Historical Geography Journal ISSN 2782-6511

Dmitry V. Sarychev
Voronezh State University
Voronezh, Russia
E-mail: sarychev.geo@gmail.com
ORCID: 0000-0002-3755-0108

Grigory L. Zemtsov
Candidate of Historical Sciences, Lipetsk State Pedagogical University
Lipetsk, Russia
E-mail: grizem@rambler.ru
ORCID: 0000-0002-7177-7242

 Download | Back to the Content № 1. 2023

UDC 902.2(470.61):912.648
DOI: 10.58529/2782-6511-2023-2-1-6-23

ABSTRACT. The paper is devoted to an archaeological predictive modeling technique with GIS and machine learning based on maximal entropy algorithm (MaxEnt). Archaeological sites of the late roman time presented by settlements of Kashirka-Sedelok type (mid-3rd — early 4th century AD) in the Upper Don basin were the modeling objects. We found out that there are 169 known sites of such type in the study region, and collected all available information on their locations into a geodatabase including our own field survey data. The coordinates of these sites split into training and testing subsets served for developing a predictive model with MaxEnt. Environmental GIS-layers based on a digital elevation model and thematic maps were the model predictors. We made such predictors to reflect the paleogeography of the Upper Don basin in the study time period by choosing relatively stable landscape features of relief, bedrock, climate, hydrography and soils of the area. The trained model analyzed through more than 7 million cells of 90×90 m with overall area of 59 400 sq. km to identify potentially suitable areas for the Kashirka-Sedelok settlements and found 29 860 ha the most suitable areas (less than 1 % of the study area) as the result. The efficiency of the conducted modeling, evaluated on the testing sites, is high based on metrics of receiver operating characteristic (AUC = 0,915) and Kvamme’s Gain (KG = 0,97). The results of modeling serve as an agenda for the upcoming archaeological surveys in the region

KEYWORDS: archaeological predictive modeling, APM, maximal entropy, MaxEnt, late roman time, archaeological sites of the Kashirka-Sedelok type, GIS

For citation: Sarychev D.V., Zemtsov G.L. Predictive Archaeological Modeling with MaxEnt (Late Roman Settlements in The Upper Don Basin Case) // Historical Geography Journal. 2023. Vol. 2. № 1. P. 6–23.

REFERENCES

• Baldwin R. A. Use of Maximum Entropy Modeling in Wildlife Research. Entropy, 2009, vol. 11, no. 4, pp. 854–866. DOI: 10.3390/e11040854 (In English).
• Banks W. E. The Application of Ecological Niche Modeling Methods to Archaeological Data in Order to Examine Culture-Environment Relationships and Cultural Trajectories. Quaternaire, 2017, vol. 28, no. 2, pp. 271–276. DOI: 10.4000/quaternaire.7966 (In English).
• Boyce M. S., Vernier P. R., Nielsen S. E., Schmiegelow F. A. Evaluating Resource Selection Functions. Ecological Modeling, 2002, no. 157, pp. 281–300. DOI: 10.1016/S0304-3800(02)00200-4 (In English).
• Brown J., Hill D., Dolan A., Carnaval A. C., Haywood A. M. PaleoClim, High Spatial Resolution Paleoclimate Surfaces for Global Land Areas. Scientific Data, 2018, vol. 5, iss. 1, article number: 180254. DOI: 10.1038/sdata.2018.254 (In English).
• Chechushkov I. V., Valiakhmetov I. A. [“The Wind Is Getting Stronger”: Modeling Wind Speed in The Formation of Explanatory Models of Settlement Systems]. Arkheologiya i geoinformatika [Archaeology and geoinformatics], 2021, vol. 10. Available at: https://www.archaeolog.ru/media/periodicals/agis/AGIS-10/Chechushkov/page1.html (accessed: 10.01.2023). DOI: 10.25681/IARAS.2021.978-5-94375-342-8.21 (In Russian).
• Dolina Dona: priroda i landshafty [Don Valley: Nature and Landscapes]. Voronezh: Tsentr-Chernozemnoye kn. izd-vo Publ., 1982. (In Russian).
• Elith J., Leathwick J. R. The Contribution of Species Distribution Modelling to Conservation Prioritization. Spatial Conservation Prioritization: Quantitative Methods & Computational Tools. Oxford: Oxford University Press, 2009, pp. 70–93. (In English).
• Elith J., Phillips S. J., Hastie Т., Dudik М., Chee Y. E., Yates C. J. A Statistical Explanation of MaxEnt for Ecologists. Diversity and Distributions, 2011, no. 17, pp. 43–57. DOI: 10.1111/j.1472-4642.2010.00725.x (In English).
• Galletti C. S., Ridder E., Falconer S. E., Fall P. L. Maxent Modeling of Ancient and Modern Agricultural Terraces in the Troodos Foothills, Cyprus. Applied Geography, 2013, no. 39, pp. 46–56. DOI: 10.1016/j.apgeog.2012.11.020 (In English).
• Gerlitz, L., Conrad O., Böhner J. Large Scale Atmospheric Forcing and Topographic Modification of Precipitation Rates Over High Asia — A Neural Network Based Approach. Earth System Dynamics, 2015, no. 6, pp. 1–21. (In English).
• GIS and Archaeological Site Location Modeling. Boca Raton: CRC Press Taylor & Francis Group, 2006. (In English).
• Glebova A. B., Sergeev I. S., Bykov N. I. [Geoinformation Analysis with the Construction of a Neural Network Model for Predicting Location of Archaeological Monuments in the Landscapes of South-Eastern Altai]. Vestnik Sankt-Peterburgskogo universiteta. Nauki o Zemle [Vestnik of Saint Petersburg University. Earth Sciences], 2022, vol. 67, no. 3, pp. 491–514. DOI: 10.21638/spbu07.2022.306 (In Russian).
• Guisan A., Weiss S. B., Weiss A. D. GLM Versus CCA Spatial Modeling of Plant Species Distribution. Plant Ecology, 1999, no. 143, pp. 107–122. DOI: https://doi.org/10.1023/A:1009841519580 (In English).
• Hastie T., Tibshirani R., Friedman J. H. The Elements of Statistical Learning: Data Mining, Inference, And Prediction. 2^nd ed. New York: Springer-Verlag, 2009. (In English).
• Hirzel A. H., Le Lay G., Helfer V., Randon C., Guisan A. Evaluating the Ability of Habitat Suitability Models to Predict Species Presences. Ecological Modeling, 2006, vol. 199, iss. 2, pp. 142–152. DOI: 10.1016/j.ecolmodel.2006.05.017 (In English).
• Howey M. C., Palace M. W., McMichael C. H. Geospatial Modeling Approach to Monument Construction Using Michigan from AD 1000–1600 as a Case Study. Proceedings of the National Academy of Sciences, 2016, vol. 113, iss. 27, pp. 7443–7448. DOI: 10.1073/pnas.1603450113 (In English).
• Judge W. J., Martin D. W., Sebastian L. Quantifying the Present and Predicting the Past: Theory, Method, and Application of Archaeological Predictive Modeling. Washington, D. C.: Bureau of Land Management, 1989. (In English).
• Kass J. M., Muscarella R., Galante P. J. et al. ENMeval 2.0: Redesigned for Customizable and Reproducible Modeling of Species’ Niches and Distributions. Methods in Ecology and Evolution, 2021, vol. 12, iss. 9, pp. 1602–1608. DOI: 10.1111/2041-210x.13628 (In English).
• Kramer-Schadt S., Niedballa J., Pilgrim J. D. et al. The Importance of Correcting for Sampling Bias in MaxEnt Species Distribution Models. Diversity Distribution, 2013, vol. 19, iss. 11, pp. 1366–1379. DOI: 10.1111/ddi.12096 (In English).
• Lissovsky A. A., Dudov S. V. [Advantages and Limitations of Application of the Species Distribution Modeling Methods. 2. MaxEnt]. Zhurnal obshchey biologii [Journal of General Biology], 2020, vol. 81, no. 2, pp. 135–146. DOI: 10.31857/S0044459620020049 (In Russian).
• Liu C., White M., Newell G. Selecting Thresholds for the Prediction of Species Occurrence with Presence-Only Data. Journal of Biogeography, 2013, vol. 40, no. 4, pp. 778–789. (In English).
• Lobo J. M., Jimenez-Valverde A., Real R. AUC: A Misleading Measure of the Performance of Predictive Distribution Models. Global Ecology & Biogeography, 2008, vol. 17, iss. 2, pp. 145–151. DOI: 10.1111/j.1466-8238.2007.00358.x (In English).
• Martynov A. I., Medvedev A. A., Alekseenko N. A., Koshutin R. A. [Creation of a Predictive Model for the Search for Archaeological Objects in the Solovetsky Archipelago]. Geodeziya, kartografiya, geoinformatika i kadastry. Ot idei do vnedreniya: sb. nauch. statey [Geodesy, Cartography, Geoinformatics and Cadastres. From Idea to Implementation: Collection of Sci. Articles]. Saint Petersburg: Politekhnika Publ., 2017, pp. 448–455. (In Russian).
• McCune B., Keon D. Equations for Potential Annual Direct Incident Radiation and Heat Load. Journal of Vegetation Science, 2002, vol. 13, iss. 4, pp. 603–606. DOI: 10.1111/j.1654-1103.2002.tb02087.x (In English).
• Merow C., Smith M. J., Silander J. A. A Practical Guide to MaxEnt for Modeling Species’ Distributions: What It Does, and Why Inputs and Settings Matter. Ecography, 2013, vol. 36, iss. 10, pp. 1058–1069. DOI: 10.1111/j.1600-0587.2013.07872.x (In English).
• Moore I. D., Gessler P. E., Nielsen G. A., Petersen G. A. Terrain Attributes: Estimation Methods and Scale Effects. Modeling Change in Environmental Systems. London: Wiley, 1993, pp. 189–214. (In English).
• Nicu I. C., Mihu-Pintilie A., Williamson J. GIS-Based and Statistical Approaches in Archaeological Predictive Modelling (NE Romania). Sustainability, 2019, vol. 11, iss. 21, pp. 1–13. DOI: 10.3390/su11215969 (In English).
• Oblomsky A. M. [On the Rhythms of Development of the Forest-Steppe Dnieper and Don Region in the Late Roman and Hun Times]. Arkheologiya Tsentral’nogo Chernozem’ya i sopredel’nykh territoriy: sb. nauch. statey [Archaeology of the Central Chernozem Region and Adjacent Territories: A Collection of Sci. Articles]. Lipetsk: Izd-vo Voronezh. ped. in-ta Publ., 1999, pp. 127–134. (In Russian).
• Phillips S. J., Anderson R. P., Schapire R. E. Maximum Entropy Modeling of Species Geographic Distributions. Ecological Modeling, 2006, vol. 190, iss. 3–4, pp. 231–259. DOI: 10.1016/j.ecolmodel.2005.03.026 (In English).
• Phillips S. J., Dudík М. Modeling of Species Distributions with Maxent: New Extensions and a Comprehensive Evaluation. Ecography, 2008, vol. 31, iss. 2, pp. 161–175. DOI: 10.1111/j.0906-7590.2008.5203.x (In English).
• Poggio L., Sousa L. M., Batjes N. H., Heuvelink G. M., Kempen B., Ribeiro E., Rossiter D. SoilGrids 2.0: Producing Soil Information for the Globe with Quantified Spatial Uncertainty. Soil, 2021, vol. 7, iss. 1, pp. 217–240. DOI: 10.5194/soil-7-217-2021 (In English).
• Rafuse D. J. A Maxent Predictive Model for Hunter-Gatherer Sites in the Southern Pampas, Argentina. Open Quaternary, 2021, vol. 7, no. 6, pp. 1–21. DOI: 10.5334/oq.97 (In English).
• Sarychev D. V., Zemtsov G. L., Fabritsius E. V. [Identification of Archaeological Sites of the Late Roman Period in the Lipetsk Region Using the Maximum Entropy Method]. Geoinformatsionnoye kartografirovaniye v regionakh Rossii: sb. nauch. statey [Geoinformation Mapping in the Regions of Russia: A Collection of Sci. Articles]. Voronezh: Tsifrovaya poligrafiya Publ., 2020, pp. 302–308. (In Russian).
• Sarychev D. V., Zemtsov G. L., Fabritsius E. V. [Modeling the Location of Archaeological Sites by the Maximum Entropy Method (On the Example of the Late Roman Settlements in theLipetsk Region)]. Arkheologiya i geoinformatika. Chetvertaya Mezhdunar. konf. Tezisy dokladov [Archaeology and Geoinformatics. Fourth International Conf. Abstracts of Reports]. Moscow: IA RAN Publ., 2019, pp. 85–86. (In Russian).
• Stepinski T., Jasiewicz J. Geomorphons — A New Approach to Classification of Landform. Proceedings of Geomorphometry. Redlands: Esri Press, 2011, pp. 109–112. (In English).
• Verhagen P., Drăguţ L. Object-Based Landform Delineation and Classification from Dems for Archaeological Predictive Mapping. Journal of Archaeological Science, 2012, vol. 39, no. 3, pp. 698–703. DOI: 10.1016/j.jas.2011.11.001 (In English).
• Vostochnaya Evropa v seredine I tysyacheletiya n. e. [Eastern Europe in the Middle of the 1^st Millennium AD]. Moscow: Institut arkheologii RAN Publ., 2007. (Early Slavonic world. Archeology of the Slavs and their neighbors: Series of scientific publications; iss. 9). (In Russian).
• Wachtel I., Zidon R., Garti S., Shelach-Lavi G. Predictive Modeling for Archaeological Site Locations: Comparing Logistic Regression and Maximal Entropy in North Israel and North-East China. Journal of Archaeological Science, 2018, no. 92, pp. 28–36. DOI: 10.1016/j.jas.2018.02.001 (In English).
• Wollan A. K., Bakkestuen V., Kauserud H., Gulden G., Halvorsen R. Modelling and Predicting Fungal Distribution Patterns Using Herbarium Data. Journal of Biogeography, 2008, vol. 35, iss. 12, pp. 2298–2310. DOI: 10.1111/j.1365-2699.2008.01965.x (In English).
• Yamazaki D., Ikeshima D., Tawatari R. et al. A High Accuracy Map of Global Terrain Elevations. Geophysical Research Letters, 2017, vol. 44, iss. 11, pp. 5844–5853. DOI: 10.1002/2017GL072874 (In English).
• Yaworsky P. M., Vernon K. B., Spangler J. D., Brewer S. C., Codding B. F. Advancing Predictive Modeling in Archaeology: An Evaluation of Regression and Machine Learning Methods on the Grand Staircase-Escalante National Monument. PloS ONE, 2020, vol. 15, iss. 10, p. e0239424. DOI: 10.1371/journal.pone.0239424 (In English).
• Zaitseva E. A. [Forecasting the Location of Archeological Objects Using GIS and Remote Sensing of the Earth] Trudy IV (XX) Vserossiyskogo arkheologicheskogo s”yezda v Kazani: sb. nauch. statey. V 5 t. [Proceedings of the 4^th (20^th) All-Russian Archaeological Congress in Kazan: A Collection of Sci. Articles. In 5 vols.]. Kazan: Otechestvo Publ., 2014, vol. 4, pp. 399–401. (In Russian).
• Zemtsov G. L., Sarychev D. V., Fabricius E. V., Goncharov V. O. [Population of the Upper Don Region in the Late Roman Time: Victim or Aggressor?]. Stratum plus. Arkheologiya i kul’turnaya antropologiya [Stratum plus. Archaeology and Cultural Anthropology], 2019, no. 4, pp. 257–264. (In Russian).
• Zemtsov G. L., Sarychev D. V., Fabritsius E. V. [Cartography of Late Roman Settlements in the Basin of the River Bystraya Sosna]. Gumanitarnyye issledovaniya Tsentral’noy Rossii [Humanities Researches of the Central Russia], 2019, no. 4 (13), pp. 7–10. DOI: 10.24411/2541-9056-2019-00001 (In Russian).
• Zemtsov G. L., Sarychev D. V., Goncharov V. O., Fabritsius E. V. [Plyshchan Microregion of Settlements of the Late Roman Period in the Upper Don Region]. Rossiiskaia arkheologiia [Russian Archaeology], 2020, no. 2, pp. 60–71. DOI: 10.31857/S086960630005677-3 (In Russian).
• Zevenbergen L. W., Thorne C. R. Quantitative Analysis of Land Surface Topography. Earth Surface Processes and Landforms, 1987, vol. 12, iss. 1, pp. 47–56. DOI: 10.1002/ESP.3290120107 (In English).