Innovative Landslide Susceptibility Mapping Portrayed by CA‐AQD and K‐Means Clustering Algorithms

Abstract

This study aims at proposing and designing an improved clustering algorithm for assessing landslide susceptibility using an integration of a Chameleon algorithm and an adaptive quadratic distance (CA-AQD algorithm). It targets improving the prediction capacity of clustering algorithms in landslide susceptibility modelling by overcoming the limitations found in present clustering models, including strong dependence on the initial partition, noise, and outliers as well as difficulties in quantifying the triggering factors (such as rainfall/precipitation). The model was implemented in Baota District, Shaanxi province, China. The CA-AQD algorithm was adopted to split all grids in the study area into many groups with more similar characteristic values, which also owed to efficiently quantifying the uncertain (rainfall) value by using AQD. The K-means algorithm divides these groups into five susceptibility classes according to the values of landslide density in each group. The model was then evaluated using statistical metrics and the performance was validated and compared to that of the traditional Chameleon algorithm and KPSO algorithm. The results show that the CA-AQD algorithm attained the best performance in assessing landslide susceptibility in the study area. Thus, this work adds to the literature by introducing the first empirical integration and application of the CA-AQD algorithm to the assessment of landslides in the study area, which then is a new insight to the field. Also, the method can be helpful for dealing with landslides for better social and economic development.

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

“…Based on the existing LSM literature in the study area, landslide susceptibility is usually classified into 5 levels: very high susceptibility level (VHSL), high susceptibility level (HSL), moderate susceptibility level (MSL), low susceptibility level (LSL), and very low susceptibility level (VLSL) [43,44,46,47,60,89,90]. However, the DIANA and ROCK methods categorized the mapping units (points/objects as used in the methods) to their respective subclasses, but did not identify the susceptibility levels in the subsets.…”

Landslide susceptibility mapping using O-CURE and PAM clustering algorithms

“…Because of these limitations, SL methods may not be applicable where there are a limited number of labeled samples as they are not always easy to obtain and may be expensive to acquire in abundance through image interpretation and site surveying, especially in a large study area. USL-based approaches are applied and have contributed to improving the implementation and the accuracy of LSM in such situations (Lei et al, 2018;Hu et al, 2021;Yimin et al, 2021;Mao et al, 2022;Su et al, 2022;Liu et al, 2023). USL-based methods such as clustering can be used to map the susceptibility areas, as they can identify the underlying structures in unlabeled datasets, hence, do not require data with predefined labels, and do not involve a training process during their implementation.…”

“…Over decades, these methods have been widely used in other fields such as marketing research, pattern recognition, and image processing, but very rarely explored in LSM studies (Huang et al, 2020;Su et al, 2022). In recent years, making use of the advantages of these methods, some landslide researchers have also shown interest and conducted LSM studies using these methods (Wan et al, 2015;Wang et al, 2017;Hu et al, 2019;Mao et al, 2021a;Mao et al, 2021b;Hu et al, 2021;Pokharel et al, 2021;Yimin et al, 2021;Mao et al, 2022). From the analysis of these studies and other traditional clustering algorithms, some limitations were observed: the inability to detect subclasses with arbitrary shapes, sensitivity to noise, inability to perform well in large study areas with large datasets, and principally a standard method to process the uncertain data (rainfall) has not being obtained yet.…”

“…Moreover, to evaluate the performance of the O-CURE method, five statistic metrics are applied, i.e., accuracy, sensitivity, specificity, kappa, and AUC. Also, the traditional CURE, existing LSM clustering methods: Chameleon algorithm and an adaptive quadratic distance-CA-AQD (Yimin et al, 2021), Agglomerative Hierarchical Clustering algorithm based on Overlapped Interval Divergence distance-AHC-OLID (Mao et al, 2021a), and OPTICS algorithm using the Hausdorff distance-OA-HD (Hu et al, 2021) as well as Decision Tree-DT (Nikoobakht et al, 2022), Support Vector Machine-SVM (Nikoobakht et al, 2022), and Uncertain Decision Tree-DTU (Mao et al, 2017) supervised learning models were applied for comparison as benchmark methods using data from the same study area. Furthermore, the key objectives of this study are to develop an improved clustering method-the O-CURE algorithm for LSM modeling in Baota District and apply landslide density, attribute values, and the partitioning around medoids (PAM) algorithm to indicate the landslide susceptibility levels in the study area.…”