Search

Landslides are a geological phenomenon that is causing considerable economic and human losses annually in various regions of the world. In some cases, the complex behaviors of some such phenomena cause that single machine learning models fail in modeling them well. To overcome this issue, this paper presents two novel genetic-algorithm (GA)-based ensemble models constructed with the decision tree (DT), k-nearest neighbors (KNN), and Naive Bayes (NB) models based on the bagging and random sub-space (RS) methods for landslide susceptibility assessment and mapping in Ajloun and Jerash governorates in Jordan. Sixteen factors, including topographic, climatic, human, and geological factors were used as possible factors that influence landslide occurrence in the study area. In addition to this, one hundred and ninety two landslide locations were employed for training and testing the models. The GA was used in this study for feature selection based on three models: DT, KNN, and NB. Model performance evaluation based on the area under the receiver operating characteristic (AUROC) curve indicated that the ensemble models outperform the standalone ones. The values of the AUROC curves in the validation phases for the five models, namely, the GA-based DT, KNN, NB, bagging-based, and RS-based ensemble model, were 0.63, 0.69, 0.63, 0.89, and 0.95, respectively. The results of this study suggest that simple models can be combined using the bagging and RS methods to produce integrated models that have higher accuracy than that of any of the individual simple models. [ABSTRACT FROM AUTHOR]