CoChat
Sign Up
Cited by 29

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Towards the use of artificial intelligence deep learning networks for detection of archaeological sites

Karamitrou, Alexandra, Sturt, Fraser, Bogiatzis, Petros, Beresford-Jones, David·2022·Surface Topography: Metrology and Properties
DOI 10.1088/2051-672x/ac9492
Open this paper in CoChat — free account

Abstract

While remote sensing data have long been widely used in archaeological prospection over large areas, the task of examining such data is time consuming and requires experienced and specialist analysts. However, recent technological advances in the field of artificial intelligence (AI), and in particular deep learning methods, open possibilities for the automated analysis of large areas of remote sensing data. This paper examines the applicability and potential of supervised deep learning methods for the detection and mapping of different kinds of archaeological sites comprising features such as walls and linear or curvilinear structures of different dimensions, spectral and geometrical properties. Our work deliberately uses open-source imagery to demonstrate the accessibility of these tools. One of the main challenges facing AI approaches has been that they require large amounts of labeled data to achieve high levels of accuracy so that the training stage requires significant computational resources. Our results show, however, that even with relatively limited amounts of data, simple eight-layer, fully convolutional network can be trained efficiently using minimal computational resources, to identify and classify archaeological sites and successfully distinguish them from features with similar characteristics. By increasing the number of training sets and switching to the use of high-performance computing the accuracy of the identified areas increases. We conclude by discussing the future directions and potential of such methods in archaeological research.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1088/2051-672x/ac9492

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • By establishing the capabilities of human satellite surveyors using freely available imagery under ideal conditions, the paper provides an important point of comparison for machine learning results, especially those conducted in south central Peru and other desert regions.

    “By establishing the capabilities of human satellite surveyors using freely available imagery under ideal conditions, we provide an important point of comparison for machine learning results–especially those conducted in south central Peru and other desert regions [58].”

    From Unstructured satellite survey detects up to 20% of archaeological sites in coastal valleys of southern Peru (2024) · cites this paper as [58]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 60

  1. Anichini, 2021, The automatic recognition of ceramics from only one photo: The ArchAIDE app, Journal of Archaeological Science: Reports., 36, 102788
  2. Agapiou, 2021, Detection of Archaeological surface ceramics using deep learning image-based methods and very high-resolution UAV imageries, Land, 10, 1365, 10.3390/land10121365 · DOI
  3. Badrinarayanan, 2017, SegNet: a deep convolutional encoder-decoder architecture for image segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 39, 2481, 10.1109/TPAMI.2016.2644615 · DOI · Paper page
  4. Baxter, 2009, Archaeological data analysis and fuzzy clustering, Archaeometry, 51, 1035, 10.1111/j.1475-4754.2008.00449.x · DOI
  5. Beresford-Jones, 2013, 10.5871/bacad/9780197264768.001.0001 · DOI
  6. Bewley, 2002, Aerial archaeology: Developing Future Practice, IOS Press, NATO Science Series, I: Life and Behavioural Sciences, 337, 311
  7. Bikoulis, 2018, Ancient pathways and geoglyphs in the sihuas valley of southern peru, Antiquity, 92, 1377, 10.15184/aqy.2018.197 · DOI
  8. Bonhage, 2021, A modified Mask region-based convolutional neural network approach for the automated detection of archaeological sites on high-resolution light detection and ranging-derived digital elevation models in the north german lowland, Archaeological Prospection, 28, 177, 10.1002/arp.1806 · DOI · Paper page
  9. Cadwallader, 2018b, Algunas contribuciones a la comprensión de la transición Paracas-Nasca, Samaca, valle bajo de Ica, Boletín de Arqueología de la Pontificia Universidad Católica del Perú, 25, 147, 10.18800/boletindearqueologiapucp.201801.005 · DOI
  10. Cadwallader, 2015, Dating the dead: new radiocarbon dates from the lower ica valley, south coast peru, Radiocarbon, 57, 765, 10.2458/azu_rc.57.18343 · DOI
  11. Cadwallader, 2018a, Doubts about how the middle horizon collapsed (c. AD 1000) and other insights from the looted cemeteries of the lower ica valley on the south coast of peru, Journal of Field Archaeology, 43, 316, 10.1080/00934690.2018.1464306 · DOI
  12. Cao, 2009, An initialization method for the K-Means algorithm using neighborhood model, Comput. Math. Appl., 58, 474, 10.1016/j.camwa.2009.04.017 · DOI
  13. Caspari, 2019, Convolutional neural networks for archaeological site detection—Finding ‘princely’ tombs, J. Archaeolog. Sci., 110, 10.1016/j.jas.2019.104998 · DOI
  14. Chi, 2016, Big data for remote sensing: challenges and opportunities, Proc. IEEE, 104, 2207, 10.1109/JPROC.2016.2598228 · DOI
  15. Cigna, 2018, Tracking human-induced landscape disturbance at the nasca lines UNESCO world heritage site in peru with COSMO-SkyMed InSAR, Remote Sens., 2018, 572, 10.3390/rs10040572 · DOI
  16. Dey, 2016, Machine learning algorithms: a review, International Journal of Computer Science and Information Technologies, 7, 1174
  17. Flores, 2019, Computer algorithm for archaeological projectile points automatic classification, Journal on Computing and Cultural Heritage, 12, 1, 10.1145/3300972 · DOI
  18. Fukushima, 1980, Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biol. Cybern., 36, 193, 10.1007/BF00344251 · DOI · Paper page
  19. Fukushima, 1983, Neocognitron: a neural network model for a mechanism of visual pattern recognition, IEEE Transactions on Systems, Man, and Cybernetics. SMC-, 13, 826, 10.1109/TSMC.1983.6313076 · DOI
  20. Garcia-Garcia, 2018, A survey on deep learning techniques for image and video semantic segmentation, Appl. Soft Comput., 70, 41, 10.1016/j.asoc.2018.05.018 · DOI
  21. Goodfellow, 2016, Chapter 7: regularization for deep learning
  22. Gregory, 2019, Searching data: a review of observational data retrieval practices in selected disciplines, J Assoc Inf Sci Tech, 70, 419, 10.1002/asi.24165 · DOI
  23. Haburaj, 2017, Geo-statistical methods to analyse changes in pre-Hispanic settlement patterns in the Río Ica catchment, Peru, Journal of Archaeological Science: Reports, 12, 272, 10.1016/j.jasrep.2017.01.033 · DOI
  24. Ho, 1995, Random decision forests, 1, 278, 10.1109/ICDAR.1995.598994 · DOI
  25. Ho, 1998, The random subspace method for constructing decision forests, IEEE Trans. Pattern Anal. Mach. Intell., 20, 832, 10.1109/34.709601 · DOI
  26. Holstein, 1927, Chan-chan: capital of the great chimu, Geographical Review, 17, 36, 10.2307/208132 · DOI
  27. Hubel, 1959, Receptive fields of single neurones in the cat’s striate cortex, J. Physiol., 148, 574, 10.1113/jphysiol.1959.sp006308 · DOI · Paper page
  28. Jin, 2011, K-Means clustering, 10.1007/978-0-387-30164-8_425 · DOI
  29. Kao, 2004, Decomposition methods for linear support vector machines, Neural Comput., 16, 1689, 10.1162/089976604774201640 · DOI · Paper page
  30. Kazimi, 2019, Object instance segmentation in digital terrain models, 10.1007/978-3-030-29891-3_43 · DOI
  31. Kintigh, 1982, Heuristic approaches to spatial analysis in archaeology, American Antiquity, 47, 31, 10.2307/280052 · DOI
  32. Küçükdemirci, 2020, Deep learning based automated analysis of archaeo-geophysical images, 10.1002/arp.1763 · DOI
  33. Lambers, 2018, Airborne and spaceborne remote sensing and digital image analysis in archaeology, 109, 10.1007/978-3-319-25316-9_7 · DOI
  34. Lambers, 2019, Integrating remote sensing, machine learning, and citizen science in dutch archaeological prospection, Remote Sensing, 11, 794, 10.3390/rs11070794 · DOI
  35. LeCun, 1989, Backpropagation applied to handwritten zip code recognition, Neural Comput., 1, 541, 10.1162/neco.1989.1.4.541 · DOI · Paper page
  36. Long, 2015, Fully convolutional networks for semantic segmentation, 3431, 10.1109/CVPR.2015.7298965 · DOI · Paper page
  37. Menze, 2012, Mapping patterns of long-term settlement in Northern Mes-opotamia at a large scale, Proc. Natl Acad. Sci. USA, 109, E778, 10.1073/pnas.1115472109 · DOI · Paper page
  38. Minaee, 2021, Image Segmentation using deep learning: a survey, IEEE transactions on pattern analysis and machine intelligence, 44, 3523, 10.1109/TPAMI.2021.3059968 · DOI · Paper page
  39. Moseley, 1975, . Chan chan: andean alternative of the preindustrial city, Science., 187, 219, 10.1126/science.187.4173.219 · DOI
  40. Mossun, 2013, Flights into the Past. Aerial photography, photo interpretation and mapping for archaeology, 10.11588/propylaeumdok.00002009 · DOI
  41. Odena, 2016, Deconvolution and Checkerboard Artifacts, Distill, 10.23915/distill · DOI
  42. Orengo, 2020, Automated detection of archaeological mounds using machine-learning classification of multisensor and multitemporal satellite data, Proc. of the National Academy of Sciences of the United States of America, 10.1073/pnas.2005583117 · DOI · Paper page
  43. Pawlowicz, 2021, Applications of deep learning to decorated ceramic typology and classification: A case study using Tusayan White Ware from Northeast Arizona, J. Archaeolog. Sci., 130, 10.1016/j.jas.2021.105375 · DOI
  44. Protzen, 2004, Los colores de tambo colorado: una reevaluación, BOLETÍN DE ARQUEOLOGÍA PUCP, 8, 267, 10.18800/boletindearqueologiapucp.200401.013 · DOI
  45. Qi, 2017, An effective and efficient hierarchical K-means clustering algorithm, Int. J. Distrib. Sens. Netw., 13, 8, 10.1177/1550147717728627 · DOI
  46. Rayne, 2020, Detecting change at archaeological sites in north africa using open-source satellite imagery, Remote Sensing, 12, 3694, 10.3390/rs12223694 · DOI · Paper page
  47. Reeves, 1936, Aerial photography and archaeology, American Antiquity, 2, 102, 10.2307/275881 · DOI
  48. Ruggles, 2015, Geoglyphs of the peruvian coast, 10.1007/978-1-4614-6141-8_76 · DOI
  49. Russakovsky, 2015, ImageNet large scale visual recognition challenge, Int. J. Comput. Vision, 115, 211, 10.1007/s11263-015-0816-y · DOI · Paper page
  50. Sagi, 2020, Artificial intelligence for ocean science data integration: Current state, gaps, and way forward, Elementa., 10.1525/ELEMENTA.418 · DOI
  51. Schmidhuber, 2015, Deep learning in neural networks: an overview, Neural Netw., 61, 85, 10.1016/j.neunet.2014.09.003 · DOI · Paper page
  52. Smailes, 2011, Building chan chan: a project management perspective, Latin American Antiquity, 22, 37, 10.7183/1045-6635.22.1.37 · DOI
  53. Somrak, 2020, Learning to classify structures in ALS-derived visualizations of ancient maya settlements with CNN, Remote Sensing, 12, 2215, 10.3390/rs12142215 · DOI
  54. Soroush, 2020, Deep learning in archaeological remote sensing: automated qanat detection in the kurdistan region of Iraq, Remote Sensing, 12, 500, 10.3390/rs12030500 · DOI
  55. Tamiminia, 2020, Google earth engine for geo-big data applications: a meta-analysis and systematic review, ISPRS J. Photogramm. Remote Sens., 164, 152, 10.1016/j.isprsjprs.2020.04.001 · DOI
  56. Trier, 2018, Using deep neural networks on airborne laser scanning data: Results from a case study of semi‐automatic mapping of archaeological topography on Arran, Scotland, Archaeological Prospection, 26, 2, 10.1002/arp.1731 · DOI
  57. Ulku, 2022, A survey on deep learning-based architectures for semantic segmentation on 2D images, Applied Artificial Intelligence, 36, 2032924, 10.1080/08839514.2022.2032924 · DOI
  58. Verschoof-van der Vaart, 2020, Combining deep learning and location-based ranking for large-scale archaeological prospection of LiDAR data from The Netherlands, ISPRS International Journal of Geo-Information, 9, 293, 10.3390/ijgi9050293 · DOI · Paper page
  59. Verschoof-van der Vaart, 2021, Using carcassonnet to automatically detect and trace hollow roads in LiDAR data from the Netherlands, Journal of Cultural Heritage, 47, 143, 10.1016/j.culher.2020.10.009 · DOI
  60. Yu, 2021, Matrix SegNet: a practical deep learning framework for landslide mapping from images of different areas with different spatial resolutions, Remote Sensing, 13, 3158, 10.3390/rs13163158 · DOI

Cited by

Sorted by citations

Metadata

Authors
Karamitrou, A., Sturt, F., Bogiatzis, P., & Beresford-Jones, D.
ORCID
Venue
Surface Topography: Metrology and Properties
Publisher
IOP Publishing
Published
2022-10-03
Volume
10
Issue
4
Pages
044001
ISSN
2051-672X
DOI
10.1088/2051-672x/ac9492
Cited by
29
References
7
Licence
Funders
  • Daphne Jackson Trust
  • National Environment Research Council

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.

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