Probabilistic landslide ensemble prediction systems: lessons to be learned from hydrology

Abstract

Abstract. Landslide forecasting and early warning has a long tradition in landslide research and is primarily carried out based on empirical and statistical approaches, e.g., landslidetriggering rainfall thresholds. In the last decade, flood forecasting started the operational mode of so-called ensemble prediction systems following the success of the use of ensembles for weather forecasting. These probabilistic approaches acknowledge the presence of unavoidable variability and uncertainty when larger areas are considered and explicitly introduce them into the model results. Now that highly detailed numerical weather predictions and high-performance computing are becoming more common, physically based landslide forecasting for larger areas is becoming feasible, and the landslide research community could benefit from the experiences that have been reported from flood forecasting using ensemble predictions. This paper reviews and summarizes concepts of ensemble prediction in hydrology and discusses how these could facilitate improved landslide forecasting. In addition, a prototype landslide forecasting system utilizing the physically based TRIGRS (Transient Rainfall Infiltration and Grid-Based Regional Slope-Stability) model is presented to highlight how such forecasting systems could be implemented. The paper concludes with a discussion of challenges related to parameter variability and uncertainty, calibration and validation, and computational concerns.

Shallow Landslide Susceptibility Models Based on Artificial Neural Networks Considering the Factor Selection Method and Various Non-Linear Activation Functions

“…Such methods do not require a historical inventory of landslides when developing susceptibility maps but require detailed geotechnical properties and geometric conditions. As such, physically based models are more practical for site-specific areas with homogeneous conditions [9], as it is expensive and time-consuming to build up a database for applications in large-scale areas [10,11].…”

Land Subsidence Susceptibility Mapping Using Bayesian, Functional, and Meta-Ensemble Machine Learning Models

“…Recently, there has been great interest within the hazard prediction community toward improving the performance of hazard susceptibility models. In various fields, machine learning techniques have been shown to be effective in terms of performance [58][59][60][61][62]. In particular, ensemble learning has improved machine learning results by combining several models [17,63,64].…”

A Regional-Scale Landslide Warning System Based on 20 Years of Operational Experience

“…A series of tests was therefore performed to check the feasibility of incorporating soil moisture in the warning system. This represented a major change in the philosophy of the rainfall threshold model but it was supported by a new perspective brought into landslide studies by novel approaches focused on hydrologic issues [42,43]. Indeed, in rainfall threshold studies, long-period antecedent rainfall has always been used as a proxy of the antecedent soil moisture conditions; therefore, the idea of incorporating directly soil moisture data into the warning system has a robust background, although it is quite unexplored in RSLEWS and is limited to few case studies mainly related to remotely sensed measures (e.g., [7]).…”