An improved algorithm for identifying shallow and deep-seated landslides in dense tropical forest from airborne laser scanning data

Abstract

Landslides are natural disasters that cause environmental and infrastructure damage worldwide. They are difficult to be recognized, particularly in densely vegetated regions of the tropical forest areas. Consequently, an accurate inventory map is required to analyze landslides susceptibility, hazard, and risk. Several studies were done to differentiate between different types of landslide (i.e. shallow and deep-seated); however, none of them utilized any feature selection techniques. Thus, in this study, three feature selection techniques were used (i.e. correlation-based feature selection (CFS), random forest (RF), and ant colony optimization (ACO)). A fuzzy-based segmentation parameter (FbSP optimizer) was used to optimize the segmentation parameters. Random forest (RF) was used to evaluate the performance of each feature selection algorithms. The overall accuracies of the RF classifier revealed that CFS algorithm exhibited higher ranks in differentiation landslide types. Moreover, the results of the transferability showed that this method is easy, accurate, and highly suitable for differentiating between types of landslides (shallow and deep-seated). In summary, the study recommends that the outlined approaches are significant to improve in distinguishing between shallow and deep-seated landslide in the tropical areas, such as; Malaysia.

Landslide Susceptibility Mapping for the Muchuan County (China): A Comparison Between Bivariate Statistical Models (WoE, EBF, and IoE) and Their Ensembles with Logistic Regression

“…According to the regional geological environment characteristics and previous studies [46][47][48], 12 landslide conditioning factors were selected, including altitude, plan curvature, profile curvature, slope angle, distance to roads, distance to rivers, topographic wetness index (TWI), normalized different vegetation index (NDVI), land use, soil, and lithology. A digital elevation model (DEM) with 30 × 30 m resolution provided by the Geospatial Data Cloud of Chinese Academy of Sciences (GSCloud) was introduced to generate a series of topographic factors, such as altitude, plan curvature, profile curvature, slope angle, slope aspect, and TWI [49].…”

Geographic Object-Based Image Analysis for Automated Landslide Detection Using Open Source GIS Software

“…In our analysis we did not discriminate between shallow and deep-seated landslides, as we were lacking this information in the landslide inventory. Extracting the information on the depth of the sliding surface based solely on HRDTM is a challenging task [65,66]. Yet, we suggest that model performance may benefit from further discrimination between deep-seated and shallow landslides or between different landslide types producing contrasting geometries (e.g., translational landslide versus debris flow).…”

Image Segmentation Parameter Selection and Ant Colony Optimization for Date Palm Tree Detection and Mapping from Very-High-Spatial-Resolution Aerial Imagery

“…Considering the growing availability of very-high-spatial-resolution (VHSR) remote sensing data from various platforms and sensors, a broad spectrum of research has adopted geographic object-based image analysis (GEOBIA) as a successful classification approach to map various vegetation species, such as oil palm trees [6,7], mangrove trees [8,9], rubber plantations [10], and olives [11,12]. In fact, GEOBIA has extensively been used in the literature as a fundamental approach for feature extraction from VHSR images, due to its advantages over the traditional per-pixel classifiers [13][14][15]. While pixel-based classification methods only consider the spectral properties of individual pixels, GEOBIA enables the recognition of multiscale objects from a single image or across several images, and makes the best use of integration between spectral, spatial, textural, thermal, and backscattering values, vector data, and contextual information to accurately extract natural and human-made features [16][17][18][19].…”

“…Recent studies have successfully applied a variety of feature-selection approaches with GEOBIA, including RF [34,44], SVM with recursive feature elimination [45], correlation-based feature selection (CFS) [46], and chi-square [47]. Recently, only a few studies have integrated the metaheuristic optimization technique with the GEOBIA framework, such as particle swarm optimization (PSO) [42] and ACO [13,17]. Sameen et al [17] integrated ACO to select the most relevant features to classify LIDAR data using GEOBIA.…”