Convolutional neural networks for archaeological site detection – Finding “princely” tombs

Caspari, Gino; Crespo, Pablo (2019). Convolutional neural networks for archaeological site detection – Finding “princely” tombs. Journal of archaeological science, 110, p. 104998. Elsevier 10.1016/j.jas.2019.104998

[img] Text
Caspari - Crespo 2019 CNNs in Archaeology.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (2MB)
[img]
Preview
Text
CaspariCrespo_PrincelyTombs.pdf - Accepted Version
Available under License Creative Commons: Attribution-Noncommercial-No Derivative Works (CC-BY-NC-ND).

Download (1MB) | Preview

Creating a quantitative overview over the early Iron Age heritage of the Eurasian steppes is a difficult task due to the vastness of the ecological zone and the often problematic access. Remote sensing based detection on open-source high-resolution satellite data in combination with convolutional neural networks (CNN) provide a potential solution to this problem. We create a CNN trained to detect early Iron Age burial mounds in freely available optical satellite data. The CNN provides a superior method for archaeological site detection based on the comparison to other detection algorithms trained on the same dataset. Throughout all comparison metrics (precision, recall, and score) the CNN performs best.

Item Type:

Journal Article (Original Article)

Division/Institute:

06 Faculty of Humanities > Department of History and Archaeology > Institute of Archaeological Sciences > Near Eastern Archaeology
06 Faculty of Humanities > Department of History and Archaeology > Institute of Archaeological Sciences

UniBE Contributor:

Caspari, Gino Ramon

Subjects:

900 History > 930 History of ancient world (to ca. 499)
000 Computer science, knowledge & systems
600 Technology > 620 Engineering

ISSN:

0305-4403

Publisher:

Elsevier

Language:

English

Submitter:

Gino Ramon Caspari

Date Deposited:

19 Sep 2019 14:02

Last Modified:

05 Dec 2022 15:30

Publisher DOI:

10.1016/j.jas.2019.104998

BORIS DOI:

10.7892/boris.133265

URI:

https://boris.unibe.ch/id/eprint/133265

Actions (login required)

Edit item Edit item
Provide Feedback