Addressing class imbalance in soil movement predictions

Abstract 70: 30 ratio of training and testing data. To tackle the class imbalance problem, various oversampling techniques, including the synthetic minority oversampling technique (SMOTE), K K -means SMOTE performed the best in testing, with an accuracy, precision, and recall rate of 0.995, 0.995, and 0.995, respectively, and an F1 score of 0.995. Additionally, models without oversampling exhibited poor performance in training and testing, highlighting the importance of incorporating oversampling techniques to enhance predictive capabilities.

Location
Deutsche Nationalbibliothek Frankfurt am Main
Extent
Online-Ressource
Language
Englisch

Bibliographic citation
Addressing class imbalance in soil movement predictions ; volume:24 ; number:6 ; year:2024 ; pages:1913-1928 ; extent:16
Natural hazards and earth system sciences ; 24, Heft 6 (2024), 1913-1928 (gesamt 16)

Creator
Kumar, Praveen
Priyanka, Priyanka
Uday, Kala Venkata
Dutt, Varun

DOI
10.5194/nhess-24-1913-2024
URN
urn:nbn:de:101:1-2408051426115.631373882839
Rights
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Last update
14.08.2025, 11:03 AM CEST

Data provider

This object is provided by:
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.

Associated

  • Kumar, Praveen
  • Priyanka, Priyanka
  • Uday, Kala Venkata
  • Dutt, Varun

Other Objects (12)