Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Investigating Ancient Agricultural Field Systems In Sweden From Airborne Lidar Data By Using Convolutional Neural Network

Kucukdemirci, Melda LU ; Landeschi, Giacomo LU ; Ohlsson, Mattias LU orcid and Dell'Unto, Nicolo LU orcid (2023) In Archaeological Prospection 30(2). p.209-219
Abstract
Today, the advances in airborne LIDAR technology provide high-resolution datasets that allow specialists to detect archaeological features hidden under wooded areas more efficiently. Still, the complexity and large scale of these datasets require automated analysis. In this respect, artificial intelligence (AI)-based analysis has recently created an alternative approach for interpreting remote sensing data. In this study, a convolutional neural network (CNN) is proposed to detect clearance cairns, which are visible in today's landscape and act as important markers of past agricultural activities. For this aim, the U-shape network architecture is adapted, trained from scratch with an original labelled dataset and tested in various field... (More)
Today, the advances in airborne LIDAR technology provide high-resolution datasets that allow specialists to detect archaeological features hidden under wooded areas more efficiently. Still, the complexity and large scale of these datasets require automated analysis. In this respect, artificial intelligence (AI)-based analysis has recently created an alternative approach for interpreting remote sensing data. In this study, a convolutional neural network (CNN) is proposed to detect clearance cairns, which are visible in today's landscape and act as important markers of past agricultural activities. For this aim, the U-shape network architecture is adapted, trained from scratch with an original labelled dataset and tested in various field sites, focusing on southern Sweden. Although it is challenging to tune the hyperparameters and decide on the proper network architecture to obtain reliable prediction, long-running experimental tests with this model produced promising results, with training and validation metrics of 0.8406 Dice-coefficient, 0.7469 Val-dice coefficient, and 0.7350 IuO and 0.6034 Val-IoU values, once trained with the best parameters. Thus, the proposed CNN model in this study made data interpretation quicker and guided scholars to focus on the location of the target objects, opening a new frontier for future landscape analysis and archaeological research. (Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Artificial intelligence (AI), archeology, LIDAR remote sensing, Convolutional neural networks (CNN), landsape archaeology, deep learning, prehistoric agricultural activity, Segmentation Classification
in
Archaeological Prospection
volume
30
issue
2
pages
11 pages
publisher
John Wiley & Sons Inc.
external identifiers
  • scopus:85142145527
ISSN
1099-0763
DOI
10.1002/arp.1886
project
ARTIFICIAL INTELLIGENCE AND LANDSCAPE ANALYSIS; EXPANDING METHODS AND CHALLENGING PARADIGMS
language
English
LU publication?
yes
id
41ca425c-fd75-4935-8455-9df446068be4
date added to LUP
2022-11-11 08:03:43
date last changed
2024-04-15 20:34:22
@article{41ca425c-fd75-4935-8455-9df446068be4,
  abstract     = {{Today, the advances in airborne LIDAR technology provide high-resolution datasets that allow specialists to detect archaeological features hidden under wooded areas more efficiently. Still, the complexity and large scale of these datasets require automated analysis. In this respect, artificial intelligence (AI)-based analysis has recently created an alternative approach for interpreting remote sensing data. In this study, a convolutional neural network (CNN) is proposed to detect clearance cairns, which are visible in today's landscape and act as important markers of past agricultural activities. For this aim, the U-shape network architecture is adapted, trained from scratch with an original labelled dataset and tested in various field sites, focusing on southern Sweden. Although it is challenging to tune the hyperparameters and decide on the proper network architecture to obtain reliable prediction, long-running experimental tests with this model produced promising results, with training and validation metrics of 0.8406 Dice-coefficient, 0.7469 Val-dice coefficient, and 0.7350 IuO and 0.6034 Val-IoU values, once trained with the best parameters. Thus, the proposed CNN model in this study made data interpretation quicker and guided scholars to focus on the location of the target objects, opening a new frontier for future landscape analysis and archaeological research.}},
  author       = {{Kucukdemirci, Melda and Landeschi, Giacomo and Ohlsson, Mattias and Dell'Unto, Nicolo}},
  issn         = {{1099-0763}},
  keywords     = {{Artificial intelligence (AI); archeology; LIDAR remote sensing; Convolutional neural networks (CNN); landsape archaeology; deep learning; prehistoric agricultural activity; Segmentation Classification}},
  language     = {{eng}},
  number       = {{2}},
  pages        = {{209--219}},
  publisher    = {{John Wiley & Sons Inc.}},
  series       = {{Archaeological Prospection}},
  title        = {{Investigating Ancient Agricultural Field Systems In Sweden From Airborne Lidar Data By Using Convolutional Neural Network}},
  url          = {{http://dx.doi.org/10.1002/arp.1886}},
  doi          = {{10.1002/arp.1886}},
  volume       = {{30}},
  year         = {{2023}},
}