Construction of rapid early warning and comprehensive analysis models for urban waterlogging based on AutoML and comparison of the other three machine learning algorithms

•The nowcasting and inversion models for urban waterlogging constructed by the AML based on genetic algorithm was recommended based on the comparison of AML, CatBoost, XGBoost and BPDNN.•The input parameters of the models were discussed in detail and determined as the weights of the urban waterloggi...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of hydrology (Amsterdam) Jg. 605; S. 127367
Hauptverfasser:	Guo, Yuchen, Quan, Lihong, Song, Lili, Liang, Hao
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier B.V 01.02.2022
Schlagworte:	algorithms Automatic machine learning algorithm based on genetic algorithms BPDNN CatBoost China Comprehensive analysis data collection rain Rapid early warning risk topography urban areas Urban waterlogging XGBoost China BPDNN Comprehensive analysis XGBoost Urban waterlogging AutoML Rapid early warning CatBoost Automatic machine learning algorithm based on genetic algorithms
ISSN:	0022-1694, 1879-2707
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!