The Use of Machine Learning and Satellite Imagery to Detect Roman Fortified Sites - The Case Study of Blad Talh (Tunisia Section)

Aug 5, 2026

Upload by Jiven

This study develops an ad hoc machine-learning approach to locate archaeological sites in arid environments. Pleiades (P1B) imagery was processed in Google Earth Engine after being uploaded to the platform’s cloud environment. Average SAR data were combined with the P1B image within the Blad Talh area at Gafsa, southern Tunisia, a pre-desert region associated with Roman civilization. Validation with field survey data produced a probability map with overall accuracy and Kappa coefficient of 0.93 and 0.91. The findings demonstrate that satellite data and machine learning can identify buried Roman fortified sites.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Introduction

Study Rationale and Need for Efficient Surveying

Remote Sensing for Archaeological Site Detection

Machine-Learning Integration in Remote Sensing

applied sciences Article The Use of Machine Learning and Satellite Imagery to Detect Roman Fortiﬁed Sites: The Case Study of Blad Talh (Tunisia Section) Nabil Bachagha 1,*, Abdelrazek Elnashar 2, Moussa Tababi 3, Fatma Souei 4 and Wenbin Xu 1 Citation: Bachagha, N.; Elnashar, A.; Tababi, M.; Souei, F.; Xu, W. The Use of Machine Learning and Satellite Imagery to Detect Roman Fortiﬁed Sites: The Case Study of Blad Talh (Tunisia Section) . Appl. Sci. 2023, 13, 2613. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)app13042613 Academic Editor: Tung-Ching Su Received: 20 January 2023 Revised: 10 February 2023 Accepted: 12 February 2023 Published: 17 February 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 The School of Geo-Science and Info-Physics, Central South University, Changsha 410006, China 2 Department of Natural Resources, Faculty of African Postgraduate Studies, Cairo University, Giza 12613, Egypt 3 Faculty of Letters and Humanities of Sousse, University of Sousse, FLSHS-LR, Sousse 13ES11, Tunisia 4 Department of Computer Science, Hunan University, Changsha 410082, China * [Correspondence: bachaghanabil@csu.edu.cn](Correspondence: bachaghanabil@csu.edu.cn) Abstract: This study focuses on an ad hoc machine-learning method for locating archaeological sites in arid environments. Pleiades (P1B) were uploaded to the cloud asset of the Google Earth Engine (GEE) environment because they are not yet available on the platform. The average of the SAR data was combined with the P1B image in the selected study area called Blad Talh at Gafsa, which is located in southern Tunisia. This pre-desert region has long been investigated as an important area of Roman civilization (106 BCE). The results show an accurate probability map with an overall accuracy and Kappa coefﬁcient of 0.93 and 0.91, respectively, when validated with ﬁeld survey data. The results of this research demonstrate, from the perspective of archaeologists, the capability of satellite data and machine learning to discover buried archaeological sites. This work shows that the area presents more archaeological sites, which has major implications for understanding the archaeological signiﬁcance of the region. Remote sensing combined with machine learning algorithms provides an effective way to augment archaeological surveys and detect new cultural deposits. Keywords: archaeological; machine learning; Google Earth Engine; remote sensing; fortiﬁed sites 1. Introduction Similar to most research-driven ﬁelds, archaeology fundamentally depends on the following two precious and scarce resources: time and money [1] . Archaeologists often travel long distances to reach areas of interest and devote a considerable amount of time to excavations and surveys. Additionally, the discovery of archaeological sites is among the most time-consuming and labour-intensive activities. Archaeologists often use advanced technologies to search for less expensive and faster methodologies for archaeological research. Southern Tunisia is a vast region with difﬁcult access to the investigation area and limited opportunities for in-person data collection. Consequently, land managers spend precious and dwindling resources conducting expensive surveys that result in very few representative samples. One way to address this problem is to develop survey strategies that focus on archaeological potential. Satellite image analysis is a relatively low-cost method with great potential for addressing these needs. The application of remote sensing technology is an effective method for producing relatively complete records of archaeologica

FAQs

What data sources were used in the study of Blad Talh?

The study combined average SAR data with Pleiades (P1B) imagery processed in Google Earth Engine, with Blad Talh as the selected study area.

How were the results validated, and what accuracy was achieved?

Results were validated using field survey data, yielding an overall accuracy of 0.93 and a Kappa coefficient of 0.91.

Why is machine learning important for detecting buried archaeological sites here?

Machine-learning enables automated feature finding from remote-sensing inputs, supporting archaeologists in discovering buried sites and understanding the archaeological significance of the region.

Aug 5, 2026

Upload by Jiven