• Treffer 1 von 10
Zurück zur Trefferliste

Transferability of data-driven models to predict urban pluvial flood water depth in Berlin, Germany

  • Data-driven models have been recently suggested to surrogate computationally expensive hydrodynamic models to map flood hazards. However, most studies focused on developing models for the same area or the same precipitation event. It is thus not obvious how transferable the models are in space. This study evaluates the performance of a convolutional neural network (CNN) based on the U-Net architecture and the random forest (RF) algorithm to predict flood water depth, the models' transferability in space and performance improvement using transfer learning techniques. We used three study areas in Berlin to train, validate and test the models. The results showed that (1) the RF models outperformed the CNN models for predictions within the training domain, presumable at the cost of overfitting; (2) the CNN models had significantly higher potential than the RF models to generalize beyond the training domain; and (3) the CNN models could better benefit from transfer learning technique to boost their performance outside training domains thanData-driven models have been recently suggested to surrogate computationally expensive hydrodynamic models to map flood hazards. However, most studies focused on developing models for the same area or the same precipitation event. It is thus not obvious how transferable the models are in space. This study evaluates the performance of a convolutional neural network (CNN) based on the U-Net architecture and the random forest (RF) algorithm to predict flood water depth, the models' transferability in space and performance improvement using transfer learning techniques. We used three study areas in Berlin to train, validate and test the models. The results showed that (1) the RF models outperformed the CNN models for predictions within the training domain, presumable at the cost of overfitting; (2) the CNN models had significantly higher potential than the RF models to generalize beyond the training domain; and (3) the CNN models could better benefit from transfer learning technique to boost their performance outside training domains than RF models.zeige mehrzeige weniger

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar Statistik - Anzahl der Zugriffe auf das Dokument
Metadaten
Verfasserangaben:Omar SeleemORCiDGND, Georgy AyzelORCiDGND, Axel BronstertORCiDGND, Maik HeistermannORCiDGND
DOI:https://doi.org/10.5194/nhess-23-809-2023
ISSN:1684-9981
ISSN:1561-8633
Titel des übergeordneten Werks (Englisch):Natural Hazards and Earth System Sciences
Verlag:Copernicus
Verlagsort:Göttingen
Publikationstyp:Wissenschaftlicher Artikel
Sprache:Englisch
Datum der Erstveröffentlichung:24.02.2023
Erscheinungsjahr:2023
Datum der Freischaltung:20.04.2023
Band:23
Ausgabe:2
Seitenanzahl:23
Erste Seite:809
Letzte Seite:822
Fördernde Institution:Universität Potsdam
Fördernde Institution:Deutsche Forschungsgemeinschaft (DFG)
Fördernummer:PA 2023_013
Fördernummer:Projektnummer 491466077
Organisationseinheiten:Mathematisch-Naturwissenschaftliche Fakultät / Institut für Umweltwissenschaften und Geographie
DDC-Klassifikation:5 Naturwissenschaften und Mathematik / 55 Geowissenschaften, Geologie / 550 Geowissenschaften
Peer Review:Referiert
Fördermittelquelle:Publikationsfonds der Universität Potsdam
Publikationsweg:Open Access / Gold Open-Access
Lizenz (Deutsch):License LogoCC-BY - Namensnennung 4.0 International
Externe Anmerkung:Zweitveröffentlichung in der Schriftenreihe Zweitveröffentlichungen der Universität Potsdam : Mathematisch-Naturwissenschaftliche Reihe ; 1323
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.