EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mapping Complex Artificial Levees and Predicting Their Condition Using Machine Learning-Integrated Electrical Resistivity Tomography

Diaa Sheishah, Enas Abdelsamei, Viktória Blanka-Végi, Dávid Filyó, Gergő Magyar, Ahmed Mohsen, Alexandru Hegyi, Abbas M. Abbas, Csaba Tóth, Tibor Borza, Péter Kozák, Alexandru Onaca und 2 weitere

Water · 30.03.2026 · 18 (7) · 826

DOI: 10.3390/w18070826 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 30.03.2026. Verfasst von Diaa Sheishah und 13 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the University of Szeged, the Interreg VI-A IPA Hungary-Serbia Programme.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial levees along major rivers are critical for flood-risk mitigation, yet many aging structures have poorly constrained internal composition and material heterogeneity, limiting the reliability of conventional safety assessments. This study develops a quantitative, non-destructive framework for characterizing levee internal structure by integrating electrical resistivity tomography (ERT) with borehole (BH) observations. ERT profiles were combined with borehole measurements of grain size (D50) and water content to investigate subsurface compositional variability and to evaluate relationships between sedimentological and geophysical parameters. Grain-size data from borehole samples were modeled using four predictive approaches—random forest regression (RFR), artificial neural networks (ANN), linear regression (LR), and support vector regression (SVR)—based on ERT-derived resistivity and moisture information. The results reveal pronounced internal heterogeneity within the investigated levees and demonstrate consistent relationships between sediment composition, water content, and electrical resistivity. Among the tested models, the ensemble-based RFR provided the highest predictive performance (R2 = 0.81). These findings indicate that D50 characteristics of levee materials can be reliably inferred from ERT data using machine learning, reducing the need for destructive sampling. The proposed approach offers a transferable methodology for levee assessment and supports future applications in non-destructive monitoring, spatially explicit flood-risk analysis, and climate-resilient flood-protection management.

Förderung

  • the University of Szeged
  • the Interreg VI-A IPA Hungary-Serbia Programme

Zitieren

APA

Sheishah, D., Abdelsamei, E., Blanka-Végi, V., Filyó, D., Magyar, G., Mohsen, A., Hegyi, A., Abbas, A. M., Tóth, C., Borza, T., Kozák, P., Onaca, A., Hajdú, S., & Sipos, G. (2026). Mapping Complex Artificial Levees and Predicting Their Condition Using Machine Learning-Integrated Electrical Resistivity Tomography. Water, 18(7), 826. https://doi.org/10.3390/w18070826

Vancouver

Sheishah D, Abdelsamei E, Blanka-Végi V, Filyó D, Magyar G, Mohsen A, et al. Mapping Complex Artificial Levees and Predicting Their Condition Using Machine Learning-Integrated Electrical Resistivity Tomography. Water. 2026;18(7):826. doi:10.3390/w18070826

BibTeX
@article{Sheishah2026,
  author = {Sheishah, Diaa and Abdelsamei, Enas and Blanka-Végi, Viktória and Filyó, Dávid and Magyar, Gergő and Mohsen, Ahmed and Hegyi, Alexandru and Abbas, Abbas M. and Tóth, Csaba and Borza, Tibor and Kozák, Péter and Onaca, Alexandru and Hajdú, Sándor and Sipos, György},
  title = {Mapping Complex Artificial Levees and Predicting Their Condition Using Machine Learning-Integrated Electrical Resistivity Tomography},
  journal = {Water},
  year = {2026},
  volume = {18},
  number = {7},
  pages = {826},
  doi = {10.3390/w18070826}
}
Kostenlos starten →