AI-accelerated Nazca survey nearly doubles the number of known figurative geoglyphs and sheds light on their purpose
Open accessAbstract
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.
AI snapshot
Written from the paper’s full text.
TL;DR
An AI-assisted survey of the Nazca Pampa detected 303 new figurative relief-type geoglyphs, nearly doubling the known total, and found that relief-type and line-type geoglyphs differ in motifs, distribution, and likely purpose. Relief-type geoglyphs are associated with informal trails and human/domesticated motifs, while line-type geoglyphs are associated with the formal linear/trapezoidal network and wild-animal motifs.
Key findings
- The AI-assisted survey detected 303 new figurative relief-type geoglyphs, almost doubling the previously known 380 relief-type geoglyphs; it also found 42 new geometric geoglyphs.
- Motifs differ strongly: line-type geoglyphs (50 known) are 64% wild animals, while relief-type geoglyphs (683 total after the new finds) are 81.6% human or human-modified motifs—33.8% humanoids, 32.9% decapitated heads, and 14.9% domesticated camelids—with wild animals only 6.9% (47 geoglyphs).
- Distribution differs: relief-type geoglyph groups average 43 m from the nearest trail, whereas line-type geoglyphs average 34 m from the nearest line/trapezoid. The authors conclude relief-type geoglyphs were viewed while walking trails and shared information among individuals or small groups, while line-type geoglyphs were part of a community ceremonial/pilgrimage network.
- Discovery rate accelerated from about 1.5 geoglyphs/y historically to 18.7/y in 2004–2020, and the 2022/23 season’s 303 new figurative geoglyphs represent a further 16-fold acceleration.
Methods
- The AI model used a pretrained neural network fine-tuned on relief-type geoglyphs, with a gridded classification model producing a continuous geoglyph probability map at 5 m resolution. It consumed 112 × 112 pixel true-color crops (about 11 × 11 m), sampled with a moving window step of about 5 m and 3 m overlap; training/validation used 401 relief-type geoglyph outlines (368 training, 33 validation) from 406 known relief-type geoglyphs, with data augmentation.
- Screening examined 47,410 AI candidate boxes, assigning 1,309 high-potential candidates to three ranks over 1,200 labor hours; the September 2022–February 2023 field survey visited 341 locations over 1,440 labor hours and confirmed 303 new figurative geoglyphs, for 2,640 total labor hours.
- Spatial analysis compared distances between relief-type geoglyph groups and trails, and between line-type geoglyphs and the linear/trapezoidal network, alongside motif classification and pottery-based dating context.
Limitations
- The paper states that 968 promising candidates could not be surveyed in 2022/23 and estimates at least 248 additional AI-proposed figurative geoglyphs may be found in future fieldwork (37 Rank I, 66 Rank II, 145 Rank III), excluding additional group finds and non-AI finds.
- The paper states the trail meshwork is only partially mapped, so a 500 m cutoff was used and geoglyphs not within 500 m of trails were removed from the analysis.
- Evident from the text: the AI focused only on relief-type geoglyphs, training data were limited to a few hundred known geoglyphs with poor contrast, and screening still required substantial human labor (1,200 hours; an average of 36 AI suggestions per promising candidate).
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
- Findingown data
42 new geometric geoglyphs were discovered.
“In addition, 42 new geometric geoglyphs were discovered”
Quote in the paperNot a substantial claim - Findingown data
968 promising candidates could not be surveyed during the 2022/23 fieldwork.
“Nine hundred sixty-eight of the promising candidates could not be surveyed during the 2022/23 fieldwork.”
Quote in the paperNot a substantial claim - Findingown data
The field survey confirmed 303 newly confirmed figurative geoglyphs.
“It required 1,440 labor hours and resulted in 303 newly confirmed figurative geoglyphs.”
Quote in the paperSubstantial claim - Findingown data
There is a significant difference between the 50 large line-type geoglyphs and the 683 small relief-type geoglyphs in what is depicted.
“As a result of integrating the newly discovered 303 geoglyphs into the already known figurative geoglyphs, we found that there is a significant difference between the 50 large line-type geoglyphs and the 683 small relief-type geoglyphs in what is depicted”
Quote in the paperSubstantial claim - Findingown data
Most relief-type geoglyphs (81.6%) depict human motifs or motifs of things modified by humans: 33.8% humanoids, 32.9% decapitated heads, and 14.9% domesticated camelids.
“Most relief-type geoglyphs (81.6%) depict human motifs or motifs of things modified by humans (33.8% humanoids, 32.9% decapitated heads, and 14.9% domesticated camelids).”
Quote in the paperSubstantial claim
- Findingown data
Wild animals represent only 6.9% (47 geoglyphs) of the relief-type geoglyphs.
“Wild animals, which dominate the line-type geoglyphs, represent only 6.9% (47 geoglyphs) of the relief-type geoglyphs.”
Quote in the paperNot a substantial claim - Findingreasoning
The discovery rate accelerated to 18.7 per year from 2004 to 2020.
“It has accelerated due to the availability of remotely sensed high-resolution imagery to 18.7/y from 2004 to 2020.”
Quote in the paperNot a substantial claim - Findingown data
1,200 labor hours were spent screening the AI-model geoglyph candidate photos.
“A total of 1,200 labor hours were spent screening the AI-model geoglyph candidate photos.”
Quote in the paperSubstantial claim - Findingown data
Human motifs (humanoids, decapitated heads, domesticated camelids) do not appear in line-type figurative geoglyphs at all.
“These do not appear in the line-type figurative geoglyphs at all.”
Quote in the paperSubstantial claim - Findingown data
Line-type geoglyphs predominantly depict wildlife-related motifs.
“Line-type geoglyphs predominantly depict wildlife-related motifs (e.g., wild animals and plants).”
Quote in the paperNot a substantial claim - Findingown data
Average distance between line-type geoglyphs and the nearest line/trapezoid is 34 m.
“Average distances between line-type geoglyphs and the nearest line/trapezoid are 34 m.”
Quote in the paperNot a substantial claim - Findingnone given
In the Nazca River Valley, line-type geoglyphs are distributed near only two major (more than 40 m wide) entrances/exits.
“In the Nazca River Valley, on the other hand, line-type geoglyphs are distributed near only two major (more than 40 m wide) entrances/exits.”
Quote in the paperSubstantial claim - Findingreasoning
About 10 trapezoidal squares, ranging in length from 300 to 950 m, have 24 line-type geoglyphs identified around them.
“There are about 10 such squares, ranging in length from 300 to 950 m, around which 24 line-type geoglyphs have been identified.”
Quote in the paperSubstantial claim - Findingnone given
The rate of discovery of new figurative Nazca geoglyphs was historically 1.5 per year from the 1940s to 2000s.
“The rate of discovery of new figurative Nazca geoglyphs has been historically on the order of 1.5 a y (from 1940s to 2000s).”
Quote in the paperSubstantial claim - Findingown data
An average of 36 AI-model suggestions were processed to find one promising candidate.
“We processed an average of 36 AI-model suggestions to find one promising candidate.”
Quote in the paperSubstantial claim - Findingown data
All individual geoglyphs that do not form groups are visible from trails.
“All individual geoglyphs that do not form geoglyph groups have been found to be visible from the trails.”
Quote in the paperSubstantial claim - Findingreasoning
Not all geoglyphs that form groups are necessarily visible from trails.
“On the other hand, not all the geoglyphs that form groups are necessarily visible from trails”
Quote in the paperNot a substantial claim - Findingown data
About 10 narrow entrances/exits to the network exist in the Ingenio River Valley at the northern end of the Nazca Pampa.
“About 10 narrow entrances/exits to the network exist in the Ingenio River Valley at the northern end of the Nazca Pampa adjacent to which trapezoids and line-type figurative geoglyphs are concentrated.”
Quote in the paperSubstantial claim - Findingown data
The field survey confirmed that relief-type geoglyphs or geoglyph scenes could be recognized from the trails.
“The field survey confirmed that relief-type geoglyphs or geoglyph scenes could be recognized from the trails.”
Quote in the paperSubstantial claim - Interpretationreasoning
Applying success rates, an additional 37 rank I, 66 rank II, and 145 rank III candidates are likely to be authentic.
“Applying success rates to all the candidate geoglyphs in each group, it can be pointed out that an additional 37 of the first rank, 66 of the second rank, and 145 of the third rank are likely to be authentic.”
Quote in the paperSubstantial claim- Rests on an assumption: The success rates of visited candidates within each rank are representative of unvisited candidates in the same rank.
- Interpretationreasoning
At least 248 additional AI-proposed figurative geoglyphs are expected upon completion of future field surveys.
“Based on the above estimate, one may expect at least 248 additional AI-proposed figurative geoglyphs to be discovered from the Nazca Pampa upon completion of future field surveys.”
Quote in the paperSubstantial claim- Rests on an assumption: The success rates of visited candidates within each rank are representative of unvisited candidates in the same rank.
- Interpretationreasoning
Repeatedly observing relief-type geoglyphs from the trails probably facilitated sharing information about human activities related to these scenes.
“Repeatedly observing relief-type geoglyphs from the trails probably facilitated sharing information about human activities related to these scenes.”
Quote in the paperNot a substantial claim - Interpretationown data
The AI-assisted method is much more scalable, as evidenced by the number of new geoglyphs it identified.
“The AI-assisted method is much more scalable, as evidenced by the number of new geoglyphs it has identified”
Quote in the paperSubstantial claim - Interpretationreasoning
Relief-type geoglyphs were objects to be viewed while walking along the trails.
“Thus, the relief-type geoglyphs were objects to be viewed while walking along the trails.”
Quote in the paperSubstantial claim - Interpretationown data
It is highly likely that people of the Early Nasca period visited the line-type figurative geoglyphs on foot from the lines and trapezoids.
“Since they are on average only 34 m apart from lines and trapezoids, it is highly likely that the people of that period visited the line-type figurative geoglyphs on foot from the lines and trapezoids.”
Quote in the paperSubstantial claim - Interpretationreasoning
Relief-type figurative geoglyphs are associated with the meshwork of trails beginning in the Initial Nasca Period.
“Our findings support two hypotheses about the figurative geoglyph associations: Relief-type figurative geoglyphs are associated with the meshwork of trails beginning in the Initial Nasca Period since pottery from this period and later is distributed there.”
Quote in the paperSubstantial claim - Interpretationreasoning
The informal trails were created and used by repetitive actions of individuals or small groups, rather than at the community level.
“It is highly likely that they were created and used by repetitive actions of individuals or small groups, rather than at the community level.”
Quote in the paperSubstantial claim - Interpretationreasoning
The network was mainly designed for groups from the Ingenio River Valley to make pilgrimages to the Cahuachi Temple and the confluence of rivers in the Nazca River Valley.
“This indicates that the network was mainly designed for groups from the Ingenio River Valley to make pilgrimages to the Cahuachi Temple and the confluence of rivers in the Nazca River Valley.”
Quote in the paperSubstantial claim - Interpretationreasoning
The differences in motifs of line-type and relief-type geoglyphs may reflect different activities practiced at the two types.
“The differences in motifs of line-type and relief-type geoglyphs may reflect different activities practiced at the two types of figurative geoglyphs.”
Quote in the paperNot a substantial claim - Interpretationreasoning
The trapezoidal geoglyphs can be regarded as ritual squares directly related to the line-type geoglyphs.
“It is reasonable to regard the trapezoidal geoglyphs, around which about half of the line-type figurative geoglyphs are distributed, as ritual squares directly related to the line-type geoglyphs.”
Quote in the paperSubstantial claim - Interpretationreasoning
Line-type figurative geoglyphs along lines and trapezoids can be regarded as part of the linear/trapezoidal network.
“Therefore, the line-type figurative geoglyphs along lines and trapezoids can be regarded as part of this network.”
Quote in the paperSubstantial claim - Interpretationown data
The paper confirmed a difference in the purpose of line-type and relief-type figurative geoglyphs by relating them to the linear/trapezoidal network and trails and analyzing differences in the distribution of their motifs.
“In this paper, we have confirmed a difference in the purpose of line-type and relief-type figurative geoglyphs by relating them to the linear/trapezoidal network and trails and analyzing differences in the distribution of their motifs.”
Quote in the paperSubstantial claim - Interpretationown data
Line-type figurative geoglyphs are associated with the network of lines/trapezoids of the Early Nasca period.
“Line-type figurative geoglyphs are associated with the network of lines/trapezoids of the Early Nasca period.”
Quote in the paperSubstantial claim - Interpretationreasoning
Rituals were performed on the giant line-type geoglyphs at the beginning and/or the end of the pilgrimage across the Nazca Pampa.
“It is highly probable that rituals were performed on the giant line-type geoglyphs at the beginning and/or the end of the pilgrimage across the Nazca Pampa.”
Quote in the paperSubstantial claim - Interpretationreasoning
Ceremonial activities related to wild animals were performed during pilgrimages.
“Since the main motifs of the line-type geoglyphs are wild animals, it is probable that ceremonial activities related to these animals were performed during pilgrimages.”
Quote in the paperSubstantial claim
- May combine two claims. 8
- Classified as probably not a substantial claim. 5
May combine two claims.
Findingown dataThe AI-assisted survey detected 303 new figurative relief-type geoglyphs, almost doubling the known relief-type geoglyphs.
“It has assisted in detecting 303 new figurative relief-type geoglyphs, almost doubling the amount of known relief-type geoglyphs”
Quote in the paperSubstantial claimMay combine two claims.
FindingreasoningOf the 125 not individually AI-suggested geoglyphs, 66 were found as part of an AI-discovered group, and 59 were found without AI help or outside AI-suggested boxes.
“Thus, of the 125 not individually AI-suggested geoglyphs, 66 were found as part of an AI-discovered group. The remaining 59 were found during the field survey without any help from AI or during screening outside of the AI-suggested boxes.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown dataOf the 303 newly discovered figurative geoglyphs, 178 were individually suggested by the AI and 125 were not individually AI-suggested.
“Of the 303 newly discovered figurative geoglyphs, 178 were individually suggested by the AI and 125 were not individually AI-suggested”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown dataThe 1,309 high-potential AI candidates were sorted into three ranks.
“The 1,309 candidates with high potential were further sorted into three ranks”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown dataThe main motifs of relief-type geoglyphs were humans, livestock, and human sacrifice, depicting scenes with humans or things modified by humans.
“The main motifs of the relief-type geoglyphs were humans, livestock, and human sacrifice, all of which depict scenes with humans or things modified by humans.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown dataThe current work represents a 16-fold acceleration (303 new figurative geoglyphs during the 2022/23 season).
“Our current work represents another 16-fold acceleration (303 new figurative geoglyphs during the 2022/23 season of field work) using big geospatial data technologies and data mining with the aid of AI.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown dataThe combined effort of screening AI suggestions and surveying the resulting sites on the ground resulted in 2,640 labor hours.
“Correspondingly, the combined effort of researchers screening AI suggestions and surveying the resulting sites on the ground resulted in an effort of 2,640 labor hours.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown dataThe field survey required 1,440 labor hours.
“It required 1,440 labor hours”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown dataRelief-type figurative geoglyphs were constructed at an average distance of 43 m from the trails, either individually or as a combination of geoglyphs depicting some scene.
“Average distances between relief-type geoglyph groups and the nearest trail are 43 m.”
- Also stated in: § Discussion · plain
“Relief-type figurative geoglyphs were constructed at an average distance of 43 m from the trails, either individually or as a combination of geoglyphs depicting some scene.”
Quote in the paperSubstantial claim- Also stated in: § Discussion · plain
Probably not a substantial claim: may not pass S4 (based). May combine two claims.
InterpretationreasoningThe line-type figurative geoglyphs and straight-line network were established and used by the communities of the Ingenio River Valley.
“It is reasonable to assume that they were established and used by the communities of the Ingenio River Valley.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable).
InterpretationreasoningAI may be at the brink of ushering in a revolution in archaeological discoveries.
“Thus, AI may be at the brink of ushering in a revolution in archaeological discoveries like the revolution aerial imaging has had on the field.”
Quote in the paperNot a substantial claimMay combine two claims.
InterpretationreasoningThe line-type figurative geoglyphs and the straight-line network can be regarded as planned public architecture.
“Since not only the line-type figurative geoglyphs but also the straight-line network shows a certain level of standardization, they can be regarded as planned public architecture.”
Quote in the paperSubstantial claim
The paper relies on this without support.
Relief-type geoglyphs are on average only 9 m in size.
“Relief-type geoglyphs are on average only 9 m in size, and they often depict humanoids and domesticated animals, more specifically llamas.”
The paper relies on this without support.
The success rates of visited candidates within each rank are representative of unvisited candidates in the same rank.
“Applying success rates to all the candidate geoglyphs in each group, it can be pointed out that an additional 37 of the first rank, 66 of the second rank, and 145 of the third rank are likely to be authentic.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Image-crop overlap does not match crop width and step size
MinorThe image crops are described as about 11 m wide. With an approximately 5 m step between neighboring crops, their overlap would be about 6 m, not 3 m.
Reported 3 · recomputed 6
“For inference, we sampled the entire Nazca Pampa and its surrounding using a moving window with a step size of approximately 5 m so that neighboring crops overlap by 3 m.”
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · see citing works
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203 · see citing works
Transformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595 · see citing works
Deep learning for computer vision: A brief review
Voulodimos, A., Doulamis, N., Doulamis, A., & Protopapadakis, E. (2018) · Computational Intelligence and Neuroscience · doi:10.1155/2018/7068349 · Cited by 3,403 · see citing works
Ingold, T. (2007) · Routledge eBooks · doi:10.4324/9780203961155 · Cited by 1,382 · see citing works
Copernicus Global Land Cover Layers—Collection 2
Buchhorn, M., Lesiv, M., Tsendbazar, N., Herold, M., Bertels, L., & Smets, B. (2020) · Remote Sensing · doi:10.3390/rs12061044 · Cited by 896 · see citing works
Life, Land and Water in Ancient Peru
Denevan, W. M., & Kosok, P. (1966) · Hispanic American Historical Review · doi:10.1215/00182168-46.2.191 · Cited by 220 · see citing works
Cahuachi in the ancient Nasca world
(1994) · Choice Reviews Online · doi:10.5860/choice.31-3855 · Cited by 126 · see citing works
A Review of Artificial Intelligence and Remote Sensing for Archaeological Research
Argyrou, A., & Αγαπίου, Ά. (2022) · Remote Sensing · doi:10.3390/rs14236000 · Cited by 114 · see citing works
Silverman, H., & Proulx, D. A. (2002) · Wiley eBooks · doi:10.1002/9780470693384 · Cited by 105 · see citing works
PAIRS: A scalable geo-spatial data analytics platform
Klein, L. J., Marianno, F. J., Albrecht, C. M., Freitag, M., Lu, S., Hinds, N., Shao, X., Rodrigues, S. B., & Hamann, H. F. (2015) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2015.7363884 · Cited by 65 · see citing works
Self-citationBerganzo‐Besga, I., Orengo, H. A., Lumbreras, F., Carrero-Pazos, M., Fonte, J., & Vilas-Estévez, B. (2021) · Remote Sensing · doi:10.3390/rs13204181 · Cited by 64 · see citing works
Deep learning reveals extent of Archaic Native American shell-ring building practices
Davis, D. S., Caspari, G., Lipo, C. P., & Sanger, M. C. (2021) · Journal of Archaeological Science · doi:10.1016/j.jas.2021.105433 · Cited by 60 · see citing works
The archaeological identification of an ancient Peruvian pilgrimage center
Silverman, H. (1994) · World Archaeology · doi:10.1080/00438243.1994.9980257 · Cited by 44 · see citing works
The Nazca Lines: A New Perspective on their Origin and Meaning
Reinhard, J. (2010) · Cited by 39 · see citing works
The archaeology and pottery of Nazca, Peru: Alfred L. Kroeber's 1926 expedition
(1999) · Choice Reviews Online · doi:10.5860/choice.36-6354 · Cited by 33 · see citing works
A 2,300-year-old architectural and astronomical complex in the Chincha Valley, Peru
Stanish, C. S., Tantaleán, H., Nigra, B. T., & Griffin, L. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1406501111 · Cited by 32 · see citing works
Learning and Recognizing Archeological Features from LiDAR Data
Albrecht, C. M., Fisher, C., Freitag, M., Hamann, H. F., Pankanti, S. U., Pezzutti, F., & Rossi, F. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9005548 · Cited by 32 · see citing works
Self-citation(1990) · doi:10.70249/9798893981193 · Cited by 26 · see citing works
The Prehistoric Ground Drawings of Peru
Isbell, W. H. (1978) · Scientific American · doi:10.1038/scientificamerican1078-140 · Cited by 21 · see citing works
Nasca origins and Paracas progenitors
Carmichael, P. H. (2016) · Ñawpa Pacha · doi:10.1080/00776297.2016.1239874 · Cited by 17 · see citing works
Johnson, D. W., Proulx, D. A., & Mabee, S. B. (2002) · Springer eBooks · doi:10.1007/978-1-4615-0597-6_12 · Cited by 11 · see citing works
Accelerating the discovery of new Nasca geoglyphs using deep learning
Sakai, M., Lai, Y., Olano, J. F. S., Hayashi, M., & Nomura, K. (2023) · Journal of Archaeological Science · doi:10.1016/j.jas.2023.105777 · Cited by 7 · see citing works
Self-citationStanish, C. S., & Tantaleán, H. (2018) · Ñawpa Pacha · doi:10.1080/00776297.2018.1444949 · Cited by 6 · see citing works
A Human Environment. Studies in honour of 20 years Analecta editorship by prof. dr. Corrie Bakels
Klinkenberg, V., & van Driel-Murray, R. V. O. C. (2020) · Cited by 5 · see citing works
Acueductos y caminos antiguos de la hoya del Río Grande de Nasca
Xesspe, T. M. (2016) · Boletín APAR. · doi:10.70748/ba.25.2016.180 · Cited by 5 · see citing works
Walking and marking the desert : geoglyphs in arid South America
Lambers, K. (2020) · Leiden Repository (Leiden University) · Cited by 3 · see citing works
Sakai, M., Freitag, M., Sakurai, A., Albrecht, C. M., & Hamann, H. F. (2024) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss53475.2024.10642513 · Cited by 2 · see citing works
Self-citationThe Geoglyphs of Palpa, Peru: Documentation, Analysis, and Interpretation
Aveni, A. F. (2006) · Journal of Field Archaeology · Cited by 1 · see citing works
OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.08774
Sakai, M., Freitag, M., Sakurai, A., Albrecht, C. M., & Hamann, H. F. (2024) · arXiv · doi:10.48550/arxiv.2405.11814
Self-citation
Flagged first, then by citations
Research works printed but not linked: 11
- M. Reiche, Mystery on the Desert (Editora Medica Peruana, Lima, 1949).
- M. Reiche, Contribuciones a la geometría y astronomía en el antiguo perú (Asociación María Reiche para las Líneas de Nasca, Lima, 1993).
- 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).
- E. Herrán, Geoglifos de Nazca: Clásicos y Nuevos Hallazgos (Nasca, 2014), [Self-published e-book].
- E. Herrán, Líneas de Nasca: De los hombres que dibujaron el desierto (Universidad de San Martín de Porres, Fondo Editorial, Lima, 2018).
- M. Sakai, Nasca Geoglyphs: Spatial Distribution Rule, Purpose of Construction, and Protection (in Japanese) (Embassy of the Republic of Peru in Japan, Tokyo, 2023).
- 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.
- 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).
- 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).
- M. Sakai, J. Olano, H. Takahashi, Líneas y cerámica en las Pampas de Nasca, Perú, 2011–2013 (Yamagata University Press, Yamagata, 2021).
- 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).
Cited by
Sorted by citations
Humanism strikes back? A posthumanist reckoning with ‘self-development’ and generative AI
Cadman, S., Tanner, C., & Pang, P. C. (2025) · AI & Society · doi:10.1007/s00146-025-02339-1 · Cited by 17 · see citing works
Mehta, J. M., Chamberlain, E. L., Helmer, M., Haire, E., McCoy, M. D., van Beek, R., Wang, H., & Yu, S. (2025) · PNAS Nexus · doi:10.1093/pnasnexus/pgaf090 · Cited by 8 · see citing works
Guo, J., Zimmer-Dauphinee, J. R., Nieusma, J. M., Lu, S., Liu, Q., Deng, R., Cui, C., Yue, J., Lin, Y., Yao, T., et al. (2025) · arXiv · doi:10.48550/arxiv.2504.20303 · Cited by 7 · see citing works
Self-citationLarge Language and Multimodal Models in Archaeological Science: A Review
Qi, X., & Wen, R. (2025) · Electronics · doi:10.3390/electronics14224507 · Cited by 6 · see citing works
Whitley, D. S., Lancaster, J., & Catacora, A. (2025) · Arts · doi:10.3390/arts14010020 · Cited by 6 · see citing works
Cardarelli, L. (2025) · Digital Applications in Archaeology and Cultural Heritage · doi:10.1016/j.daach.2025.e00452 · Cited by 3 · see citing works
Monitoring Irish Coastal Heritage Destruction: A Case Study from Inishark, Co. Galway, Ireland
Field, S., Kuijt, I., Lash, R., & Burke, T. (2025) · Remote Sensing · doi:10.3390/rs17152709 · Cited by 2 · see citing works
How Human Personality Will Change With the Use of Artificial Intelligence
Mayer, J. D. (2025) · Personality Science · doi:10.1177/27000710251386963 · Cited by 3 · see citing works
Castiello, M. E., Landauer, J., & Saintenoy, T. (2025) · Remote Sensing · doi:10.3390/rs17203499 · Cited by 2 · see citing works
Stanish, C. S., Tantaleán, H., Medina, C. T., Bongers, J. L., & Wise, K. (2026) · Journal of Anthropological Research · doi:10.1086/739379 · Cited by 1 · see citing works
Best practices for the application of computer vision-based machine learning in archaeology
Berganzo‐Besga, I., Orengo, H. A., & Lumbreras, F. (2026) · Journal of Archaeological Science · doi:10.1016/j.jas.2026.106577 · Cited by 1 · see citing works
Data Interpretation Driven by Algebra of Time-Dependent Operators
Nieto–Chaupis, H. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825233 · Cited by 1 · see citing works
Machine Learning as Mediator of Classical Electrodynamics and Quantum Mechanics
Nieto–Chaupis, H. (2024) · IEEE Asia-Pacific Conference on Applied Electromagnetics (APACE) · doi:10.1109/apace62360.2024.10877319
Goudie, A. (2025) · Springer eBooks · doi:10.1007/978-3-031-95555-6_11
One Channel is All You Need: Optimizing Hyperspectral Data for Crop Disease Detection
Buitenhuis, J. A., Vadapalli, H., & van der Haar, D. T. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-03705-3_4
Gonzalo Pimentel, G., Luis Pérez, R., Mariana Ugarte, F., Juan Gili, H., Javier Arévalo, L., Mendoza, R., Pérez-Carrasco, M., & R., M. A. S. (2026) · Antiquity · doi:10.15184/aqy.2026.10372
UAP (what are they?), NHI (who are they?), and us (who are we?)
Lomas, T. (2026) · World Futures · doi:10.1080/02604027.2026.2656115
Balmaceda-Baraona, E., Méndez, V., McRostie, V. B., Vidal-Elgueta, A., & Díaz, F. P. (2026) · Journal of Archaeological Science · doi:10.1016/j.jas.2026.106688
- Authors
- Sakai, M., Sakurai, A., Lu, S., Olano, J., Albrecht, C. M., Hamann, H. F., & Freitag, M.
- Affiliations
- Yamagata University (JP)
- Archéologie des Amériques (FR)
- IBM Research - Thomas J. Watson Research Center (US)
- Corresponding author
- Sakai, Masato
- Freitag, Marcus
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Published
- 2024-09-23
- Volume
- 121
- Issue
- 40
- Pages
- e2407652121-e2407652121
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- PMC
- PMC11459208
- OpenAlex
- W4402740526
- Semantic Scholar
- 5fe3273f5e067ef86e0b915893e06b14bbc66861
- Cited by
- 18
- References
- 30
- Citations by year
- 2026: 5 · 2025: 11 · 2024: 2
- FWCI
- 51.93
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- elib (German Aerospace Center) (acceptedVersion)
- Funders
- MEXT | Japan Society for the Promotion of Science (20H00041)
- Yamagata University (YU-COE(S)(S-4))
- IBM | IBM Research (Joint Study Agreement)
- Topics
- Social Sciences › Cultural Studies › Archaeology and Cultural Heritage
- Physical Sciences › Earth and Planetary Sciences › Space and Planetary Science › Archaeological Research and Protection
- Social Sciences › Archeology › Archaeology and Rock Art Studies
- Keywords
- ritual landscape, domestic animals, archaeological survey
- MeSH terms
- Archaeology, Humans, History, Ancient
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-30.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-30.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
