This repository contains part of the code for predicting landslide dynamics based on the FNO model in 1D and 2D, and the article is currently under review. The FNO model refers to the "FOURIER NEURAL OPERATOR FOR PARAMETRIC PARTIAL DIFFERENTIAL EQUATIONS". Based on the landslide dataset of the deep-integrated continuum method constructed by ourselves, the training and testing of the model are in the 1D and 2D landslide folders. Meanwhile in the Gif folder, we show the comparison between the prediction and numerical solution of the one-dimensional flow of the three sections of the first Baige landslide and the comparison between the two-dimensional flow prediction and numerical solution of the first Baige landslide. For the numerical modeling results of the first Baige landslide, refer to the following article"Insights from the failure and dynamic characteristics of two sequential landslides at Baige village along the Jinsha River, China".
Chen, Y., Ouyang, C., Xu, Q., Yang, W. (2024). A Deep learning method for dynamic process modeling of real landslides based on Fourier neural operator. Earth and Space Science, 11, e2023EA003417. https://doi.org/10.1029/2023EA003417