A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Modelling the rainfall threshold for shallow landslides considering the landslide predisposing factors in Portugal
https://orcid.org/0000-0003-1230-6341
https://orcid.org/0000-0001-9785-0180
https://orcid.org/0000-0002-3953-673X
AbstractRainfall-triggered landslides pose a significant threat to both infrastructure and human lives, making it crucial to comprehend the factors that contribute to their occurrence. Specifically, understanding the relationship between these factors and the amount of rain that is necessary for triggering such events is essential for effective prediction and mitigation strategies. To address this issue, our study proposes a statistical modelling approach using machine learning, specifically the Random Forest algorithm, to investigate the connection between landslide predisposing factors and the daily rainfall intensity threshold necessary for the initiation of shallow landslides in Portugal. By leveraging a comprehensive dataset comprising historical landslide events, associated critical rainfall, and ten distinct landslide predisposing factors, we developed several models and used cross-validation technique to evaluate their performance. Our findings demonstrate that the Random Forest model effectively captures a relationship among landslide predisposing factors, critical daily rainfall intensity, and landslide occurrences. The models exhibit a satisfactory accuracy in assessing the spatial variation of critical daily rainfall intensity based on the predisposing factors, with a mean absolute percentage error (MAPE) of around 17%. Furthermore, the models provide valuable insights into the relative importance of various predisposing factors in landslide triggering, highlighting the significance of each factor. It was found that it takes higher rainfall intensity to trigger shallow landslides in the north region of Portugal when considering critical rainfall events of 3 and 13 days. Slope aspect, slope angle, and clay content in the soil are among the main predisposing factors used for defining the spatial variation of the daily rainfall intensity threshold.
Modelling the rainfall threshold for shallow landslides considering the landslide predisposing factors in Portugal
https://orcid.org/0000-0003-1230-6341
https://orcid.org/0000-0001-9785-0180
https://orcid.org/0000-0002-3953-673X
AbstractRainfall-triggered landslides pose a significant threat to both infrastructure and human lives, making it crucial to comprehend the factors that contribute to their occurrence. Specifically, understanding the relationship between these factors and the amount of rain that is necessary for triggering such events is essential for effective prediction and mitigation strategies. To address this issue, our study proposes a statistical modelling approach using machine learning, specifically the Random Forest algorithm, to investigate the connection between landslide predisposing factors and the daily rainfall intensity threshold necessary for the initiation of shallow landslides in Portugal. By leveraging a comprehensive dataset comprising historical landslide events, associated critical rainfall, and ten distinct landslide predisposing factors, we developed several models and used cross-validation technique to evaluate their performance. Our findings demonstrate that the Random Forest model effectively captures a relationship among landslide predisposing factors, critical daily rainfall intensity, and landslide occurrences. The models exhibit a satisfactory accuracy in assessing the spatial variation of critical daily rainfall intensity based on the predisposing factors, with a mean absolute percentage error (MAPE) of around 17%. Furthermore, the models provide valuable insights into the relative importance of various predisposing factors in landslide triggering, highlighting the significance of each factor. It was found that it takes higher rainfall intensity to trigger shallow landslides in the north region of Portugal when considering critical rainfall events of 3 and 13 days. Slope aspect, slope angle, and clay content in the soil are among the main predisposing factors used for defining the spatial variation of the daily rainfall intensity threshold.
Modelling the rainfall threshold for shallow landslides considering the landslide predisposing factors in Portugal
https://orcid.org/0000-0003-1230-6341
https://orcid.org/0000-0001-9785-0180
https://orcid.org/0000-0002-3953-673X
AbstractRainfall-triggered landslides pose a significant threat to both infrastructure and human lives, making it crucial to comprehend the factors that contribute to their occurrence. Specifically, understanding the relationship between these factors and the amount of rain that is necessary for triggering such events is essential for effective prediction and mitigation strategies. To address this issue, our study proposes a statistical modelling approach using machine learning, specifically the Random Forest algorithm, to investigate the connection between landslide predisposing factors and the daily rainfall intensity threshold necessary for the initiation of shallow landslides in Portugal. By leveraging a comprehensive dataset comprising historical landslide events, associated critical rainfall, and ten distinct landslide predisposing factors, we developed several models and used cross-validation technique to evaluate their performance. Our findings demonstrate that the Random Forest model effectively captures a relationship among landslide predisposing factors, critical daily rainfall intensity, and landslide occurrences. The models exhibit a satisfactory accuracy in assessing the spatial variation of critical daily rainfall intensity based on the predisposing factors, with a mean absolute percentage error (MAPE) of around 17%. Furthermore, the models provide valuable insights into the relative importance of various predisposing factors in landslide triggering, highlighting the significance of each factor. It was found that it takes higher rainfall intensity to trigger shallow landslides in the north region of Portugal when considering critical rainfall events of 3 and 13 days. Slope aspect, slope angle, and clay content in the soil are among the main predisposing factors used for defining the spatial variation of the daily rainfall intensity threshold.
Modelling the rainfall threshold for shallow landslides considering the landslide predisposing factors in Portugal
Landslides
Villaça, Caio (author) / Santos, Pedro Pinto (author) / Zêzere, José Luís (author)
Landslides ; 21 ; 2119-2133
2024-09-01
Article (Journal)
Electronic Resource
English
Rainfall thresholds for shallow landslides considering rainfall temporal patterns
| Springer Verlag | 2025
NUMERICAL MODELLING OF SHALLOW LANDSLIDES TRIGGERED BY RAINFALL
| British Library Conference Proceedings | 2005
Rainfall Threshold for Shallow Landslide Triggering Due to Rising Water Table
| DOAJ | 2022
Prediction of shallow landslide by surficial stability analysis considering rainfall infiltration
| British Library Online Contents | 2017
Application of hydrological modelling for temporal prediction of rainfall-induced shallow landslides
| Springer Verlag | 2019