Search

The conventional numerical solvers for partial differential equations encounter a formidable challenge, as their computational efficiency and accuracy are heavily contingent on grid size. Recently, machine learning (ML) has exhibited substantial promise in addressing partial differential equations. Nevertheless, substantial hurdles persist in practical applications. In this work, we endeavor to establish a deep learning framework founded on the Fourier neural operator (FNO) for resolving the intricacies of simulating real landslide dynamic processes. Our findings demonstrate that the current FNO approach adeptly replicates landslide dynamic processes and boasts exceptional computational efficiency. Additionally, it is noteworthy that this data‐driven ML methodology can seamlessly incorporate data from other experimental sources or numerical simulation techniques. Consequently, this work underscores the significant potential of utilizing ML methodologies to supplant conventional numerical simulation methods. Plain Language Summary: There are great challenges involved in leveraging machine learning methods to learn realistic physical dynamic processes. When it comes to the real landslide movement across intricate terrains, it is meaningful to validate the capacities of machine learning in tackling the complicated problem. This study aims to propose an innovative solution of modeling of landslide dynamic processes from a machine learning perspective. Here, we introduce a data‐driven framework based on Fourier neural operator to predict the dynamic behavior of actual landslides. Following an exhaustive assessment, the superior performance of our suggested model in real landslide situations and its versatility in adapting to landslides across various geographical regions have been confirmed. This study explores a new approach to modeling landslide dynamic processes and highlights the great potential of data‐driven approaches to address dynamic process challenges present in real physical world. Key Points: The data‐driven deep learning method based on FNO can achieve fast prediction of real landslide accumulation processThe proposed data‐driven method for predicting landslide dynamic processes can be extended to new areas after transfer learningWe provide numerical datasets of landslide dynamics, which can serve as the foundational resources for ML‐based landslide forecasting tasks [ABSTRACT FROM AUTHOR]

Numerical prediction of landslide runout and deposition is important for estimating landslide risk and developing mitigation plans. The choice of a suitable model and its parameters and a confident calibration strategy are crucial for numerical simulations. Here, we evaluated two constitutive models with a three‐dimensional smoothed particle hydrodynamics (SPH) method by simulating the catastrophic 11 October 2018 Baige landslide. The results indicate that both the soil mechanic and fluid models can capture the dynamic runout and deposition morphology while using different values of input parameters. A point‐wise comparison of deposit elevation can minimize the calibration error. Numerical models were constrained accurately by utilizing both the static observation data and dynamic seismic signals. The effects of friction on deep‐seated landslides motion and deposition are more significant than cohesion. The 3D model includes the effects of shear stresses and velocities inside the material body, resulting in a reduced friction coefficient compared to the 2D model (e.g., depth‐averaged model). Our study highlights the potential of the 3D SPH method for modeling large‐scale complex landslides. Plain Language Summary: Landslides belong to a type of earth surface process recognized by their high damage potential. Computer models can simulate the landslides' movement to predict speed, forces, and deposition, which can help to delineate areas at risk and to design mitigation measures. We simulated the 2018 Baige landslide in China with a method known as smoothed particle hydrodynamics (SPH), to test whether it is suitable for landslide simulation and to investigate protocols for model calibration when including seismic data in addition to information on the landslide's deposit. In this method, the landslide body is represented by millions of small, moving, interacting particles, which offers advantages over established models in terms of computation time and details in the simulation. We find that SPH is suitable for modeling large‐scale natural landslides. The seismic data are more valuable in the model calibration than landslide deposit observations. The new approach yields landslide simulations that deliver more details on particle velocities within the landslide body, and their spatial and temporal distribution. These details can be used to infer the properties of landslides during the sliding process, which helps to better understand landslides in general and to set up models for events where little data are available. Key Points: A three‐dimensional mesh‐less graphics processing unit‐accelerated smoothed particle hydrodynamics formulation is suitable for modeling large‐scale natural landslidesThe selection of an appropriate constitutive model depends on the landslide features and materialsIncluding dynamic seismic signals into numerical model calibration routines in addition to topographic changes improves calibration [ABSTRACT FROM AUTHOR]

Wildfires are becoming a global natural disaster under climate change. A worthwhile concern is that the rainfall thresholds that trigger debris flows in catchments affected by recent wildfires are much lower than those that trigger debris flows in catchments with similar environments but that have not experienced wildfires. In this study, we investigated a major post‐fire debris flow event in Xiangjiao catchment triggered by heavy rainfall in 2021. Through the combination of field observation, laboratory experiments and several numerical models (rainfall interception, infiltration, erosion and runoff models), the physical mechanistic analysis and numerical simulation of the post‐fire debris flow in Xiangjiao catchment was carried out. Results show that the simulated deposited area, erosion depth, and the occurrence time of debris‐flow initiation correlate well with the actual situation. It is demonstrated that the numerical simulation method used in this study can be used to effectively describe the characteristics of the initial and propagation stages of the post‐fire debris flow generated by runoff and provide important insights and guidance for the prediction and prevention of debris‐flow disasters in catchments affected by wildfire. Plain Language Summary: Wildfires are becoming more and more common under more frequent extreme weather. After the wildfire, the overall environment would be substantially changed, which will lead to more frequent debris‐flow disasters. Consequences of these changes are worthy to be deeply investigated. In this study, we investigated a major 2021 post‐fire debris flow event in Xiangjiao catchment, China, triggered by heavy rainfall. Through the combination of field observation, laboratory experiments, and numerical models, the physical mechanistic analysis and numerical simulation of the post‐fire debris flow in Xiangjiao catchment was carried out. Key Points: The mechanism of post‐fire debris flows caused by runoff in Xiangjiao catchment is analyzedUsing multiple numerical models and multi‐source data, the 2021 Xiangjiao post‐fire debris flow is simulatedThe numerical simulation results are analyzed and correlated well with the field investigation [ABSTRACT FROM AUTHOR]

To investigate the movement mechanism of debris flow, a two-dimensional, two-phase, depth-integrated model is introduced. The model uses Mohr-Coulomb plasticity for the solid rheology, and the fluid stress is modeled as a Newtonian fluid. The interaction between solid and liquid phases, which plays a major role in debris flow movement, is assumed to consist of drag and buoyancy forces. The applicability of drag force formulas is discussed. Considering the complex interaction between debris flow and the bed surface, a combined friction boundary condition is imposed on the bottom, and this is also discussed. To solve the complex model equations, a numerical method with second-order accuracy based on the finite volume method is proposed. Several numerical experiments are performed to verify the feasibilities of model and numerical schemes. Numerical results demonstrate that different solid volume fractions substantially affect debris flow movement. [ABSTRACT FROM AUTHOR]

The volume fraction of the solid and liquid phase of debris flows, which evolves simultaneously across terrains, largely determines the dynamic property of debris flows. The entrainment process significantly influences the amplitude of the volume fraction. In this paper, we present a depth-averaged two-phase debris-flow model describing the simultaneous evolution of the phase velocity and depth, the solid and fluid volume fractions and the bed morphological evolution. The model employs the Mohr-Coulomb plasticity for the solid stress, and the fluid stress is modeled as a Newtonian viscous stress. The interfacial momentum transfer includes viscous drag and buoyancy. A new extended entrainment rate formula that satisfies the boundary momentum jump condition (Iverson and Ouyang, 2015) is presented. In this formula, the basal traction stress is a function of the solid volume fraction and can take advantage of both the Coulomb and velocity-dependent friction models. A finite volume method using Roe's Riemann approximation is suggested to solve the equations. Three computational cases are conducted and compared with experiments or previous results. The results show that the current computational model and framework are robust and suitable for capturing the characteristics of debris flows. [ABSTRACT FROM AUTHOR]