Hostname: page-component-89b8bd64d-5bvrz Total loading time: 0 Render date: 2026-05-06T05:17:19.301Z Has data issue: false hasContentIssue false
  • English
  • Français

Machine Learning Arrives in Archaeology

Part of: Digital Reviews

Published online by Cambridge University Press:  20 May 2021

Simon H. Bickler
Simon H. Bickler*
Affiliation:
Bickler Consultants Ltd., 1/623 Manukau Rd., Epsom, Auckland 1023, New Zealand
*
(arch@bickler.co.nz, corresponding author)
Rights & Permissions [Opens in a new window]

Overview

Machine learning (ML) is rapidly being adopted by archaeologists interested in analyzing a range of geospatial, material cultural, textual, natural, and artistic data. The algorithms are particularly suited toward rapid identification and classification of archaeological features and objects. The results of these new studies include identification of many new sites around the world and improved classification of large archaeological datasets. ML fits well with more traditional methods used in archaeological analysis, and it remains subject to both the benefits and difficulties of those approaches. Small datasets associated with archaeological work make ML vulnerable to hidden complexity, systemic bias, and high validation costs if not managed appropriately. ML's scalability, flexibility, and rapid development, however, make it an essential part of twenty-first-century archaeological practice. This review briefly describes what ML is, how it is being used in archaeology today, and where it might be used in the future for archaeological purposes.

Keywords

machine learningtransfer learningheritage managementclassificationneural networks

Information

Type
Digital Review
Information
Advances in Archaeological Practice , Volume 9 , Issue 2 , May 2021 , pp. 186 - 191
Copyright
Copyright © The Author(s), 2021. Published by Cambridge University Press on behalf of Society for American Archaeology

MACHINE LEARNING IN ARCHAEOLOGY

Machine learning (ML) is gaining prominence in the media and in the academic literature. This review briefly describes what ML is, how it is being used in archaeology today, and where it might be used in the future for archaeological purposes. The rapid growth in the use of ML, due in large part to the increasing accessibility and capability of the algorithms, has meant that the number of publications far outpaces any attempt to cover this in a short article. The selected publications mentioned here demonstrate how diverse, vibrant, and innovative this research has become. This research also demonstrates some of the challenges of using ML, ranging from managing the sparse and complex datasets to systemic biases that can influence the results.

Machine learning describes the study and programming of algorithms allowing computers to learn from data and then make predictions from those data (see, for example, Shalev-Shwartz and Ben-David Reference Shalev-Shwartz and Ben-David2014). Broadly, ML uses statistical techniques to analyze a set of categorized “training” data to derive a series of mathematical classifiers (“descriptors” or “feature vectors”) for each data category. The resulting classification system ideally means that objects in each category are mathematically identifiable as distinct from objects in all other categories. This trained classification model finds the best set of mathematical “features” to reliably identify examples for the categories. In other words, the computer can use math to classify quantifiable objects into distinct groups (Figure 1).

FIGURE 1.

Schematic overview of the process of machine learning applied to archaeological data, showing an example of matching decorative patterns on historical ceramics.

Dunnell's (Reference Dunnell1971) Systematics in Prehistory was prescribed reading for many students, and it has long cemented classification as a central focus for archaeologists. ML takes many of the relatively familiar statistical techniques of classification—such as factor, discriminant, and cluster analyses—to another level. It does this by closing the loop on the construction of a classification schema based on a “known”—and large—set of data to test and tune the model. This makes the classification as internally consistent as possible. Less familiar algorithms, such as those associated with neural networks, add other methods to manage noise in the data, reliability, and efficiency in the models.

In short, given a known set of classified data, ML algorithms are “trained” to understand the mathematical rules underpinning that classification, which are then used to extract, classify, sort, and draw conclusions from a new set of related data. The data that can be analyzed includes all kinds of numeric and textual information, images, and spatial-temporal datasets. Digital data is all numbers to a computer!

MACHINE LEARNING FOR ARCHAEOLOGICAL DATA

Archaeological data is also probably better described as “slow data” (see, for example, Heitman et al. Reference Heitman, Worthy and Plog2017; Kansa and Kansa Reference Kansa and Kansa2016). Whereas “Big Data” approaches focus on managing data flowing in on a continuous or near-continuous basis, archaeological data can be very slow to create—sometimes taking years or decades—and is delivered in large “lumps” of complex contextualized information. ML provides the opportunity to process such “lumps” of data, create models from those data, and then use that analysis to interpret subsequent data. These methods enable not only the sorting and management of new data but also learning from the new data and the reincorporation of the results into more robust interpretations. ML works best on highly structured and large datasets, but there are ways of using it to explore the sparse and messy datasets archaeologists often obtain.

Although ML can be applied to a range of digital data, to date, archaeologists have broadly focused on the following types:

  • • Numerical and/or categorical data

  • • Textual data

  • • Images

  • • Geospatial data

As noted earlier, ML algorithms on numerical and categorical data are very much extensions of the traditional statistical techniques (Hörr et al. Reference Hörr, Lindinger and Brunnett2014). For example, the ML analysis of chemical data for provenience studies that rely on cluster and factor analysis can be less influenced by the statistical requirements of those algorithms and can be refined as new data becomes available (Hazenfratz Marks et al. Reference Hazenfratz Marks, Munita and Neves2017). Similarly, ML has been used for pattern classification of pottery styles (Bickler Reference Bickler2018a; Chetouani et al. Reference Chetouani, Treuillet, Exbrayat and Jesset2020; Romanengo et al. Reference Romanengo, Biasotti and Falcidieno2020).

Textual data have also been analyzed using ML, including the analysis of archaeological records to extract key information or develop more consistent data (Brandsen et al. Reference Brandsen, Verberne, Wansleeben, Lambers, Calzolari, Béchet, Blache, Choukri, Cieri, Declerck, Goggi, Isahara, Maegaard, Mariani, Mazo, Moreno, Odijk and Piperidis2020; Davis Reference Davis2020; Felicetti Reference Felicetti2017). More dramatically, ML techniques offer the possibility of automating the translation of ancient languages such as Egyptian hieroglyphs (e.g., FabriciusFootnote 1; Sanders Reference Sanders2018).

The processing of images using ML has been one of the most productive areas to date for archaeologists. The forms of the images vary from photographs to stylized drawings of archaeological objects. Typically, ML has been used to identify “objects” within images, describe rock art and structural elements of buildings (Kogou et al. Reference Kogou, Shahtahmassebi, Lucian, Liang, Shui, Zhang, Su and van Schaik2020; Prasomphan and Jung Reference Prasomphan and Jung2017; Tsigkas et al. Reference Tsigkas, Sfikas, Pasialis, Vlachopoulos and Nikou2020), and analyze designs as well as tool and vessel forms (e.g., Bevan et al. Reference Bevan, Li, Martinon-Torres, Green, Xia, Zhao, Zhao, Ma, Cao and Rehren2014; Gualandi et al. Reference Gualandi, Gattiglia and Anichini2021; Nash and Prewitt Reference Nash and Prewitt2016; Pawlowicz et al. Reference Pawlowicz, Downum and Terlep2017); to identify shell or animal bone (Bickler Reference Bickler2018b; Huffer and Graham Reference Huffer and Graham2018); and to document use wear and damage on tools and ecofacts (Byeon et al. Reference Byeon, Dominguez-Rodrigo, Arampatzis, Baquedano, Yravedra, González and Koumoutsakos2019; Cifuentes-Alcobendas and Domínguez-Rodrigo Reference Cifuentes-Alcobendas and Domínguez-Rodrigo2019; Grove and Blinkhorn Reference Grove and Blinkhorn2020).

ML processing roles therefore range from sorting and filtering archaeological images to improving the management or accessibility of image data for analysis (e.g., Engel et al. Reference Engel, Mangiafico, Issavi and Lukas2019) through to the creation of automated or semiautomated processes (where expert oversight is used alongside the ML algorithms) for classification of form, taphonomy, and function (e.g., Gualandi et al. Reference Gualandi, Gattiglia and Anichini2021). ML also can be used in the reconstruction of vessels based on pattern matching of shapes and decoration or as jigsaw-puzzle solvers (Cintas et al. Reference Cintas, Lucena, Fuertes, Delrieux, Navarro, González-José and Molinos2020; Felicetti et al. Reference Felicetti, Paolanti, Zingaretti, Pierdicca and Malinverni2021; Ostertag and Beurton-Aimar Reference Ostertag and Beurton-Aimar2020).

Another benefit of the ML approach is that multiple algorithms can automatically be applied to the same dataset at the same time to form competing classifications. In this way, the “best” algorithm, with appropriate parameters, can be determined. Such automated machine learning can be advantageous because most archaeologists will tend to use a limited range of statistical algorithms with which they are familiar rather than pick and choose from those that suit specific datasets.

The difficulties of creating models with limited training material available from archaeological situations can be mitigated using “transfer learning.” Pretrained models that extract relevant features from a general set of nonarchaeological images can be supplemented with a smaller library of preclassified images relevant to the specific task. This allows the model to create the most relevant descriptors for distinguishing archaeological features from each other (see Horton and Paunic Reference Horton and Paunic2017). Such “transfer learning” is likely to become a dominant way of building useful ML models for archaeology.

THE SEARCH FOR SITES

Perhaps the most active area for archaeologists using ML relates to geospatial data. Rarely does archaeology generate the large quantities of systematically coded data at a pace that makes ML so effective in commercial environments. The increasing availability of large-scale lidar, satellite, and aerial imagery on local, regional, and national scales, however, is transforming archaeology around the globe—particularly the searching and mapping of archaeological sites (Figure 2). ML algorithms can be used to process the geospatial data in the search for sites in diverse environments (Bonhage et al. Reference Bonhage, Eltaher, Raab, Breuß, Raab and Schneider2021; Caspari and Crespo Reference Caspari and Crespo2019; Davis Reference Davis2019; Davis, DiNapoli, et al. Reference Davis, DiNapoli and Douglass2020; Davis, Seeber, et al. Reference Davis, Seeber and Sanger2020; Evans and Hofer Reference Evans and Hofer2019; Guyot et al. Reference Guyot, Hubert-Moy and Lorho2018, Reference Guyot, Lennon, Lorho and Hubert-Moy2021; Orengo et al. Reference Orengo, Conesa, Garcia, Green, Madella and Petrie2020; Soroush et al. Reference Soroush, Mehrtash, Khazraee and Ur2020; Thabeng et al. Reference Thabeng, Merlo and Adam2019; Trier et al. Reference Trier, Salberg, Pilø, Matsumoto and Uleberg2018, Reference Trier, Cowley and Waldeland2019; Verschoof-van der Vaart and Lambers Reference Vaart, Wouter and Lambers2019; Verschoof-van der Vaart et al. Reference Vaart, Wouter, Lambers, Kowalczyk and Bourgeois2020).

FIGURE 2.

An illustrative fictional example of how machine learning may be applied to feature identification in geospatial data and the reconstruction of a site.

The construction of the ML models can help to identify the contribution of different variables that are useful predictors of where sites are found across landscapes (Sharafi et al. Reference Sharafi, Fouladvand, Simpson and Alvarez2016; Zheng et al. Reference Zheng, Tang, Ogundiran and Yang2020). The different scales in which these models can operate empower archaeologists when cataloguing heritage by thematic choices, morphology, and environmental context, which in turn makes for both better heritage management (e.g., Castiello and Tonini Reference Castiello and Tonini2019; Davis, Seeber, et al. Reference Davis, Seeber and Sanger2020; Jones and Bickler Reference Jones and Bickler2017) and more detailed research around the world (e.g., Caspari and Crespo Reference Caspari and Crespo2019; Freeland et al. Reference Freeland, Heung, Burley, Clark and Knudby2016).

These ML approaches to heritage landscapes can be used to assist in mitigating some of the difficulties of predictive modeling for cultural resource management (see, for example, Dore and Wandsnider Reference Dore, Wandsnider, Mehrer and Westcott2006). This includes methods to test the internal consistency of the ML predictions and to explore in more detail the relevant factors that contribute to the presence and absence of archaeological sites in a landscape. This can be critical in areas where physical access or visibility of archaeological sites is difficult.

BLACK BOXES

The complexity of the ML algorithms is significant and the amount of work to create new models is substantial. The result of this complexity, however, is often a “black box” approach that relies on a previously created classification model and a need to accept the applicability to new data without getting too concerned over the mathematics and its possible limitations (Figure 1).

For many archaeological applications where the ML is an assistant to more detailed work, such analysis may be more than adequate. Where the objectives might be to identify a range of new possibilities for the location of sites or to assist in sorting artifact types, the benefits of machine-assisted classification, checked by additional archaeological investigation such as fieldwork, can be significant.

Byeon and colleagues (Reference Byeon, Dominguez-Rodrigo, Arampatzis, Baquedano, Yravedra, González and Koumoutsakos2019:41), for example, in their analysis of cut marks on bones suggest that their model is more reliable than manual systems. Most ML models of archaeological data, however, are likely to be less reliable than those of expert traditional methodologies because they are as yet unable to manage the range of variation and inconsistencies of archaeological data. This may be offset by major time-saving and scalability benefits, which allow the experts to focus on the more difficult or contentious examples.

Typically, the most significant hurdle to constructing good ML models is that they work best when built on large databases of information, such as thousands of catalogued images or reliably sourced material, which can be difficult to achieve, especially on archaeological budgets and with the diversity of data that may be available. The nature of archaeologically recovered samples, with poor preservation, makes the task even more difficult because fragmentation and surface state (including erosion, patina, and vegetation coverage, for example) can affect the success of identification. Specialists can typically identify material with which ML models trained on idealized collections would struggle.

The implications of this are that managing the ML models’ misclassification, resulting in either targets being wrongly classified or not classified at all, should be part of the strategy for their use in archaeological situations. The algorithms usually offer a range of ways of establishing their mathematical robustness, but archaeologists still need to ensure that the results stand up to scrutiny in the real world.

AVOIDING BIAS

Another aspect of ML is that the models are very much a product of the data from which they are built. As a result, the models tend to classify according to the categories they know about, which makes them susceptible to (at least) two major forms of bias.

The first relates to a form of lumping an assemblage into previously determined categories. This means that rare and unusual objects can easily be missed by being grouped with a more common type. A ceramic vessel of similar shape to one of the modeled forms, for example, may look “normal” but could have an unusual surface treatment that would immediately be noted by an archaeologist.

A second form of bias, and probably the most common, is that the models cannot fully incorporate the variability of the features being classified. ML analyses are susceptible to missing the “forest for the trees” because the data used to train the models are often stripped of contextual information (especially in the case of images) or operate on a limited set of prechosen variables that may not include sufficient information to distinguish between important (that is, archaeologically relevant) classes.

ML techniques do have ways of checking “performance,” but these still rely on internal mathematical measures and require attention from archaeological research to ensure that they are delivering good results. Difficulties with ML have repeatedly been encountered outside of archaeology including exacerbating race and gender biases in commercial situations (Gebru Reference Gebru, Dubber, Pasquale and Das2020).

This sort of bias is of particular concern for archaeologists using ML on data associated with Indigenous communities. Optimization techniques, such as least-cost analysis, generally result in outcomes that are based on behavioral elements such as “energy” efficiencies. “Success” is therefore measured in terms of purportedly “scientific” measures. Archaeologists engaging with Indigenous communities that are using models based on acultural—or ethnocentric—assumptions can create interpretations that are stripped of cultural context and meaning. Increasingly, those assumptions are being challenged as measures of success, especially as Indigenous forms of inquiry focus on behaviors and outcomes rooted in cultural value systems (see, for example, Davis, DiNapoli, et al. Reference Davis, DiNapoli and Douglass2020; Douglass et al. Reference Douglass, Morales, Manahira, Fenomanana, Samba, Lahiniriko, Chrisostome, Vavisoa, Soafiavy, Justome, Leonce, Hubertine, Pierre, Tahirisoa, Colomb, Lovanirina, Andriankaja and Robison2019). Archaeologists bear the responsibility of ensuring that their research contributes to descendant cultures (e.g., Allen and Phillips Reference Allen, Phillips, Phillips and Allen2010; Solomon and Forbes Reference Solomon, Forbes, Phillips and Allen2010).

EVOLUTION OR REVOLUTION

Archaeologists are not likely to be replaced in the foreseeable future by an insurrection of archaeological robots. Harari (Reference Harari2017) has given us a 97% chance of keeping our jobs! The real revolution for archaeologists is less about ML and more about the fact that ML, along with other forms of analysis, will allow for the use of a larger—and rapidly expanding—corpus of archaeological data. This transformation is shifting both academic and cultural resource management inquiry. Many of its applications are evolutionary, greatly improving the types, scale, and complexity of analytic tools that archaeologists already use.

There is no doubt that ML can significantly aid identification of archaeological samples with the potential to draw upon an ever-improving and ever-expanding library of data. This makes sharing data from projects much more important. The reward for this is making identification of new data easier and more reliable, which offers advantages for not only research objectives but also cultural heritage, where improvements can have significant financial benefits. The revolution will be in integrating these outcomes into both academic and cultural resource management frameworks, which is a significant challenge given that archaeologists will have to become competent in managing this much richer and more diverse information (Kansa and Kansa Reference Kansa and Kansa2021).

Acknowledgments

I would like to thank Peter J. Cobb for providing me with the opportunity to write this article and for discussions. Dorothy Brown helped sort out the text and references, for which I am most grateful. My thanks to University of Hong Kong undergraduate student Agnes Pui Yee Sung for redrawing Figure 1. Thomas MacDiarmid built the 3D model for Figure 2 based on precolonial Māori archaeological sites. I acknowledge the incorporation of mātauranga Māori (Indigenous knowledge) in that work.

Footnotes

1. Fabricious website for decoding ancient languages, https://artsexperiments.withgoogle.com/fabricius.

References

REFERENCES CITED

Allen, Harry, and Phillips, Caroline 2010 Maintaining the Dialogue: Archaeology, Cultural Heritage and Indigenous Communities. In Bridging the Divide: Indigenous Communities and Archaeology into the 21st Century, edited by Phillips, Caroline and Allen, Harry, pp. 17–48. Routledge, New York.Google Scholar
Bevan, Andrew, Li, Xiuzhen, Martinon-Torres, Marcos, Green, Susie, Xia, Yin, Zhao, Kun, Zhao, Zhen, Ma, Shengtao, Cao, Wei, and Rehren, Thilo 2014 Computer Vision, Archaeological Classification and China's Terracotta Warriors. Journal of Archaeological Science 49:249–254.CrossRefGoogle Scholar
Bickler, Simon H. 2018a Machine Learning Identification and Classification of Historic Ceramics. Archaeology in New Zealand 61(1):20–32.Google Scholar
Bickler, Simon H. 2018b Prospects for Machine Learning for Shell Midden Analysis. Archaeology in New Zealand 61(1):48–58.Google Scholar
Bonhage, Alexander, Eltaher, Mahmoud, Raab, Thomas, Breuß, Michael, Raab, Alexandra, and Schneider, Anna 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. DOI:10.1002/arp.1806.CrossRefGoogle Scholar
Brandsen, Alex, Verberne, Suzan, Wansleeben, Milco, and Lambers, Karsten 2020 Creating a Dataset for Named Entity Recognition in the Archaeology Domain. In LREC 2020 Marseille: Twelfth International Conference on Language Resources and Evaluation: Conference Proceedings, edited by Calzolari, Nicoletta, Béchet, Frédéric, Blache, Philippe, Choukri, Khalid, Cieri, Christopher, Declerck, Thierry, Goggi, Sara, Isahara, Hitoshi, Maegaard, Bente, Mariani, Joseph, Mazo, Hélène, Moreno, Asuncion, Odijk, Jan, and Piperidis, Stelios, pp. 4573–4577. European Language Resources Association, Paris.Google Scholar
Byeon, Wonmin, Dominguez-Rodrigo, Manuel, Arampatzis, Georgios, Baquedano, Enrique, Yravedra, José, González, Miguel Ángel, and Koumoutsakos, Petros 2019 Automated Identification and Deep Classification of Cut Marks on Bones and Its Paleoanthropological Implications. Journal of Computational Science 32:36–43.CrossRefGoogle Scholar
Caspari, Gino, and Crespo, Pablo 2019 Convolutional Neural Networks for Archaeological Site Detection–Finding “Princely” Tombs. Journal of Archaeological Science 110:104998. DOI:10.1016/j.jas.2019.104998.CrossRefGoogle Scholar
Castiello, Maria-Elena, and Tonini, Marj 2019 An Innovative Approach for Risk Assessment in Archaeology Based on Machine Learning: A Swiss Case Study. Paper presented at the International Colloquium on Digital Archaeology in Bern (DAB), February 4–6, University of Bern, Switzerland.Google Scholar
Chetouani, Aladine, Treuillet, Sylvie, Exbrayat, Matthieu, and Jesset, Sébastien 2020 Classification of Engraved Pottery Sherds Mixing Deep-Learning Features by Compact Bilinear Pooling. Pattern Recognition Letters 131:1–7.CrossRefGoogle Scholar
Cifuentes-Alcobendas, Gabriel, and Domínguez-Rodrigo, Manuel 2019 Deep Learning and Taphonomy: High Accuracy in the Classification of Cut Marks Made on Fleshed and Defleshed Bones Using Convolutional Neural Networks. Scientific Reports 9:Article 18933. DOI:10.1038/s41598-019-55439-6.CrossRefGoogle ScholarPubMed
Cintas, Celia, Lucena, Manuel, Fuertes, José Manuel, Delrieux, Claudio, Navarro, Pablo, González-José, Rolando, and Molinos, Manuel 2020 Automatic Feature Extraction and Classification of Iberian Ceramics Based on Deep Convolutional Networks. Journal of Cultural Heritage 41:106–112.CrossRefGoogle Scholar
Davis, Dylan S. 2019 Object-Based Image Analysis: A Review of Developments and Future Directions of Automated Feature Detection in Landscape Archaeology. Archaeological Prospection 26:155–163.CrossRefGoogle Scholar
Davis, Dylan S. 2020 Defining What We Study: The Contribution of Machine Automation in Archaeological Research. Digital Applications in Archaeology and Cultural Heritage 18:e00152. DOI:10.1016/j.daach.2020.e00152.CrossRefGoogle Scholar
Davis, Dylan S., DiNapoli, Robert J., and Douglass, Kristina 2020 Integrating Point Process Models, Evolutionary Ecology and Traditional Knowledge Improves Landscape Archaeology—A Case from Southwest Madagascar. Geosciences 10:287.CrossRefGoogle Scholar
Davis, Dylan S., Seeber, Katherine E., and Sanger, Matthew C. 2020 Addressing the Problem of Disappearing Cultural Landscapes in Archaeological Research Using Multi-Scalar Survey. Journal of Island and Coastal Archaeology, in press. DOI:10.1080/15564894.2020.1803457.CrossRefGoogle Scholar
Dore, Christopher D., and Wandsnider, LuAnn 2006 Modeling for Management in a Compliance World. In GIS and Archaeological Site Location Modeling, edited by Mehrer, Mark W. and Westcott, Konnie L., pp. 66–88. CRC Press, Boca Raton.Google Scholar
Douglass, Kristina, Morales, Eréndira Quintana, Manahira, George, Fenomanana, Felicia, Samba, Roger, Lahiniriko, Francois, Chrisostome, Zafy Maharesy, Vavisoa, Voahirana, Soafiavy, Patricia, Justome, Ricky, Leonce, Harson, Hubertine, Laurence, Pierre, Briand Venance, Tahirisoa, Carnah, Colomb, Christoph Sakisy, Lovanirina, Fleurita Soamampionona, Andriankaja, Vanillah, and Robison, Rivo 2019 Toward a Just and Inclusive Environmental Archaeology of Southwest Madagascar. Journal of Social Archaeology 19:307–332.CrossRefGoogle Scholar
Dunnell, Robert C. 1971 Systematics in Prehistory. Macmillan, New York.Google Scholar
Engel, Claudia, Mangiafico, Peter, Issavi, Justine, and Lukas, Dominik 2019 Computer Vision and Image Recognition in Archaeology. In Proceedings of the Conference on Artificial Intelligence for Data Discovery and Reuse 2019. DOI:10.1145/3359115.3359117.CrossRefGoogle Scholar
Evans, Damian, and Hofer, Nina 2019 Exploring Complexity in the Archaeological Landscapes of Monsoon Asia Using Lidar and Deep Learning. Geophysical Research Abstracts 21:1. Electronic document, https://meetingorganizer.copernicus.org/EGU2019/EGU2019-17465.pdf, accessed April 7, 2021.Google Scholar
Felicetti, Achille 2017 Teaching Archaeology to Machines: Extracting Semantic Knowledge from Free Text Excavation Reports. ERCIM News 111:9–10. Electronic document, https://ercim-news.ercim.eu/en111/special/teaching-archaeology-to-machines-extracting-semantic-knowledge-from-free-text-excavation-reports, accessed April 7, 2021.Google Scholar
Felicetti, Andrea, Paolanti, Marina, Zingaretti, Primo, Pierdicca, Roberto, and Malinverni, Eva Savina 2021 Mo.Se.: Mosaic Image Segmentation Based on Deep Cascading Learning.Virtual Archaeology Review 12(24):25–38.CrossRefGoogle Scholar
Freeland, Travis, Heung, Brandon, Burley, David V., Clark, Geoffrey, and Knudby, Anders 2016 Automated Feature Extraction for Prospection and Analysis of Monumental Earthworks from Aerial LiDAR in the Kingdom of Tonga. Journal of Archaeological Science 69:64–74.CrossRefGoogle Scholar
Gebru, Timnit 2020 Race and Gender. In The Oxford Handbook of Ethics of AI, edited by Dubber, Markus D., Pasquale, Frank, and Das, Sunit, pp. 253–270. Oxford University Press, New York.Google Scholar
Grove, Matt, and Blinkhorn, James 2020 Neural Networks Differentiate between Middle and Later Stone Age Lithic Assemblages in Eastern Africa. PLoS ONE 15(8):e0237528. DOI:10.1371/journal.pone.0237528.CrossRefGoogle ScholarPubMed
Gualandi, Maria, Gattiglia, Gabriele, and Anichini, Francesca 2021 An Open System for Collection and Automatic Recognition of Pottery through Neural Network Algorithms. Heritage 4(1):140–159.CrossRefGoogle Scholar
Guyot, Alexandre, Hubert-Moy, Laurence, and Lorho, Thierry 2018 Detecting Neolithic Burial Mounds from LiDAR-Derived Elevation Data Using a Multi-Scale Approach and Machine Learning Techniques. Remote Sensing 10(2):225. DOI:10.3390/rs10020225.CrossRefGoogle Scholar
Guyot, Alexandre, Lennon, Marc, Lorho, Thierry, and Hubert-Moy, Laurence 2021 Combined Detection and Segmentation of Archeological Structures from LiDAR Data Using a Deep Learning Approach. Journal of Computer Applications in Archaeology 4(1):1–19. DOI:10.5334/jcaa.64.CrossRefGoogle Scholar
Harari, Yuval N. 2017 The Rise of the Useless Class. Ideas.Ted.com, February 24. Electronic document, http://ideas.ted.com/the-rise-of-the-useless-class, accessed March 2017.Google Scholar
Hazenfratz Marks, Roberto, Munita, Casimiro, and Neves, Gelmires 2017 Neural Networks (SOM) Applied to INAA Data of Chemical Elements in Archaeological Ceramics from Central Amazon. STAR: Science & Technology of Archaeological Research 3:334–340.CrossRefGoogle Scholar
Heitman, Carrie, Worthy, Martin, and Plog, Stephen 2017 Innovation through Large-Scale Integration of Legacy Records: Assessing the “Value Added” in Cultural Heritage Resources. Journal on Computing and Cultural Heritage 10(3):17.CrossRefGoogle Scholar
Hörr, Christian, Lindinger, Elisabeth, and Brunnett, Guido 2014 Machine Learning Based Typology Development in Archaeology. Journal on Computing and Cultural Heritage 7(1):1–23.CrossRefGoogle Scholar
Horton, Robert, and Paunic, Vanja 2017 Featurizing Images: The Shallow End of Deep Learning. Electronic document, http://blog.revolutionanalytics.com/2017/09/wood-knots.html, accessed 3rd March 2021.Google Scholar
Huffer, Damien, and Graham, Shawn 2018 Fleshing Out the Bones: Studying the Human Remains Trade with Tensorflow and Inception. Journal of Computer Applications in Archaeology 1:55–63.CrossRefGoogle Scholar
Jones, Benjamin, and Bickler, Simon H. 2017 High Resolution LiDAR Data for Landscape Archaeology in New Zealand. Archaeology in New Zealand 60(3):35–44.Google Scholar
Kansa, Eric, and Kansa, Sarah Whitcher 2016 Toward Slow Data in Archaeology. Paper Presented at the 81st Annual Meeting of the Society for American Archaeology, Orlando, Florida.Google Scholar
Kansa, Eric, and Kansa, Sarah Whitcher 2021 Digital Data and Data Literacy in Archaeology Now and in the New Decade. Advances in Archaeological Practice 9:81–85.CrossRefGoogle Scholar
Kogou, Sotiria, Shahtahmassebi, Golnaz, Lucian, Andrei, Liang, Haida, Shui, Biwen, Zhang, Wenyuan, Su, Bomin, and van Schaik, Sam 2020 From Remote Sensing and Machine Learning to the History of the Silk Road: Large Scale Material Identification on Wall Paintings. Scientific Reports 10:19312. DOI:10.1038/s41598-020-76457-9.CrossRefGoogle ScholarPubMed
Nash, Brendan S., and Prewitt, Elton R. 2016 The Use of Artificial Neural Networks in Projectile Point Typology. Lithic Technology 41:194–211.CrossRefGoogle Scholar
Orengo, Hector, Conesa, Francesc C., Garcia, Arnau, Green, Adam, Madella, Marco, and Petrie, Cameron 2020 Automated Detection of Archaeological Mounds Using Machine-Learning Classification of Multisensor and Multitemporal Satellite Data. PNAS 117:18240–18250.CrossRefGoogle ScholarPubMed
Ostertag, Cécilia, and Beurton-Aimar, Marie 2020 Matching Ostraca Fragments Using a Siamese Neural Network. Pattern Recognition Letters 131:336–340.CrossRefGoogle Scholar
Pawlowicz, Leszek, Downum, Christian, and Terlep, Michael 2017 Applications of Machine Learning for Classification and Analysis of Southwestern U.S. Decorated Ceramics. Poster presented at the 82nd Annual Meeting of the Society for American Archaeology, Vancouver, British Colombia.Google Scholar
Prasomphan, Sathit, and Jung, Jai E. 2017 Mobile Application for Archaeological Site Image Content Retrieval and Automated Generating Image Descriptions with Neural Network. Mobile Networks and Applications 22:642–649.CrossRefGoogle Scholar
Romanengo, Chiara, Biasotti, Silvia, and Falcidieno, Bianca S. 2020 Recognising Decorations in Archaeological Finds through the Analysis of Characteristic Curves on 3D Models. Pattern Recognition Letters 131:405–412.CrossRefGoogle Scholar
Sanders, Donald H. 2018 Neural Networks, AI, Phone-Based VR, Machine Learning, Computer Vision and the CUNAT Automated Translation App—Not Your Father's Archaeological Toolkit. In 2018 3rd Digital Heritage International Congress (DigitalHERITAGE) held jointly with 2018 24th International Conference on Virtual Systems & Multimedia (VSMM 2018), pp. 1–5. DOI:10.1109/DigitalHeritage.2018.8810002.CrossRefGoogle Scholar
Shalev-Shwartz, Shai, and Ben-David, Shai 2014 Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, New York.CrossRefGoogle Scholar
Sharafi, Siyamack, Fouladvand, Sajjad, Simpson, Ian, and Alvarez, Juan 2016 Application of Pattern Recognition in Detection of Buried Archaeological Sites Based on Analysing Environmental Variables, Khorramabad Plain, West Iran. Journal of Archaeological Science: Reports 8:206–215.CrossRefGoogle Scholar
Solomon, Maui, and Forbes, Susan 2010 Indigenous Archaeology: A Moriori Case Study. In Bridging the Divide: Indigenous Communities and Archaeology into the 21st Century, edited by Phillips, Caroline and Allen, Harry, pp. 213–232. Routledge, New York.Google Scholar
Soroush, Mehrnoush, Mehrtash, Alireza, Khazraee, Emad, and Ur, Jason 2020 Deep Learning in Archaeological Remote Sensing: Automated Qanat Detection in the Kurdistan Region of Iraq. Remote Sensing 12(3):500. DOI:10.3390/rs12030500.CrossRefGoogle Scholar
Thabeng, Lokwalo, Merlo, Stefania, and Adam, Elhadi 2019 High-Resolution Remote Sensing and Advanced Classification Techniques for the Prospection of Archaeological Sites’ Markers: The Case of Dung Deposits in the Shashi-Limpopo Confluence Area (Southern Africa). Journal of Archaeological Science 102:48–60.CrossRefGoogle Scholar
Trier, Øivind, Cowley, David, and Waldeland, Ander U. 2019 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 26:165–175.CrossRefGoogle Scholar
Trier, Øivind, Salberg, Arnt-Børre, and Pilø, Lars 2018 Semi-Automatic Mapping of Charcoal Kilns from Airborne Laser Scanning Data Using Deep Learning. In CAA2016: Oceans of Data: Proceedings of the 44th Conference on Computer Applications and Quantitative Methods in Archaeology, edited by Matsumoto, Mieko and Uleberg, Espen, pp. 219–231. Archaeopress, Oxford.Google Scholar
Tsigkas, Giorgos, Sfikas, Giorgos, Pasialis, Anastasios, Vlachopoulos, Andreas, and Nikou, Christophoros 2020 Markerless Detection of Ancient Rock Carvings in the Wild. Pattern Recognition Letters 135:337–345.CrossRefGoogle Scholar
Vaart, Verschoof-van der, Wouter, B., and Lambers, Karsten 2019 Learning to Look at LiDAR: The Use of R-CNN in the Automated Detection of Archaeological Objects in LiDAR Data from the Netherlands. Journal of Computer Applications in Archaeology 2:31–40.CrossRefGoogle Scholar
Vaart, Verschoof-van der, Wouter, B., Lambers, Karsten, Kowalczyk, Wojtek, and Bourgeois, Quentin P. 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(5):293.CrossRefGoogle Scholar
Zheng, Minrui, Tang, Wenwu, Ogundiran, Akin, and Yang, Jianxin 2020 Spatial Simulation Modeling of Settlement Distribution Driven by Random Forest: Consideration of Landscape Visibility. Sustainability 12(11):4748. DOI:10.3390/su12114748.CrossRefGoogle Scholar
Figure 0

FIGURE 1. Schematic overview of the process of machine learning applied to archaeological data, showing an example of matching decorative patterns on historical ceramics.

Figure 1

FIGURE 2. An illustrative fictional example of how machine learning may be applied to feature identification in geospatial data and the reconstruction of a site.