Documentation (Release 10.1.0.dev0). GitHub Source Code (2023). https://github.com/python-pillow/Pillow/blob/main/src/PIL/ImageFilter.py.
42
C. Shorten, T. M. Khoshgoftaar, A survey on image data augmentation for deep learning. J. Big Data 6, 60 (2019), https://doi.org/10.1186/s40537-019-0197-0.
43
M. Sakai, J. Olano, “Programa de Investigación Arqueológica de las Líneas y Geoglifos de las Pampas de Nasca. Plan Bianual n.º 1, años 2015-2017” (Final Report, Ministry of Culture of Peru, Lima, 2017).
44
M. Sakai, J. Olano, “Programa de Investigación Arqueológica de las Líneas y Geoglifos de las Pampas de Nasca. Plan Bianual n.º 2, años 2017-2020” (Final Report, Ministry of Culture of Peru, Lima, 2020).
45
M. Sakai, J. Olano, “Programa de Investigación Arqueológica de las Líneas y Geoglifos de las Pampas de Nasca. Plan Bianual n.º 3, años 2022-2026” (Annual Report of 2022, Ministry of Culture of Peru, Lima, 2023).
46
N. Hug, pytorch/vision. GitHub. https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py. Accessed 5 September 2021.
47
A. Murray, H. Van Kemenade, python-pillow/Pillow. GitHub. https://github.com/python-pillow/Pillow/blob/main/src/PIL/ImageFilter.py. Accessed 21 July 2021.
Information & Authors
Information
Published in
Cover image: Pictured is green foxtail (Setaria viridis), an annual grass. Magda Garbowski et al. combined data from more than 75,000 vegetation plots across the United States with functional trait data for more than 5,500 plant species to uncover how naturalized species affect plant community traits. Compared with communities dominated by native species, communities dominated by naturalized species were shorter, more shallowly rooted, and exhibited traits supporting rapid resource acquisition and low reliance on mycorrhizal symbionts. According to the authors, community-level trait shifts likely underpin the functional changes observed in invaded ecosystems. See the article by Garbowski et al. e2403120121. Image credit: Magda Garbowski.
Classifications
Copyright
Copyright © 2024 the Author(s). Published by PNAS. This open access article is distributed under Creative Commons Attribution-NonCommercial-NoDerivatives License 4.0 (CC BY-NC-ND).
Data, Materials, and Software Availability
All non-restricted data used in this paper is included in the manuscript. The precise location data of the geoglyphs that were used for training the AI model is available in reports on previous NASCA surveys (43–45). We don’t have permission to make this data accessible in a public database, but legitimate users may request it from the Peruvian Ministry of Culture. Data created by us on the geoglyphs are available upon request to Masato Sakai: [email protected], if permission is granted by the Peruvian Ministry of Culture and other organizations. Software used in this article is available from the following public GitHub repositories (46, 47).
Submission history
Received: April 17, 2024
Accepted: July 30, 2024
Published online: September 23, 2024
Published in issue: October 1, 2024
Keywords
Acknowledgments
This work was carried out under the permit: RD 187-2022-DGPA-VMPCIC-MC in 2022-2026, granted by the Peruvian Ministry of Culture. We thank Kazuo Aoyama, Renzo Barreto, Luis Delgado, Yunis Elguera, Ariadna Gomez, Kaoru Honda, Takeshi Inomata, Yuko Ito, Katsuko Kondo, Masayuki Kuronuma, Lisa Lu, Frank Medina, Jason Nesbitt, Sergio Saez, Joel Salhuana, and Kevin Vaughn. Finally, we thank Solomon Assefa (IBM Research) for his leadership in supporting this work. This work was supported by the Japan Society for the Promotion of Science KAKENHI (grant no. 20H00041) and Yamagata University YU-COE(S)(S-4). This work was also generously supported by IBM Research through a Joint Study agreement. C.M.A. has been additionally supported by the Helmholtz Association through the Framework of HelmholtzAI, grant ID: ZT-I-PF-5-01–Local Unit Munich Unit @Aeronautics, Space and Transport.
Author Contributions
M.S., A.S., S.L., C.M.A., H.F.H., and M.F. designed research; M.S., S.L., J.O., C.M.A., H.F.H., and M.F. performed research; M.S., A.S., S.L., J.O., C.M.A., H.F.H., and M.F. analyzed data; and M.S., A.S., S.L., J.O., C.M.A., H.F.H., and M.F. wrote the paper.
Competing Interests
The authors declare no competing interest.
Notes
This article is a PNAS Direct Submission.
Authors
Metrics & Citations
Metrics
Citation statements
Altmetrics
Citations
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
View Options
View options
PDF format
Download this article as a PDF file
DOWNLOAD PDFGet Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Personal login Institutional LoginRecommend to a librarian
Recommend PNAS to a LibrarianPurchase options
Purchase this article to access the full text.