EUVIMEDEUVIMED entdecken
Crossref

Evaluating Mask R‐CNN models to extract terracing across oceanic high islands: A case study from Sāmoa

Seth Quintus, Dylan S. Davis, Ethan E. Cochrane

Archaeological Prospection · 2023-10 · 30 (4) · 477-492

DOI: 10.1002/arp.1909 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Archaeological Prospection, online erschienen am 13.07.2023. Verfasst von Seth Quintus und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 97 Literaturangaben. Gefördert von: Marsden Fund, National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lidar datasets have been crucial for documenting the scale and nature of human ecosystem engineering and land use. Automated analysis methods, which have been rising in popularity and efficiency, allow for systematic evaluations of vast landscapes. Here, we use a Mask R‐CNN deep learning model to evaluate terracing—artificially flattened areas surrounded by steeper slopes—on islands in American Sāmoa. Mask R‐CNN is notable for its ability to simultaneously perform detection and segmentation tasks related to object recognition, thereby providing robust datasets of both geographic locations of terracing features and their spatial morphometry. Using training datasets from across American Sāmoa, we train this model to recognize terracing features and then apply it to the island of Tutuila to undertake an island‐wide survey for terrace locations, distributions and morphologies. We demonstrate that this model is effective (F1 = 0.718), but limitations are also documented that relate to the quality of the lidar data and the size of terracing features. Our data show that the islands of American Sāmoa display shared patterns of terracing, but the nature of these patterns are distinct on Tutuila compared with the Manu'a island group. These patterns speak to the different interior configurations of the islands. This study demonstrates how deep learning provides a better understanding of landscape construction and behavioural patterning on Tutuila and has the capacity to expand our understanding of these processes on other islands beyond our case study.

Förderung

  • Marsden Fund
  • National Science Foundation

Zitieren

APA

Quintus, S., Davis, D. S., & Cochrane, E. E. (2023). Evaluating Mask R‐CNN models to extract terracing across oceanic high islands: A case study from Sāmoa. Archaeological Prospection, 30(4), 477-492. https://doi.org/10.1002/arp.1909

Vancouver

Quintus S, Davis DS, Cochrane EE. Evaluating Mask R‐CNN models to extract terracing across oceanic high islands: A case study from Sāmoa. Archaeological Prospection. 2023;30(4):477-492. doi:10.1002/arp.1909

BibTeX
@article{Quintus2023,
  author = {Quintus, Seth and Davis, Dylan S. and Cochrane, Ethan E.},
  title = {Evaluating Mask R‐CNN models to extract terracing across oceanic high islands: A case study from Sāmoa},
  journal = {Archaeological Prospection},
  year = {2023},
  volume = {30},
  number = {4},
  pages = {477--492},
  doi = {10.1002/arp.1909}
}
Kostenlos starten →