Search

As a frequent natural disaster, landslides incur significant economic and human losses worldwide. The main idea of this paper is to propose novel integrative models for landslide susceptibility evaluation in a prone area of Chaharmahal va Bakhtiari Province in Iran. To do this, four metaheuristic techniques, namely chimp optimization algorithm (ChOA), crow search algorithm (CSA), satin bowerbird optimization (SBO), and water cycle algorithm (WCA) are used to supervise the training of an artificial neural network (ANN). A spatial database is created by 170 historical landslides and 14 most common conditioning factors. The models are optimized in terms of hyper-parameters and elite ones are then used to produce the susceptibility maps. During the training phase, all models could acquire a reliable understanding of the landslide pattern. The obtained accuracy index of area under the receiving operating characteristic curve (AUROC) showed that the maps produced by the WCA-ANN (AUROC = 0.925) and SBO-ANN (AUROC = 0.900) are more accurate than those of the ChOA-ANN (AUROC = 0.851) and CSA-ANN (AUROC = 0.855). Considering this assessment, the suggested hybrid models are reliable enough for landslide susceptibility modeling. Accordingly, the generated susceptibility map can be used for urban planning and generating alert systems over the studied area. [ABSTRACT FROM AUTHOR]

Landslide susceptibility map (LSM) provide useful tool for decision makers in hazard mitigation concerns. In the present paper, a novel hybrid block-based neural network model (HBNN) for the purpose of producing high-resolution LSM was developed. This hybrid approach was found through the mixture of expert modular structures and divide-and-conquer strategy incorporated with genetic algorithm (GA). The introduced HBNN then was applied on southern part of Guilan province (north of Iran) using 14 causative factors covering topographic and geomorphologic features, and geological and tectonical factors as well as hydrology, land data, and climate conditions. The landslide inventory map was provided using a synergy work from monitored events, interpretation of aerial photographs, and carried out geotechnical investigations in the area as well as field surveys. To insight, the predictability of proposed HBNN was compared with two developed models using multilayer perceptrons (MLPs) and generalized feed forward neural network (GFFN). The generated LSM was validated using receiver operating characteristic (ROC) curves, statistical error indices, and sensitivity and weight analyses as well as monitored landslides. Based on the compared metrics, HBNN with 86.52% and 90.15% in prediction and success rate as well as 89.36% for precision-recall curve demonstrated more consistent tool for future landslide susceptibility zonation. This implies on capability of developed HBNN in producing higher resolution and more reliable LSM for urban and land-use planners. [ABSTRACT FROM AUTHOR]

Landslides can cause extensive damage, particularly those triggered by earthquakes. The current study used back propagation of an artificial neural network (ANN) to conduct risk studies on landslides in the area affected by the Manjil-Rudbar earthquake in Iran in 1990 (M = 7.7). Newmark displacement analysis was used to develop an earthquake-induced landslide hazard map for the blocks representing Chahar-Mahal and Chalkasar near the earthquake epicenter, an area of 309 km2. The input data included soil cohesion, soil friction angle, unit weight of soil, unit weight of water, distance from hypocenter, slope, and earthquake magnitude as effective parameters for landslide occurrence. The hazard map was compared with an inventory map and other research findings. The results indicated that the landslides predicted by ANN covered 50% of the inventory map of the study area (2088 of 4097 slide cells). The results of the current study suggest that the ANN method is relatively efficient for accurate prediction of landslides. [ABSTRACT FROM AUTHOR]

Here, we investigated the landslide susceptibility in the southern coast of the Caspian Sea, located in the northern part of Iran. This is of high importance for this area as it is highly touristic and agriculturally used and therefore of high value for the local inhabitants. Lack of landslide susceptibility map regarding this area is particularly a main motivation for this study. As a basis for modeling, a field mapping of different landslide types was performed. According to the field studies, this area has a high potential for landslide occurrence, and various kinds of mass movement can be observed all over the area. In order to preparing the area’s landslide susceptibility map, topographic, geotechnical, and landslide data were gathered, digitalized, and stored as raster layers. Then, using the infinite slope analysis, the static safety factor was determined in different conditions of saturation ( m) and thickness ( t) of landslide in order to get the most appropriate landslide susceptibility map. The accuracy of analysis was evaluated by comparing the recent landslides with the FS maps. The results indicated that the map obtained using m = 1 and t = 5 m compared with other maps has more compliance with the area. Therefore, this condition was used as cutoff in preparing the area’s landslide susceptibility map. This map comprises five susceptibility ranges: very low, low, moderate, high, and very high. This map shows that high percent of the region (36 %) is subject to landslides. The landslide susceptibility map was verified using 69 older landslides in the area. The results indicated that most of the landslides in the area were concentrated in high and very high susceptibility classes. The landslide susceptibility map prepared in this study can be practical in engineering projects and architectural activities in the investigated area. [ABSTRACT FROM AUTHOR]