Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Machine Learning Modeling for Spatial-Temporal Prediction of Geohazard
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 signals
Machine Learning Modeling for Spatial-Temporal Prediction of Geohazard
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 signals
Machine Learning Modeling for Spatial-Temporal Prediction of Geohazard
Ma, Junwei (Herausgeber:in) / Dou, Jie (Herausgeber:in)
2023
1 Online-Ressource (274 p.)
Buch
Elektronische Ressource
Unbekannt
Integrated Geohazard Management - A Systemwide Approach
| British Library Conference Proceedings | 1996
Foundation Scour as a Geohazard
| ASCE | 2019
Regional modelling of geohazard change
| British Library Conference Proceedings | 2009
North Falkland Basin Geohazard Study
| British Library Conference Proceedings | 2007