COLAFOS: a hybrid machine learning model to forecast potential coseismic landslides severity

Abstract

Timely and rational prediction of coseismic landslides is crucial for the design and development of key infrastructure capable to protect human lives in seismically active regions. This research introduces the novel Hybrid Coseismic Landslide Forecasting model (COLAFOS) that takes into consideration three parameters namely: The Average Slope of the Active Areas, the Slope Aspect and the types of Geological forms. The developed model was tested on two datasets from the island of Lefkada Greece, for years 2003 and 2015. COLAFOS is a hybrid model, employing the Fuzzy c-Means clustering, the Ensemble Adaptive Boosting (ENS_AdaBoost) and the Ensemble Subspace k-Nearest Neighbour (ENSUB k-NN) algorithms. The introduced model managed to correctly classify the coseismic landslides according to their severity, with a success rate of 70.07% and 72.88% for 2003 and 2015, respectively. The algorithm has shown very good performance for the classes of major severity, reaching an accuracy up to 92%. Accuracy, Sensitivity, Specificity, Precision and F-1 Score, were used to evaluate the performance of the model. Given the fact that this is a multi-class classification problem, ‘One Versus All’ Strategy was used in the evaluation process. Although the datasets were relatively unbalanced, the evaluation indices sealed the efficiency of the model.

Keywords

• Fuzzy C-means
• ensemble subspace k-NN
• ensemble AdaBoost
• clustering
• classification