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]

The efficiency and accuracy of grid-based computational fluid dynamics methods are strongly dependent on the chosen cell size. The computational time increases exponentially with decreasing cell size. Therefore, a grid coarsing technology without apparent precision loss is essential for various numerical modeling methods. In this article, a physical adaption neural network (PANN) is proposed to optimize coarse grid representation from a fine grid. A new convolutional neural network is constructed to achieve a significant reduction in computational cost while maintaining a relatively accurate solution. An application to numerical modeling of dynamic processes in landslides is firstly carried out, and better results are obtained compared to the baseline method. More applications in various flood scenarios in mountainous areas are then analyzed. It is demonstrated that the proposed PANN downscaling method outperforms other currently widely used downscaling methods. The code is publicly available and can be applied broadly. Computing by PANN is hundreds of times more efficient, meaning that it is significant for the numerical modeling of various complicated Earth-surface flows and their applications. [ABSTRACT FROM AUTHOR]

Abstract: A two-dimensional mountainous mass flow dynamic procedure solver (Massflow-2D) using the MacCormack-TVD finite difference scheme is proposed. The solver is implemented in Matlab on structured meshes with variable computational domain. To verify the model, a variety of numerical test scenarios, namely, the classical one-dimensional and two-dimensional dam break, the landslide in Hong Kong in 1993 and the Nora debris flow in the Italian Alps in 2000, are executed, and the model outputs are compared with published results. It is established that the model predictions agree well with both the analytical solution as well as the field observations. [Copyright &y& Elsevier]