Search

Geomorphology generally aims to describe and investigate the processes that lead to the formation of landscapes, while geochronology is needed to detect their timing and duration. Due to restrictions on exporting geological samples from Egypt, modern geoscientific studies in the Nile Delta lack the possibility of dating the investigated sediments and geological features by standard techniques such as OSL or AMS 14C; therefore, this study aims to validate a new approach using machine‐learning algorithms on portable X‐ray fluorescence (pXRF) data. Archaeologically dated sediments from the archaeological excavations of Buto (Tell el‐Fara'in; on‐site) that pXRF analyses have geochemically characterized serve as training data for running and comparing Neural Nets, Random Forests, and single‐decision trees. The established pXRF fingerprints are transferred via machine‐learning algorithms to set up a chronology for undated sediments from sediment cores (i.e., the test data) of the nearby surroundings (off‐site). Neural Nets and Random Forests work fine in dating sediments and deliver the best classification results compared with single‐decision trees, which struggle with outliers and tend to overfit the training data. Furthermore, Random Forests can be modeled faster and are easier to understand than the complex, less transparent Neural Nets. Therefore, Random Forests provide the best algorithm for studies like this. Furthermore, river features east of Kom el‐Gir are dated to pre‐Ptolemaic times (before 332 B.C.) when Kom el‐Gir had possibly not yet been settled. The research in this paper shows the success of close interactions from various scientific disciplines (Geoinformatics, Physical Geography, Archaeology, Ancient History) to decipher landscape evolution in the long‐term‐settled Nile Delta's environs using machine learning. With the approach's design and the possibility of integrating many other geographical/sedimentological methods, this study demonstrates the potential of the methodological approach to be applied in other geoscientific fields. Highlights: Neural Nets and Random Forest yield excellent results in classifying sedimentsC5.0 single‐decision trees showed substantial deficits in this context [ABSTRACT FROM AUTHOR]

The current state of research about ancient settlements within the Nile Delta allows the hypothesizing of fluvial connections to ancient settlements all over the Nile Delta. Previous studies suggest a larger Nile branch close to Kom el-Gir, an ancient settlement hill in the northwestern Nile Delta. To contribute new knowledge to this little-known site and prove this hypothesis, this study aims at using small-scale paleogeographic investigations to reconstruct an ancient channel system in the surroundings of Kom el-Gir. The study pursues the following: (1) the identification of sedimentary environments via stratigraphic and portable X-ray fluorescence (pXRF) analyses of the sediments, (2) the detection of fluvial elements via electrical resistivity tomography (ERT), and (3) the synthesis of all results to provide a comprehensive reconstruction of a former fluvial network in the surroundings of Kom el-Gir. Therefore, auger core drillings, pXRF analyses, and ERT were conducted to examine the sediments within the study area. Based on the evaluation of the results, the study presents clear evidence of a former channel system in the surroundings of Kom el-Gir. Thereby, it is the combination of both methods, 1-D corings and 2-D ERT profiles, that derives a more detailed illustration of previous environmental conditions which other studies can adopt. Especially within the Nile Delta which comprises a large number of smaller and larger ancient settlement hills, this study's approach can contribute to paleogeographic investigations to improve the general understanding of the former fluvial landscape. Kurzfassung: Der derzeitige Stand der Forschung über antike Siedlungen im Nildelta erlaubt es, Hypothesen fluvialer Verbindungen zu antiken Siedlungen im gesamten Nildelta aufzustellen. Frühere Studien deuten auf einen größeren Nilarm in der Nähe des Kom el-Girs, einem antiken Siedlungshügel im nordwestlichen Nildelta, hin. Um neue Erkenntnisse zu dieser wenig bekannten Stätte zu gewinnen und diese Hypothese zu beweisen, zielt diese Studie auf kleinräumige paläogeographische Untersuchungen zur Rekonstruktion eines antiken Kanal-/Rinnensystems in der Umgebung des Kom el-Girs ab. Die Studie verfolgt: (1) die Identifizierung von Sedimentationsmili eus mittels stratigraphischer und pXRF-Analysen, (2) den Nachweis fluvialer Strukturen mittels elektrischer Widerstandsmessung (ERT) und (3) die Synthese aller Ergebnisse, um eine umfassende Rekonstruktion eines ehemaligen fluvialen Netzwerkes in der Umgebung des Kom el-Girs zu erstellen. Dazu wurden Rammkernsondierungen , pXRF-Analysen und elektrische Widerstandsmessungen (ERT) durchgeführt, um die Sedimente innerhalb des Untersuchungsgebietes zu beschreiben. Die Auswertung der Ergebnisse zeigt deutliche Hinweise auf ein ehemaliges Kanal-/Rinnensystem in der Umgebung des Kom el-Girs. Dabei ist es die Kombination beider Methoden, der 1D-Bohrungen und 2D-ERT-Profile, die eine detailliertere Darstellung früherer Umweltbedingungen ermöglicht und die von anderen Studien übernommen werden kann. Besonders im Nildelta mit seiner großen Anzahl kleinerer und größerer antiker Siedlungshügel , kann der Ansatz dieser Studie in weiteren paläogeographischen Untersuchungen Anwendung finden, um das allgemeine Verständnis ehemaliger Flusslandschaften zu verbessern. [ABSTRACT FROM AUTHOR]