Explainable artificial intelligence with negative sample optimization for archaeological site prediction in Surkhandarya Uzbekistan
Source abstract
Abstract
Archaeological Predictive Model is crucial for efficient site identification but faces challenges like high uncertainty in negative samples, limited accuracy, and simplistic analyses of site-environment interactions. This study, based on 189 Kushan-period sites in the Surkhandarya Region of Uzbekistan, introduces a kernel density estimation (KDE)-based strategy to improve negative sample selection. Five machine learning models, incorporating geomorphological, climatic, and terrain variables, were assessed for predicting site locations. SHAP (SHapley Additive exPlanations) analysis was used to investigate the relationship between environmental factors and settlement patterns. Results show that the proposed strategy significantly enhances predictive performance, with AUC and accuracy increasing by 12.1% and 14%, respectively. Random Forest outperformed other models in robustness across various conditions. Land cover, slope, and precipitation emerged as key factors influencing site distribution. This research offers a novel framework for archaeological prospection, combining machine learning with environmental analysis.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Archaeological Research and Protection · Image Processing and 3D Reconstruction · Archaeology and ancient environmental studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (72)
Show source-provided references
1. Cacciari, I., Pocobelli, G. F. Machine learning: A novel tool for archaeology. Handb. Cult. Herit. Anal. [Internet]. Springer, Cham; p. 961–1002 (2022).10.1007/978-3-030-60016-7_33 ↗
2. Luo, L., Wang, X., Guo, H., Jia, X. & Fan, A. Earth observation in archaeology: A brief review. Int. J. Appl. Earth Obs. Geoinf. 116, 103169 (2023).
3. Zhen, Q. Exploring the early anthropocene: Implications from the long-term human–climate interactions in early China. Mediterr. Archaeol. Archaeom. 21, 133–133 (2021).
4. Lloyd, C. D., Atkinson, P. M. Archaeology and geostatistics. J Archaeol Sci. Acad. Press. 31,151–65 (2004).10.1016/j.jas.2003.07.004 ↗
5. Löwenborg, D. Using geographically weighted regression to predict site representativity. Mak Hist Interactive, Proceedings CAA Conf 37th Annu Meet. Williamsburg, Virginia. p. 203--215 (2009).
6. Matyukira, C., Mhangara, P. Advancement in the application of geospatial technology in archaeology and cultural heritage in south africa: A scientometric review. Remote Sens. Multidisciplinary Digital Publishing Institute. 15, 4781 (2023).10.3390/rs15194781 ↗
7. Kvamme, K. Computer processing techniques for regional modeling of archaeological site locations (1983).
8. Kvamme, K. L. One-sample tests in regional archaeological analysis: New possibilities through computer technology. Am. Antiq. 55, 367–381 (1990).10.2307/281655 ↗
9. Kvamme, K. L. A predictive site location model on the high plains: An example with an independent test. Plains Anthropol. Routledge (1992).10.1080/2052546.1992.11909662 ↗
10. Vanacker, V. et al. Using Monte Carlo simulation for the environmental analysis of small archaeologic datasets, with the mesolithic in northeast Belgium as a case study. J. Archaeol. Sci. 28, 661–669 (2001).10.1006/jasc.2001.0654 ↗
11. Bauer, A., Nicoll, K., Park, L. & Matney, T. Archaeological site distribution by geomorphic setting in the southern lower Cuyahoga River Valley, northeastern Ohio: Initial observations from a GIS database. Geoarchaeology 19, 711–729 (2004).10.1002/gea.20021 ↗
12. Finke, P. A., Meylemans, E. & Van De Wauw, J. Mapping the possible occurrence of archaeological sites by Bayesian inference. J. Archaeol. Sci. 35, 2786–2796 (2008).10.1016/j.jas.2008.05.004 ↗
13. Jarosław, J. & Hildebrandt-Radke, I. Using multivariate statistics and fuzzy logic system to analyse settlement preferences in lowland areas of the temperate zone: an example from the Polish Lowlands. J. Archaeol. Sci. 36, 2096–2107 (2009).10.1016/j.jas.2009.06.004 ↗
14. Verhagen, P. & Whitley, T. G. Integrating Archaeological Theory and Predictive Modeling: a Live Report from the Scene. J. Archaeol. Method Theory 19, 49–100 (2012).10.1007/s10816-011-9102-7 ↗
15. Balla, A., Pavlogeorgatos, G., Tsiafakis, D. & Pavlidis, G. Modelling archaeological and geospatial information for burial site prediction, identification and management. Int J. Herit. Digit Era 2, 585–609 (2013).10.1260/2047-4970.2.4.585 ↗
16. Balla, A., Pavlogeorgatos, G., Tsiafakis, D. & Pavlidis, G. Recent advances in archaeological predictive modeling for archeological research and cultural heritage management. Mediterr. Archaeol. Archaeom. 14, 143–143 (2014).
17. Li, L., Nahayo, L., Habiyaremye, G. & Christophe, M. Applicability and performance of statistical index, certain factor and frequency ratio models in mapping landslides susceptibility in Rwanda. GEOCARTO Int. 37, 638–656 (2022).10.1080/10106049.2020.1730451 ↗
18. Wang, Y., Fang, Z., Hong, H., Costache, R. & Tang, X. Flood susceptibility mapping by integrating frequency ratio and index of entropy with multilayer perceptron and classification and regression tree. J. Environ. Manag. 289, 112449 (2021).10.1016/j.jenvman.2021.112449 ↗
19. Ozdemir, A. GIS-based groundwater spring potential mapping in the Sultan Mountains (Konya, Turkey) using frequency ratio, weights of evidence and logistic regression methods and their comparison. J. Hydrol. 411, 290–308 (2011).10.1016/j.jhydrol.2011.10.010 ↗
20. Phillips, S. J., Anderson, R. P., Dudik, M., Schapire, R. E., Blair, M. E. Opening the black box: An open-source release of maxent. ECOGRAPHY. Hoboken: Wiley. 40, 887–93 (2017),10.1111/ecog.03049 ↗
21. Fourcade Y., Besnard A. G., Secondi J. Paintings predict the distribution of species, or the challenge of selecting environmental predictors and evaluation statistics. Glob Ecol Biogeogr. Hoboken: Wiley 27, 245–56 (2018).10.1111/geb.12684 ↗
22. Tonini, M. An Explorative Application of Random Forest Algorithm for Archaeological Predictive Modeling. A Swiss Case Study. J. Comput. Appl. Archaeol. 4, 110–125 (2021).
23. Noviello, M., Cafarelli, B., Calculli, C., Sarris, A. & Mairota, P. Investigating the distribution of archaeological sites: Multiparametric vs probability models and potentials for remote sensing data. Appl. Geogr. 95, 34–44 (2018).10.1016/j.apgeog.2018.04.005 ↗
24. 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. J. Archaeol. Sci. 92, 28–36 (2018).10.1016/j.jas.2018.02.001 ↗
25. Luo, L., Wang, X. & Guo, H. Transitioning from remote sensing archaeology to space archaeology: Towards a paradigm shift. Remote Sens Environ. 308, 114200 (2024).10.1016/j.rse.2024.114200 ↗
26. Luo, L., Wang, X., Guo, H. Remote sensing archaeology: The next century. The Innovation. Elsevier. 3 (2022).10.1016/j.xinn.2022.100335 ↗
27. Wang, S., Han, W., Zhang, X., Li, J. & Wang, L. Geospatial remote sensing interpretation: From perception to cognition. Innov. Geosci. Innov. Geosci. 2, 100056 (2024).10.59717/j.xinn-geo.2024.100056 ↗
28. Nsanziyera, A. F. et al. Remote-sensing data-based Archaeological Predictive Model (APM) for archaeological site mapping in the desert area, South Morocco. Comptes Rendus Géosci. 350, 319–330 (2018).10.1016/j.crte.2018.06.010 ↗
29. Cuthbertson, P. et al. Finding karstic caves and rockshelters in the Inner Asian mountain corridor using predictive modelling and field survey. PLOS One Public Libr. Sci. 16, e0245170 (2021).10.1371/journal.pone.0245170 ↗
30. Li, L., Li, Y., Chen, X., Sun, D. A Prediction Study on Archaeological Sites Based on Geographical Variables and Logistic Regression—A Case Study of the Neolithic Era and the Bronze Age of Xiangyang. Sustainability. Multidisciplinary Digital Publishing Institute. 14, 15675 (2022).10.3390/su142315675 ↗
31. Carleton, W. C., Conolly, J. & Ianonne, G. A locally-adaptive model of archaeological potential (LAMAP). J. Archaeol. Sci. 39, 3371–3385 (2012).10.1016/j.jas.2012.05.022 ↗
32. Wang, Y., Shi, X., Oguchi, T. Archaeological Predictive Modeling Using Machine Learning and Statistical Methods for Japan and China. ISPRS Int J Geo-Inf. Multidisciplinary Digital Publishing Institute. 12, 238 (2023).10.3390/ijgi12060238 ↗
33. Brouwer Burg, M., Peeters, H., Lovis, W. A., editors. Uncertainty and sensitivity analysis in archaeological computational modeling [Internet]. Cham: Springer International Publishing. (2016).10.1007/978-3-319-27833-9 ↗
34. Graves, D. The use of predictive modelling to target Neolithic settlement and occupation activity in mainland Scotland. J. Archaeol. Sci. 38, 633–656 (2011).10.1016/j.jas.2010.10.016 ↗
35. Yan, L. et al. Towards an Operative Predictive Model for the Songshan Area during the Yangshao Period. ISPRS Int J Geo-Inf. Multidisciplinary Digital Publishing Institute. 10, 217. (2021).10.3390/ijgi10040217 ↗
36. Kempf, M. The application of GIS and satellite imagery in archaeological land-use reconstruction: A predictive model?. J. Archaeol. Sci. Rep. 25, 116–128 (2019).
37. Yang H. et al. Predicting ancient city sites using GEE coupled with geographic element features and temporal spectral features: A case study of the Neolithic and Bronze Age of the Jianghan region, China. Npj Herit. Sci. Nature Publishing Group. 13, 1–15 (2025).10.1038/s40494-025-01557-6 ↗
38. Klehm, C. et al. Toward archaeological predictive modeling in the Bosutswe region of Botswana: Utilizing multispectral satellite imagery to conceptualize ancient landscapes. J. Anthropol. Archaeol. 54, 68–83 (2019).10.1016/j.jaa.2019.02.002 ↗
39. Cui, J. Mapping landscape in Longshan period’s hierarchical society (3000–2000BCE) of North Loess Plateau: from archaeological predictive model to GIS spatial analysis. Herit. Sci. 12, 78 (2024).10.1186/s40494-024-01194-5 ↗
40. Flores-Aqueveque, V. et al. Machine learning-based identification of geomorphological units in Quintero Bay (32°S) and its implications for the search for early drowned archaeological sites on the western coast of South America. Quat. Int 712, 109585 (2024).10.1016/j.quaint.2024.11.003 ↗
41. Zhu, X., Chen, F., Guo, H. A Spatial Pattern Analysis of Frontier Passes in China’s Northern Silk Road Region Using a Scale Optimization BLR Archaeological Predictive Model. Heritage. Multidisciplinary Digital Publishing Institute 1, 15–32 (2018).10.3390/heritage1010002 ↗
42. Chefaoui, R. M. & Lobo, J. M. Assessing the effects of pseudo-absences on predictive distribution model performance. Ecol. Model. 210, 478–486 (2008).10.1016/j.ecolmodel.2007.08.010 ↗
43. Vojteková, J. et al. Prediction of potential occurrence of historical objects with defensive function in Slovakia using machine learning approach. Sci Rep. Nature Publishing Group. 14, 30350 (2024).10.1038/s41598-024-82290-1 ↗
44. Li, G. et al. GIS and machine learning models target dynamic settlement patterns and their driving mechanisms from the Neolithic to Bronze Age in the northeastern Tibetan Plateau. Remote Sens. Multidisciplinary Digital Publishing Institute. 16, 1454 (2024).10.3390/rs16081454 ↗
45. Li, C., et al. Interpretable foundation models as decryptors peering into the Earth system. The Innovation. Elsevier. 5, (2024).10.1016/j.xinn.2024.100682 ↗
46. Różkowski, J., Rzętała, M. Uzbekistan’s aquatic environment and water management as an area of interest for hydrology and thematic tourism. J. Environ. Manag. Tour. ASERS Ltd. 12, 642–53 (2021).10.14505//jemt.v12.3(51).04 ↗
47. TANG Yun-peng, W. A. N. G. J. ian-xin The Main Results of Archaeological Work in the Surkhandarya Basin, Uzbekistan: Archaeolgical Observation of Yuezhi and Kushan Culture. J. Northwest Univ. (Philos. Soc. Sci. Ed.) 51, 80–92 (2021).
48. Takaku, J., Tadono, T., Tsutsui, K. Generation of high resolution global DSM from ALOS PRISM. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. Copernicus GmbH XL–4, 243–8 (2014).10.5194/isprsarchives-XL-4-243-2014 ↗
49. Yokoyama, R., Shirasawa, M. & Pike, R. J. Visualizing topography by openness:A new application of image processing to digital elevation models. Photogramm. Eng. Remote Sens. 68, 257–266 (2002).
50. Guisan, A., Weiss, S. B. & Weiss, A. D. GLM versus CCA spatial modeling of plant species distribution. Plant Ecol. 143, 107–122 (1999).10.1023/A:1009841519580 ↗
51. Riley, S. J., DeGloria, S. D., Elliot, R. A Terrain Reggedness Index that Quantifies Topographic Heterogeneity. Intermt. J. Sci. 5–5. (1999).
52. Feng, Z., Yang, Y., Zhang, D. & Tang, Y. Natural environment suitability for human settlements in China based on GIS. J. Geogr. Sci. 19, 437–446 (2009).10.1007/s11442-009-0437-x ↗
53. Moore, I. D., Grayson, R. B. & Ladson, A. R. Digital terrain modelling: A review of hydrological, geomorphological, and biological applications. Hydrol. Process 5, 3–30 (1991).10.1002/hyp.3360050103 ↗
54. Cheng, H. et al. Climate variations of central Asia on orbital to millennial timescales. Sci. Rep. Nature Publishing Group. 6, 36975. (2016).10.1038/srep36975 ↗
55. Wu, H., Wang, X., Wang, X., Zhang, L. & Dong, S. Predictive modeling for neolithic settlements in the Lingnan Region, South China. J. Archaeol. Sci. Rep. 49, 103992 (2023).
56. Oonk, S., Spijker, J. A supervised machine-learning approach towards geochemical predictive modelling in archaeology. J. Archaeol. Sci. Academic Press. 59, 80–88 (2015).10.1016/j.jas.2015.04.002 ↗
57. Elliot, T., Morse, R., Smythe, D., Norris, A. Evaluating machine learning techniques for archaeological lithic sourcing: A case study of flint in Britain. Sci Rep. Nature Publishing Group. 11, 10197 (2021).10.1038/s41598-021-87834-3 ↗
58. Iban, M. C., Sekertekin, A. Machine learning based wildfire susceptibility mapping using remotely sensed fire data and GIS: A case study of Adana and Mersin provinces, Turkey. Ecol Inform. Amsterdam: Elsevier. 69, 101647 (2022).10.1016/j.ecoinf.2022.101647 ↗
59. Hong, H., Liu, J. & Zhu, A.-X. Modeling landslide susceptibility using LogitBoost alternating decision trees and forest by penalizing attributes with the bagging ensemble. Sci. Total Environ. 718, 137231 (2020).10.1016/j.scitotenv.2020.137231 ↗
60. Tian, Y. et al. Evolution of influence ranges of Neolithic-Bronze Age cities in the Songshan Mountain region of central China based on GIS spatial analysis. REMOTE Sens. 14, (2022).10.3390/rs14225631 ↗
61. Comer, J. A., Comer, D. C., Dumitru, I. A., Priebe, C. E. & Patsolic, J. L. Sampling methods for archaeological predictive modeling: Spatial autocorrelation and model performance. J. Archaeol. Sci. Rep. 48, 103824 (2023).
62. Zhao, F. et al. Refined landslide susceptibility mapping in township area using ensemble machine learning method under dataset replenishment strategy. Gondwana Res. 131, 20–37 (2024).10.1016/j.gr.2024.02.011 ↗
63. Lan, X. et al. Prediction of the potential distribution and preservation of archaeological wooden artifacts in Yangzhou City, China. J. Cult. Herit. 71, 346–357 (2025).10.1016/j.culher.2024.12.008 ↗
64. Castiello, M. E. Computational and machine learning tools for archaeological site modeling [Internet]. Cham: Springer International Publishing. (2022).10.1007/978-3-030-88567-0 ↗
65. Wang, C. et al. The influences of the spatial extent selection for non-landslide samples on statistical-based landslide susceptibility modelling: A case study of Anhui province in China. Nat. Hazards 112, 1967–1988 (2022).10.1007/s11069-022-05252-8 ↗
66. Hong, H., Wang, D., Zhu, A.-X. & Wang, Y. Landslide susceptibility mapping based on the reliability of landslide and non-landslide sample. Expert Syst. Appl. 243, 122933 (2024).10.1016/j.eswa.2023.122933 ↗
67. Yang, S. et al. Sample size effects on landslide susceptibility models: A comparative study of heuristic, statistical, machine learning, deep learning and ensemble learning models with SHAP analysis. Comput Geosci. 193, 105723 (2024).10.1016/j.cageo.2024.105723 ↗
68. Dou, H., He, J., Huang, S., Jian, W., Guo, C. Influences of non-landslide sample selection strategies on landslide susceptibility mapping by machine learning. Geomat. Nat. Hazards Risk. Taylor & Francis. 14, 2285719 (2023).10.1080/19475705.2023.2285719 ↗
69. Jochim, M. A. Dots on the Map: Issues in the Archaeological Analysis of Site Locations. J. Archaeol. Method Theory 30, 876–894 (2023).10.1007/s10816-022-09580-8 ↗
70. 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. Lozano S, editor. PLOS ONE. Public Library of Science. 15, e0239424 (2020).10.1371/journal.pone.0239424 ↗
71. Mihu-Pintilie, A., Nicu, I. C. GIS-based Landform Classification of Eneolithic Archaeological Sites in the Plateau-plain Transition Zone (NE Romania): Habitation Practices vs. Flood Hazard Perception. Remote Sens. Multidisciplinary Digital Publishing Institute. 11, 915 (2019).10.3390/rs11080915 ↗
72. Trevisani, S., Teza, G. & Guth, P. L. Hacking the topographic ruggedness index. Geomorphology 439, 108838 (2023).10.1016/j.geomorph.2023.108838 ↗