Landslide Hazard Assessment Based on Explainable Stacking Learning Model (ESLM): A Case Study of the Ili River Basin

Five images show the loss curves of the DNN model for each fold in the 5-fold cross-validation (including both the training and validation sets). 2. The Excel file contains extracted data of landslide and non-landslide points, providing only 300 rows of data here. 3.

The `.ipynb` file is the Python code for the ESLM model in this paper, mainly implementing the use of the SHAP method to explain the results of the Stacking model.