EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Quantifying urban land cover imperviousness as input for flood simulation using machine learning: South African case study

Ione Loots iD, Jeffrey Colin Smithers, Thomas Rodding Kjeldsen

Water Science & Technology · 2025

DOI: 10.2166/wst.2025.067 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water Science & Technology, 2025. Verfasst von Ione Loots und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil Engineering, University of Pretoria, Pretoria, South Africa E-mail: ione.loots@up.ac.za. Hauptthemen laut MEDLINE: Machine Learning, Floods. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The imperviousness of urban surfaces is an important parameter in simulating urban hydrological responses, but quantifying imperviousness can be challenging and time-consuming. In response, this study presents a new framework to efficiently estimate the imperviousness of urban surfaces, using satellite images with Red, Green and Blue bands and a land cover dataset with multiple built-up urban classes through remote sensing, machine learning and field verification. The methodology is adaptable to other regions with similar datasets. For a case study in Pretoria, South Africa, major differences in median total impervious area percentages (mTIA%) were identified when compared between land cover groups: residential areas had a lower imperviousness median (mTIA% = 38%) than commercial (mTIA% = 81%) and industrial (mTIA% = 89%) land cover. The mTIA% also varies between 17 and 61% for a range of different formally developed residential classes and between 14 and 43% for a range of different informally developed residential classes. These mTIA% are recommended for any urban area within the South African National Land Cover dataset. These values can be incorporated into hydraulic and hydrological models, which improve the efficiency of parameter estimation for modelling. The methodology successfully quantified temporal imperviousness changes in the study area.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningFloodsSouth AfricaCitiesModels, TheoreticalHydrologyComputer Simulation

Stichwörter der Autor:innen

QGISimperviousinformal settlementland coverremote sensingurban flood

Autor:innen und Institutionen

  • Department of Civil Engineering, University of Pretoria, Pretoria, South Africa E-mail: ione.loots@up.ac.za.
  • Centre for Water Resources Research and School of Engineering, University of KwaZulu-Natal, Pietermaritzburg, South Africa.
  • Department of Architecture and Civil Engineering, University of Bath, Bath, UK.

ORCID-Profile: Ione Loots

Zitieren

APA

Loots, I., Smithers, J. C., & Kjeldsen, T. R. (2025). Quantifying urban land cover imperviousness as input for flood simulation using machine learning: South African case study. Water Science & Technology. https://doi.org/10.2166/wst.2025.067

Vancouver

Loots I, Smithers JC, Kjeldsen TR. Quantifying urban land cover imperviousness as input for flood simulation using machine learning: South African case study. Water Science & Technology. 2025. doi:10.2166/wst.2025.067

BibTeX
@article{Loots2025,
  author = {Loots, Ione and Smithers, Jeffrey Colin and Kjeldsen, Thomas Rodding},
  title = {Quantifying urban land cover imperviousness as input for flood simulation using machine learning: South African case study},
  journal = {Water Science & Technology},
  year = {2025},
  doi = {10.2166/wst.2025.067}
}
Kostenlos starten →