Evaluation of prediction capability of the artificial neural networks for mapping landslide susceptibility in the Turbolo River catchment (northern Calabria, Italy)

Conforti, Massimo; Pascale, Stefania De; Robustelli, Gaetano; Sdao, Francesco

doi:10.1016/j.catena.2013.08.006

Cited by 353 publications

(214 citation statements)

References 92 publications

Supporting

Mentioning

190

Contrasting

Unclassified

Order By: Relevance

“…Based on the review of previous literature [13,16,17,25] and field surveys, seven factors that were identified as causative and triggering factors for landslide activity in the study area were selected to predict the failure potential of slopes. They are lithology, slope angle, slope aspect, slope height, slope structure, distance from faults, and land use.…”

Section: Influencing Factorsmentioning

confidence: 99%

“…There is no standard principle for selecting the influencing parameters because they often vary from one area to another. However it is commonly recognized that the parameter selection depends on the environmental conditions of the study area, the mechanisms of failed slopes, Sustainability 2017, 9, 32 5 of 15 and the scale of analyses [17]. It should be implemented according to the data availability and the significance of data in relation to the problem at question [23].…”

Section: Influencing Factorsmentioning

confidence: 99%

“…Aspect controls some microclimatic parameters, such as exposure to sunlight and winds, rainfall intensity, and soil moisture [17]. It was obtained from the DEM and was categorized into four classes according to Conforti et al [17], as shown in Table 1.…”

Section: Slope Aspectmentioning

confidence: 99%

“…With the development of science and technology, soft computing techniques, such as data mining and artificial intelligence, have also been widely used in geological hazard assessment. Examples of these approaches include artificial neural networks [14][15][16][17], genetic algorithms [18,19], decision trees [20,21], and support vector machines [22][23][24][25]. However predictions provided by these methods are not probabilistic.…”

Section: Introductionmentioning

confidence: 99%

“…It was obtained from the DEM and was categorized into four classes according to Conforti et al [17], as shown in Table 1. The relationship between lithology and failed slopes is presented in Figure 5d.…”

Section: Slope Aspectmentioning

confidence: 99%

See 4 more Smart Citations

An RVM-Based Model for Assessing the Failure Probability of Slopes along the Jinsha River, Close to the Wudongde Dam Site, China

Chen

Shang

2016

Sustainability

View full text Add to dashboard Cite

Abstract:Assessing the failure potential of slopes is of great significance for land use and management. The objective of this paper is to develop a novel model for evaluating the failure probability of slopes based on a relevance vector machine (RVM), with a special attention to the characteristics of failed slopes along the lower reaches of the Jinsha River, close to the Wudongde dam site. Seven parameters that influence the occurrence of landslides were selected as environmental factors; namely lithology, slope angle, slope height, slope aspect, slope structure, distance from faults, and land use. A total of 55 landslides mapped in the study area were used to train and test the RVM model. The results suggest that the accuracy of the model in predicting the failure probability of slopes, using both training and testing data sets, is very high and deemed satisfactory. To validate the model performance, it was applied to 28 landslide cases identified in the upper reaches of the Jinsha River, where environmental and geological conditions are similar to those of the study area. An accuracy of approximately 92.9% was obtained, which demonstrates that the RVM model has a good generalization performance.

show abstract

Section: Influencing Factorsmentioning

confidence: 99%

Section: Influencing Factorsmentioning

confidence: 99%

Section: Slope Aspectmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Slope Aspectmentioning

confidence: 99%

See 3 more Smart Citations

An RVM-Based Model for Assessing the Failure Probability of Slopes along the Jinsha River, Close to the Wudongde Dam Site, China

Chen

Shang

2016

Sustainability

View full text Add to dashboard Cite

show abstract

Multi‐temporal Digital Photogrammetric Analysis for Quantitative Assessment of Soil Erosion Rates in the Landola Catchment of the Upper Orcia Valley (Tuscany, Italy)

et al. 2014

Self Cite

View full text Add to dashboard Cite

This paper focuses on the analysis of the slope and catchment erosion dynamics in a typical Mediterranean context and its sensitivity to recent climatic and socio-economic changes. The main objective of the present study is to test the reliability of digital photogrammetric analysis to evaluate the time and space evolution of erosion processes mainly triggered by surface running waters and landslides for about the last 60 years. The selected test area is the Landola catchment, a minor tributary of the Upper Orcia River Valley (Southern Tuscany). The Upper Orcia valley is a key site for the comprehension of denudation processes typically acting in Mediterranean badland areas thanks to the following: (i) the availability of long-lasting erosion monitoring datasets (20 years' long direct measurements at erosion 'hot spots'); (ii) its representativeness as a sub-humid Mediterranean badland area; and (iii) the rapidity of development of erosion processes, which makes it suitable as an open-air laboratory for the study of badland dynamics. The outputs of this work highlight that the application of highresolution digital photogrammetric methodologies can represent a powerful and low-cost tool to evaluate rates and spatial-temporal distribution of denudation processes, as confirmed by the validation through field point monitoring in areas close to the study area. The results obtained for the study area confirm that high erosion rates are a persistent environmental problem for the Upper Orcia Valley, which is not solved up to now, despite various land conservation interventions. The performed multi-temporal analysis shows a slight decrease in the average water erosion rate during the last 60 years and a parallel increase in the frequency of mass wasting events. These variations are most likely related to a complex interplay between land use changes that have affected the study area during the studied period, revealing a very delicate equilibrium between farming activities and erosion processes.

show abstract

Spatial variation in the frequency and magnitude of mass movement in a semiarid, complex‐terrain agricultural watershed on the Loess Plateau of China

Zhu

2019

Land Degrad Dev

View full text Add to dashboard Cite

The previous inventory datasets of mass movement typically include large‐sized mass movements (e.g., landslides), whereas small ones are often missing due to either being too small to be interpreted from remote sensing images or too time‐consuming to measure them in the field. Thus, the relative significance of different‐sized mass movement in sediment production remains unknown. In this study, first, a total of 547 recent mass movements, with a volume ranging from 0.3 to 19,000 m3, are surveyed in a small complex‐terrain watershed on the Loess Plateau of China; then, sediment contributions by mass movement of different magnitude and frequency are evaluated; furthermore, the effects of causative factors on both mass movement frequency and magnitude are examined and compared; finally, Geographic Information Systems (GIS) and statistical methods are employed to assess mass movement susceptibility and erosion risk. The results showed that majority of the mass movements are very small (<10 m3). Even though a large mass movement can produce a disproportionally high amount of debris on a per event basis, small‐ and medium‐sized mass movements (<1,000 m3) are overall more important in sediment production in the watershed. The GIS‐based modeling results also demonstrate that there is significant difference in spatial variation between the susceptibility and erosion risk of mass movements. Therefore, although the mass movement susceptibility map is very useful in prioritizing hazard prevention and mitigation, it should be combined with the mass movement erosion risk map in erosion control planning and design, which has not been done in the past.

show abstract

Evaluation of prediction capability of the artificial neural networks for mapping landslide susceptibility in the Turbolo River catchment (northern Calabria, Italy)

Cited by 353 publications

References 92 publications

An RVM-Based Model for Assessing the Failure Probability of Slopes along the Jinsha River, Close to the Wudongde Dam Site, China

An RVM-Based Model for Assessing the Failure Probability of Slopes along the Jinsha River, Close to the Wudongde Dam Site, China

Multi‐temporal Digital Photogrammetric Analysis for Quantitative Assessment of Soil Erosion Rates in the Landola Catchment of the Upper Orcia Valley (Tuscany, Italy)

Spatial variation in the frequency and magnitude of mass movement in a semiarid, complex‐terrain agricultural watershed on the Loess Plateau of China

Contact Info

Product

Resources

About