The use of neural networks for the search of archaeological sites from the Scythian period (7th — 3rd centuries BC) in Southwestern Tuva
DOI:
https://doi.org/10.25178/nit.2025.4.14Keywords:
Tuva; Southwestern Tuva; Scythian period; archaeological site; geoinformation analysis; neural networkAbstract
The article presents a new approach for identifying previously unexplored archaeological sites of the Scythian period (7th–3rd centuries BC) in the territory of Southwestern Tuva through the application of modern research methods, namely neural networks. To achieve this objective, a database was created comprising archaeological sites of the Scythian era located within the study area. The database was compiled both from literature sources and from the authors’ own field research. The analysis involved 639 Scythian-period sites.
Based on the SRTM digital elevation model in ArcGIS 10.2, using the Spatial Analyst extension, as well as in the Python 3.7 environment, a geoinformation analysis was carried out to assess the distribution of archaeological sites across nine landscape parameters: absolute elevation, slope gradient, slope aspect, proximity to watercourses, elevation above the nearest watercourse, solar radiation intensity in December and June, visibility of mountain peaks, and distance from mountain peaks. The choice of parameters was informed by patterns of archaeological site distribution observed in the landscapes of Southwestern Tuva and Southeastern Altai during field expeditions.
Subsequently, variance analysis was performed to determine the significance of each parameter. Based on the obtained data, a feedforward neural network was trained, and a predictive model of potential locations of previously unexplored archaeological sites was constructed. Verification of the predictive model was conducted using satellite imagery provided by the World Imagery resource within ArcGIS Online. Approximately 150 predicted areas, each measuring 250×250 meters, were visually inspected. In 48 cases, previously unknown archaeological objects (kurgans) were discovered.
In conclusion, considering all the acquired data, a cartographic scheme of the settlement area of populations during the Scythian period was developed.
References
Arzhantseva, I. A., Vafeev, R. A., Schubert, A. and Harke, G. (2015) 3D reconstructions of the Por-Bazhyn complex (Tuva). In: Korobov, D. S. (ed.) Archaeology and Geoinformatics. Second International Conference. Abstracts of Papers. Moscow, Institute of Archaeology RAS. 52 p. P. 9. (In Russ.)
Vainshtein, S. I. (1958) Some results of the archaeological expedition of the Tuvan Research Institute of Language, Literature and History in 1956–1957. In: Serdobov, N. A. (ed.) Scholarly Notes of the Tuvan Research Institute of Language, Literature and History. Issue 6. Kyzyl, Tuvan Book Publishing House. 307 p. Pp. 217–237. (In Russ.)
Glebova, A. B., Sergeev, I. S. and Bykov, N. I. (2022) Geoinformation analysis with the construction of a neural network model for predicting location of archaeological monuments in the landscapes of South-Eastern Altai. Vestnik of Saint Petersburg University. Earth Sciences, vol. 67, no. 3, pp. 491–514. (In Russ.) DOI: https://doi.org/10.21638/spbu07.2022.306
Glebova, A. B. and Sergeev, I. S. (2024) The landscape indication of archaeological sites in the valleys of the rivers Mugur and Kargy (Southwestern Tuva). Vestnik of Saint Petersburg University. Earth Sciences, no. 4, pp. 695–715. (In Russ.) DOI: https://doi.org/10.21638/spbu07.2024.405
Glebova, A. B., Sergeev, I. S., Kapkina, A. S. and Pautova, E. M. (2024) Predicting the location of archaeological sites in the landscapes of Southeastern Altai based on a neural network algorithm. In: Subbeto, D. A., Voitekhovsky, Yu. L. and Paranina, A. N. (eds.) LXXVII Herzen Readings. Geography: Development of Science and Education. Proceedings of the International Scientific and Practical Conference: in 2 vols. St. Petersburg, Herzen State Pedagogical University of Russia. Vol. 1. 304 p. Pp. 99–103. (In Russ.)
Grach, A. D. (1980) Ancient Nomads in the Center of Asia. Moscow, Nauka. 256 p. (In Russ.)
Davidson-Pilon, C. (2019) Probabilistic Programming in Python: Bayesian Inference and Algorithms. St. Petersburg, Piter. 256 p. (In Russ.)
Kyzlasov, L. R. (1979) Ancient Tuva (from the Paleolithic to the 9th century). Moscow, Moscow University Press. 207 p. (In Russ.)
Mandelshtam, A. M. (1992) Early nomads of the Scythian period in the territory of Tuva. In: Moshkova, M. G. (ed.) The Steppe Zone of the Asian Part of the USSR in the Scythian-Sarmatian Period. Archaeology of the USSR. Moscow, Nauka. 494 p. Pp. 178–196. (In Russ.)
Mannai-ool, M. Kh. (1964) Archaeological Sites of Tuva. Kyzyl, Tuvknigoizdat. 46 p. (In Russ.)
Mannai-ool, M. Kh. (1970) Tuva in the Scythian Period (Uyuk Culture). Moscow, Nauka. 117 p. (In Russ.)
Rukavishnikova, I. V., Rukavishnikov, D. V. and Morozov, P. A. (2015) Application of low-altitude aerial photography and geophysical methods in the study of stone kurgans of the Scythian period in the Turano-Uyuk Basin (Tuva). In: Korobov, D. S. (ed.) Archaeology and Geoinformatics. Second International Conference. Abstracts of Papers. Moscow, Institute of Archaeology RAS. 52 p. P. 30. (In Russ.)
Savinov, D. G. (1994) Tuva of the Early Scythian period “at the crossroads” of cultural traditions (Aldy-Bel culture). In: Savinov, D. G. (ed.) Cultural Translations and the Historical Process: Paleolithic–Middle Ages. St. Petersburg: St Petersburg University Press, 172 p. Pp. 76–89. (In Russ.)
Sambu, I. U. (1994) Corpus of Archaeological Sites of the Republic of Tuva. Kyzyl, Restipografia. 192 p. (In Russ.)
Semenov, Vl. A. (1999) Synchronization and chronology of Aldy-Bel type sites in Tuva. In: Kiryushin, Yu. F. and Tishkin, A. A. (eds.) Results of the Study of the Scythian Epoch of Altai and Adjacent Territories. Barnaul, Altai State University. 284 p. Pp. 165–169. (In Russ.)
Surazakov, A. S. (1989) On the ethnic interpretation of the monuments of the Pazyryk culture. In: Dobzhansky, V. N. (ed.) Problems of the Archaeology of the Scythian-Siberian World: Social Structure and Social Relations: in 2 parts. Kemerovo, Kemerovo State University. Part 2. 148 p. Pp. 44–47. (In Russ.)
Chollet, F. (2018) Deep Learning with Python. St. Petersburg, Piter. 400 p. (In Russ.)
Caspari, G. (2020) Mapping and Damage Assessment of “Royal” Burial Mounds in the Siberian Valley of the Kings. Remote Sensing, vol. 12(5), article 773. DOI: https://doi.org/10.3390/rs12050773
Chen, F., Zhou, R., Van de Voorde, T., Chen, X., Bourgeois, J., Gheyle, W., Yang, J., Xu, W. (2021) Automatic detection of burial mounds (kurgans) in the Altai Mountains. ISPRS Journal of Photogrammetry and Remote Sensing, vol. 177, pp. 217–237. DOI: https://doi.org/10.1016/j.isprsjprs.2021.05.010
Hanani, A., Yakub, F., Azizan, A., Roslan, S., Shairatul, A. R., Ahmad, S. A., Muhammad, S. A. A. (2022) A Review on Deep Learning Application for Detection of Archaeological Structures. Journal of Advanced Research in Applied Sciences and Engineering Technology, vol. 26, issue 1, pp. 7–14.
Soroush, M., Mehrtash, A., Khazraee, E., Jason, Ur A. (2020) Deep Learning in Archaeological Remote Sensing: Automated Qanat Detection in the Kurdistan Region of Iraq. Remote Sensing, vol. 12 (3), article 500, pp. 1–18. DOI: https://doi.org/10.3390/rs12030500
Vavulin, M. V., Chugunov, K. V., Zaitceva, O. V., Vodyasov, E. V. Pushkarev, A. A. (2021) UAV-based photogrammetry: Assessing the application potential and effectiveness for archaeological monitoring and surveying in the research on the ‘valley of the kings’ (Tuva, Russia). Digital Applications in Archaeology and Cultural Heritage, vol. 20, article e00172. DOI: https://doi.org/10.1016/j.daach.2021.e00172
Verschoof-van der Vaart, L., K. (2021) Applying automated object detection in archaeological practice: A case study from the southern Netherlands. Archaeological Prospection, vol. 29 (341), pp. 1–17. DOI: https://doi.org/10.1002/arp.1833
Zhogova, A., Oleszczak, L., Michalczewski K., Pienkos I., Caspari, G. (2023) Identifying seasonal settlement sites and land use continuity in the prehistoric southern Siberian steppe — Zhelvak 5 (Tuva). Archaeological Research in Asia, vol. 35, article 100467. DOI: https://doi.org/10.1016/j.ara.2023.100467
Published
How to Cite
For citation:
Glebova A. B. and Sergeev I. S. The use of neural networks for the search of archaeological sites from the Scythian period (7th — 3rd centuries BC) in Southwestern Tuva. New Research of Tuva, 2025, no. 4, pp. 254-266. (In Russ.). DOI: https://doi.org/10.25178/nit.2025.4.14
Issue
Section

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Author(s) license holder(s) grant rights for their work to the journal (grantee of a license) under the simple non-exclusive open license in accordance with Art. 1286.1 «Open license for a research work, work of literature or fine arts», Civil Code of the Russian Federation.
New Research of Tuva publishes articles under the Creative Commons Attribution-NonCommercial license (CC BY-NC).
Since it is an open license, author(s) reserve the right to upload the article to their institutional repository, submit it to another journal (if it allows republications), or republish it on their own website (in full, or in part).
However, several conditions apply here:
a) The republished version must always contain the name(s) and affiliation(s) of the author(s), the original title and the hyperlink to the original version on the New Research of Tuva website;
b) It must be in open access, free of charge, and no category of readers must be in any way whatsoever advantaged over general readership.
c) should the contribution be submitted elsewhere by its author(s) without substantial modification (30% or more of original text unchanged), the body of the article should contain a disclaimer that the original version was published in New Research of Tuva (with a link to the respective page)
The CC-BY-NC is a non-revocable license which applies worldwide and lasts for the duration of the work’s copyright.


