Custom cover image
Custom cover image

Machine Learning Modeling for Spatial-Temporal Prediction of Geohazard

Contributor(s): Resource type: Ressourcentyp: Buch (Online)Book (Online)Language: Undetermined Publisher: [Erscheinungsort nicht ermittelbar] : MDPI - Multidisciplinary Digital Publishing Institute, 2023Description: 1 Online-Ressource (274 p.)ISBN:
  • 9783036597867
  • 9783036597874
Subject(s): Online resources: Summary: Geohazards, such as landslides, rock avalanches, debris flow, ground fissures, and ground subsidence, pose a significant threat to people’s lives and property. Recently, machine learning (ML) has become the predominant approach in geohazard modeling, offering advantages such as an excellent generalization ability and accurately describing complex and nonlinear behaviors. However, the utilization of advanced algorithms in deep learning remains poorly understood in this field. Additionally, there are fundamental challenges associated with ML modeling, including input variable selection, uncertainty quantification, and hyperparameter tuning. This reprint presents original research exploring new advances and challenges in the application of ML in the spatial–temporal modeling of geohazards. The contributions cover the susceptibility analysis of glacier debris flow and landslides, the displacement prediction of reservoir landslides, slope stability prediction and classification, building resilience evaluation, and the prediction of rainfall-induced landslide warning signalsPPN: PPN: 1885795750Package identifier: Produktsigel: ZDB-94-OAB
No physical items for this record

Open Access. Unrestricted online access star

Namensnennung 4.0 International CC BY 4.0 cc:

https://creativecommons.org/licenses/by/4.0/

English

KIT – The Research University in the Helmholtz Association                         Home | Impressum | Datenschutz | Barrierefreiheit | KIT