A brave new world for archaeological survey: Automated machine learning-based potsherd detection using high-resolution drone imagery

Orengo, Hector H.; Garcia‐Molsosa, Arnau

doi:10.1016/j.jas.2019.105013

Cited by 68 publications

(55 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ultimately, there is no strong correlation of NDVI values to either field visibility or land use, nor is the resolution that is currently available effective in determining the percentage of ground cover visible at a scale comparable to that of the individual surveyor. One way of bridging this gap in resolution is through unmanned aerial vehicles (UAVs) that can be effectively employed to provide the necessary spatial resolution to monitor vegetation at the time of survey and even map the surface materials (Orengo and Garcia-Molsosa 2019). Though we do not present these data here, our preliminary exploration of this approach shows that the resolution of low-altitude photography and photogrammetry is sufficient for capturing minute variations in surface vegetation (Figure 8).…”

Section: Discussionmentioning

confidence: 99%

Applications of Satellite Remote Sensing for Archaeological Survey: A Case Study from the Sinis Archaeological Project, Sardinia

Plekhov

Gosner

Smith

et al. 2020

Adv. archaeol. pract.

View full text Add to dashboard Cite

Satellite imagery has long been recognized as well suited for the regional and ecological questions of many archaeological surveys. One underexplored aspect of such data is their temporal resolution. It is now possible for areas to be imaged on an almost daily basis, and this resolution offers new opportunities for studying landscapes through remote sensing in parallel with ground-based survey. This article explores the applications of these data for visibility assessment and land-cover change detection in the context of the Sinis Archaeological Project, a regional archaeological survey of west-central Sardinia. We employ imagery provided by Planet, which has a spatial resolution of 3 m, in four spectral bands, and is collected daily. Using Normalized Difference Vegetation Index (NDVI) values calculated for each survey unit, we find that there is a relationship between NDVI values and field-reported visibility in general, though the strength of this correlation differs according to land-cover classes. We also find the data to be effective at tracking short-term changes in field conditions that allow us to differentiate fields of similar land cover and visibility. We consider limitations and potentials of these data and encourage further experimentation and development.

show abstract

Section: Discussionmentioning

confidence: 99%

Applications of Satellite Remote Sensing for Archaeological Survey: A Case Study from the Sinis Archaeological Project, Sardinia

Plekhov

Gosner

Smith

et al. 2020

Adv. archaeol. pract.

View full text Add to dashboard Cite

show abstract

“…The most innovative proofs incorporated machine learning with data derived from photogrammetry. For instance, Orenga and Garcia-Molsosa (2019) demonstrated how drones can automatically identify sherd scatter density.…”

Section: Aerial Photogrammetrymentioning

confidence: 99%

The Digital Revolution to Come: Photogrammetry in Archaeological Practice

Magnani

Douglass²,

Schroder

et al. 2020

Am. Antiq.

View full text Add to dashboard Cite

The three-dimensional (3D) revolution promised to transform archaeological practice. Of the technologies that contribute to the proliferation of 3D data, photogrammetry facilitates the rapid and inexpensive digitization of complex subjects in both field and lab settings. It finds additional use as a tool for public outreach, where it engages audiences ranging from source communities to artifact collectors. But what has photogrammetry's function been in advancing archaeological analysis? Drawing on our previous work, we review recent applications to understand the role of photogrammetry for contemporary archaeologists. Although photogrammetry is widely used as a visual aid, its analytical potential remains underdeveloped. Considering various scales of inquiry—graduating from objects to landscapes—we address how the technology fits within and expands existing documentation and data visualization routines, while evaluating the opportunity it presents for addressing archaeological questions and problems in innovative ways. We advance an agenda advocating that archaeologists move from proof-of-concept papers toward greater integration of photogrammetry with research.

show abstract

“…In the same amount of time, automated methods were used to evaluate over 2000 km 2 with similar levels of success [14]. Recent MI developments by archaeologists have released code and software to permit for replication and use by other researchers [4,80], and this must become standard practice.…”

Section: Potential Solutions To the Global Divide In Machine Intelligmentioning

confidence: 99%

“…provides powerful mechanisms for collecting more complete and systematic information from remote sensing instruments to inform researchers about the archaeological record. MI, in turn, can permit for more comprehensive-and reproducible-research into important anthropological questions [4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…MI encompasses statistical classifiers, semi-automated analysis, deep learning, machine learning, and other methods of systematically parsing through image data to extract information [14,16,25]. While a majority of this work has focused on the development of algorithms for detecting archaeological deposits from landscape-scale satellite and aerial imagery, and airborne laser scanning (ALS) [6,12,26], research has laser scanning (ALS) [6,12,26], research has also focused on analyzing individual materials and smaller-scale phenomena [4,20,22,23,[27][28][29]. In the past several years, alone, there has been an explosion of machine learning research with archaeological remote sensing foci around the world (Figure 1).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Geographic Disparity in Machine Intelligence Approaches for Archaeological Remote Sensing Research

Davis

2020

Remote Sensing

View full text Add to dashboard Cite

A vast majority of the archaeological record, globally, is understudied and increasingly threatened by climate change, economic and political instability, and violent conflict. Archaeological data are crucial for understanding the past, and as such, documentation of this information is imperative. The development of machine intelligence approaches (including machine learning, artificial intelligence, and other automated processes) has resulted in massive gains in archaeological knowledge, as such computational methods have expedited the rate of archaeological survey and discovery via remote sensing instruments. Nevertheless, the progression of automated computational approaches is limited by distinct geographic imbalances in where these techniques are developed and applied. Here, I investigate the degree of this disparity and some potential reasons for this imbalance. Analyses from Web of Science and Microsoft Academic searches reveal that there is a substantial difference between the Global North and South in the output of machine intelligence remote sensing archaeology literature. There are also regional imbalances. I argue that one solution is to increase collaborations between research institutions in addition to data sharing efforts.

show abstract

A brave new world for archaeological survey: Automated machine learning-based potsherd detection using high-resolution drone imagery

Cited by 68 publications

References 21 publications

Applications of Satellite Remote Sensing for Archaeological Survey: A Case Study from the Sinis Archaeological Project, Sardinia

Applications of Satellite Remote Sensing for Archaeological Survey: A Case Study from the Sinis Archaeological Project, Sardinia

The Digital Revolution to Come: Photogrammetry in Archaeological Practice

Geographic Disparity in Machine Intelligence Approaches for Archaeological Remote Sensing Research

Contact Info

Product

Resources

About