Abstract
Abstract. Conventional outputs of physics-based landslide forecasting models are presented as deterministic warnings by calculating the safety factor (Fs) of potentially dangerous slopes. However, these models are highly dependent on variables such as cohesion force and internal friction angle which are affected by a high degree of uncertainty especially at a regional scale, resulting in unacceptable uncertainties of Fs. Under such circumstances, the outputs of physical models are more suitable if presented in the form of landslide probability values. In order to develop such models, a method to link the uncertainty of soil parameter values with landslide probability is devised. This paper proposes the use of Monte Carlo methods to quantitatively express uncertainty by assigning random values to physical variables inside a defined interval. The inequality Fs<1 is tested for each pixel in n simulations which are integrated in a unique parameter. This parameter links the landslide probability to the uncertainties of soil mechanical parameters and is used to create a physics-based probabilistic forecasting model for rainfall-induced shallow landslides. The prediction ability of this model was tested in a case study, in which simulated forecasting of landslide disasters associated with heavy rainfalls on 9 July 2013 in the Wenchuan earthquake region of Sichuan province, China, was performed. The proposed model successfully forecasted landslides in 159 of the 176 disaster points registered by the geo-environmental monitoring station of Sichuan province. Such testing results indicate that the new model can be operated in a highly efficient way and show more reliable results, attributable to its high prediction accuracy. Accordingly, the new model can be potentially packaged into a forecasting system for shallow landslides providing technological support for the mitigation of these disasters at regional scale.
Highlights
Rainfall-induced shallow landslides are common in many mountainous areas and are considered extremely dangerous (Varnes, 1978)
This paper focuses on an effective method for linking landslide probability to the uncertain soil mechanical parameters
The seemingly deterministic infinite-slope model based on soil mechanical parameters of each pixel is uncertain (Schmidt et al, 2008; Rossi et al, 2013). This will be reflected in the safety factors Fs of each pixel, leading to a situation in which, despite the advantages of the physically based landslide forecasting model, it may be misleading if used in a deterministic way for real-world applications
Summary
Rainfall-induced shallow landslides are common in many mountainous areas and are considered extremely dangerous (Varnes, 1978). The physics-based forecasting model is able to describe the variation rule of hydrological parameters induced by rainfall infiltration and further explain the failure mechanism of a slope due to the variation of hydrological parameters Those characteristics explain the interest of scholars in the physicsbased forecasting model and its implementation at regional scales (Schmidt et al, 2008; Montrasio et al, 2011; Raia et al, 2014). A series of deterministic forecasting results are generated by the model during the simulation process (Raia et al, 2014); an experienced forecaster with professional knowledge of landslides is necessary in order to identify the most probable one This approach requires a large number of calculations, which is unsuitable for operational forecasting of shallow landslides.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
