Landslide Susceptibility Mapping Using DIvisive ANAlysis (DIANA) and RObust Clustering Using linKs (ROCK) Algorithms, and Comparison of Their Performance

Landslide susceptibility mapping (LSM) studies provide essential information that helps various authorities in managing landslide-susceptible areas. This study aimed at applying and comparing the performance of DIvisive ANAlysis (DIANA) RObust Clustering using linKs (ROCK) algorithms for LSM Baota District, China. These methods can be applied when data has no labels there is insufficient inventory data. First, based on historical records, survey reports, previous studies, 293 landslides were mapped area 7 landslide-influencing attributes selected modeling. Second, clustered units into 469 476 subsets, respectively; landslide susceptibility, subsets classified 5 levels through K-means method densities attribute values. Then, their performances assessed compared statistical metrics receiver operating curve (ROC). The outcomes indicated similarity measures influenced accuracy predictive power these clustering models. In particular, a link-based measure, ROCK performed better with overall 0.8933 an under (AUC) 0.875. maps constructed from models useful assessment, prevention, mitigation strategies area, especially areas higher levels. Moreover, this comparison provides new perspective selection considerable model District.