Longevity prediction and missing data treatment of landslide dams

Landslide dam failures can cause significant damage to both society and ecosystems. Predicting the failure of these dams in advance enables early preventive measures, thereby minimizing potential harm. This paper aims to propose a fast and accurate model for predicting the longevity of landslide dams while also addressing the issue of missing data. Given the wide variation in the survival times of landslide dams—from mere minutes to several thousand years—predicting their longevity presents a considerable challenge. The study develops predictive models by considering key factors such as dam geometry, hydrodynamic conditions, materials, and triggering parameters. A dataset of 1045 landslide dam cases is analyzed, categorizing their longevity into three distinct groups: C1 (< 1 month), C2 (1 month to 1 year), and C3 (> 1 year). Multiple imputation and k-nearest neighbor algorithms are used to handle missing data on geometric size, hydrodynamic conditions, materials, and triggers. Based on the imputed data, two predictive models are developed: a classification model for dam longevity categories and a regression model for precise longevity predictions. The classification model achieves an accuracy of 88.38% while the regression model outperforms existing models with an R² value of 0.966. Two real-life landslide dam cases are used to validate the models, which show correct classification and small prediction errors. The longevity of landslide dams is jointly influenced by factors such as geometric size, hydrodynamic conditions, materials, and triggering events. Among these, geometric size has the greatest impact, followed by hydrodynamic conditions, materials, and triggers, as confirmed by variable importance in the model development.