A Deep Learning Method for the Automated Mapping of Archaeological Structures from Geospatial Data: A Case Study of Delos Island

The integration of artificial intelligence (AI), specifically through convolutional neural networks (CNNs), is paving the way for significant advancements in archaeological research. This study explores the innovative application of the so-called Mask Region-based convolutional neural network (Mask...

Full description

Saved in:
Bibliographic Details
Main Authors: Pavlos Fylaktos, George P. Petropoulos, Ioannis Lemesios
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/14/6/220
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850167437884915712
author Pavlos Fylaktos
George P. Petropoulos
Ioannis Lemesios
author_facet Pavlos Fylaktos
George P. Petropoulos
Ioannis Lemesios
author_sort Pavlos Fylaktos
collection DOAJ
description The integration of artificial intelligence (AI), specifically through convolutional neural networks (CNNs), is paving the way for significant advancements in archaeological research. This study explores the innovative application of the so-called Mask Region-based convolutional neural network (Mask R-CNN) algorithm in a GIS environment, utilizing high-resolution satellite imagery from the WorldView-3 system. By combining these state-of-the-art technologies, this study demonstrates the algorithm’s effectiveness at recognizing and segmenting the ancient structures within the archaeological site of Delos, Greece. Despite the computational constraints, the outcomes are promising, with around 25.91% of the initial vector data (434 out of 1675 polygons) successfully identified. The algorithm achieved an impressive F1 Score of 0.93% at a threshold of 0.9, indicating its high precision in differentiating specific features from their environments. This research highlights AI’s crucial role in archaeology, enabling the remote analysis of vast areas through automated or semi-automated techniques. Although these technologies cannot supplant essential on-site investigations, they can significantly enhance traditional methodologies by minimizing costs and fieldwork duration. This study also points out obstacles, such as the complexity of and variability in archaeological remains, which complicate the creation of standardized data libraries. Nevertheless, as AI technologies progress, their applications in archaeology are anticipated to broaden, fostering further innovation within the discipline.
format Article
id doaj-art-18d58424bc394a0188ef3de03ab095dd
institution OA Journals
issn 2220-9964
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj-art-18d58424bc394a0188ef3de03ab095dd2025-08-20T02:21:12ZengMDPI AGISPRS International Journal of Geo-Information2220-99642025-06-0114622010.3390/ijgi14060220A Deep Learning Method for the Automated Mapping of Archaeological Structures from Geospatial Data: A Case Study of Delos IslandPavlos Fylaktos0George P. Petropoulos1Ioannis Lemesios2Department of Geography, Harokopio University of Athens, El. Venizelou 70, Kallithea, 17671 Athens, GreeceDepartment of Geography, Harokopio University of Athens, El. Venizelou 70, Kallithea, 17671 Athens, GreeceDepartment of Geography, Harokopio University of Athens, El. Venizelou 70, Kallithea, 17671 Athens, GreeceThe integration of artificial intelligence (AI), specifically through convolutional neural networks (CNNs), is paving the way for significant advancements in archaeological research. This study explores the innovative application of the so-called Mask Region-based convolutional neural network (Mask R-CNN) algorithm in a GIS environment, utilizing high-resolution satellite imagery from the WorldView-3 system. By combining these state-of-the-art technologies, this study demonstrates the algorithm’s effectiveness at recognizing and segmenting the ancient structures within the archaeological site of Delos, Greece. Despite the computational constraints, the outcomes are promising, with around 25.91% of the initial vector data (434 out of 1675 polygons) successfully identified. The algorithm achieved an impressive F1 Score of 0.93% at a threshold of 0.9, indicating its high precision in differentiating specific features from their environments. This research highlights AI’s crucial role in archaeology, enabling the remote analysis of vast areas through automated or semi-automated techniques. Although these technologies cannot supplant essential on-site investigations, they can significantly enhance traditional methodologies by minimizing costs and fieldwork duration. This study also points out obstacles, such as the complexity of and variability in archaeological remains, which complicate the creation of standardized data libraries. Nevertheless, as AI technologies progress, their applications in archaeology are anticipated to broaden, fostering further innovation within the discipline.https://www.mdpi.com/2220-9964/14/6/220machine learningconvolutional neural networks (CNNs)WorldView-3archaeologyDelos Island
spellingShingle Pavlos Fylaktos
George P. Petropoulos
Ioannis Lemesios
A Deep Learning Method for the Automated Mapping of Archaeological Structures from Geospatial Data: A Case Study of Delos Island
ISPRS International Journal of Geo-Information
machine learning
convolutional neural networks (CNNs)
WorldView-3
archaeology
Delos Island
title A Deep Learning Method for the Automated Mapping of Archaeological Structures from Geospatial Data: A Case Study of Delos Island
title_full A Deep Learning Method for the Automated Mapping of Archaeological Structures from Geospatial Data: A Case Study of Delos Island
title_fullStr A Deep Learning Method for the Automated Mapping of Archaeological Structures from Geospatial Data: A Case Study of Delos Island
title_full_unstemmed A Deep Learning Method for the Automated Mapping of Archaeological Structures from Geospatial Data: A Case Study of Delos Island
title_short A Deep Learning Method for the Automated Mapping of Archaeological Structures from Geospatial Data: A Case Study of Delos Island
title_sort deep learning method for the automated mapping of archaeological structures from geospatial data a case study of delos island
topic machine learning
convolutional neural networks (CNNs)
WorldView-3
archaeology
Delos Island
url https://www.mdpi.com/2220-9964/14/6/220
work_keys_str_mv AT pavlosfylaktos adeeplearningmethodfortheautomatedmappingofarchaeologicalstructuresfromgeospatialdataacasestudyofdelosisland
AT georgeppetropoulos adeeplearningmethodfortheautomatedmappingofarchaeologicalstructuresfromgeospatialdataacasestudyofdelosisland
AT ioannislemesios adeeplearningmethodfortheautomatedmappingofarchaeologicalstructuresfromgeospatialdataacasestudyofdelosisland
AT pavlosfylaktos deeplearningmethodfortheautomatedmappingofarchaeologicalstructuresfromgeospatialdataacasestudyofdelosisland
AT georgeppetropoulos deeplearningmethodfortheautomatedmappingofarchaeologicalstructuresfromgeospatialdataacasestudyofdelosisland
AT ioannislemesios deeplearningmethodfortheautomatedmappingofarchaeologicalstructuresfromgeospatialdataacasestudyofdelosisland