Search

Rain-induced man-made slope failures pose great threats to public safety as most man-made slopes are formed in densely populated areas. A critical step in managing landslide risks is to predict the time, locations, and consequences of slope failures in future rainstorms. Based on comprehensive databases of in-service man-made slopes, rainstorms, and landslides in Hong Kong in the past 35 years, a spatio-temporal landslide forecasting model for man-made slopes is developed in this study within a unified machine learning framework. With a storm-based data integration strategy and multiclass classification on landslide scales, the framework incorporates landslide time and consequences into landslide susceptibility mapping to successfully achieve spatio-temporal landslide forecasting. The machine learning-based landslide forecasting model is validated against historical landslide incidents both temporally and spatially and through a case study of the June 2008 storm, and significantly outperforms the prevailing statistical rainfall-landslide correlations in the prediction accuracy. The model can predict the real-time evolution of probabilities, scales, and spatial distribution of landslides during the progression of a rainstorm, which can never be achieved by statistical methods. It can serve as an essential module for state-of-the-art landslide risk assessment and early warning. © 2022 Thomas Telford Ltd.

It is well recognised that the rheology of an interstitial fluid has profound effects on debris flow dynamics. Existing design guidelines for multiple resisting barriers, however, do not consider the rheological behaviour of debris flows explicitly while estimating barrier spacing. A modified overflow equation is proposed, considering an improved overflow trajectory and a new yield stress-based velocity attenuation model, to estimate the overflow distance in two-phase flows. This study experimentally investigates the effects of yield stress of an interstitial fluid on the impact behaviour of two-phase flows with similar Froude numbers against dual-rigid barriers. The flow composition is varied to model a wide range of natural flows based on dimensionless yield stress. The results reveal that the hydrodynamic impact coefficient increases with increasing dimensionless yield stress and exceeds the existing international design guidelines by more than 13%. The existing guidelines underestimate the overflow distance by up to 115%. The modified formulation is verified and conservatively predicts overflow distance for water floods to debris flows. It is recommended that the dimensionless yield stress of interstitial fluid together with Froude number should be used to characterise the impact and overflow dynamics of two-phase flow for a conservative design of dual barriers.

Landslide susceptibility assessment is essential for regional landslide risk assessment and mitigation. Most past studies involved cell-based analysis that takes landslide incidents as geo-spatial points. Nevertheless, given that a landslide is a two-dimensional polygon on maps and a three-dimensional object in the real world, an object-wise assessment is more logical. Fusing with artificial intelligence (AI) techniques, this paper proposes a novel AI-powered object-based landslide susceptibility assessment method to address this issue. First, landslide and non-landslide objects are defined based on an optimal object size determined by statistics of historical landslides. Next, landslide and non-landslide samples are constructed combining with geoenvironmental data layers derived from multi-source data. Subsequently, AI techniques are applied to learn susceptibility prediction based on the prepared samples. To illustrate the proposed method, a comprehensive case study of Hong Kong is conducted, in which six AI algorithms are evaluated including logistic regression (area under curve, AUC = 0.949), random forest (AUC = 0.951), LogitBoost (AUC = 0.958), convolutional neural network (CNN) (AUC = 0.966), bidirectional long short-term memory architecture of recurrent neural network (BiLSTM-RNN) (AUC = 0.966), and CNN-LSTM (AUC = 0.972), among which the BiLSTM-RNN and CNN-LSTM algorithms are applied in landslide susceptibility assessment for the first time. Results confirm that the proposed object-based method outperforms the traditional cell-based method significantly. Equally importantly, the case study produced the first set of AI-based territory-wide landslide susceptibility maps for Hong Kong. These maps can be used as a fundamental tool for quantifying natural terrain landslide risk and identifying susceptible zones where landslide mitigation measures may be needed.