Application of weights-of-evidence and certainty factor models and their comparison in landslide susceptibility mapping at Haraz watershed, Iran
read more
Citations
A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS
Application of fuzzy logic and analytical hierarchy process (AHP) to landslide susceptibility mapping at Haraz watershed, Iran
Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS
Landslide susceptibility mapping using certainty factor, index of entropy and logistic regression models in GIS and their comparison at Mugling–Narayanghat road section in Nepal Himalaya
Hybrid integration of Multilayer Perceptron Neural Networks and machine learning ensembles for landslide susceptibility assessment at Himalayan area (India) using GIS
References
Measuring the accuracy of diagnostic systems
Slope movement types and processes
Landslide hazard evaluation: a review of current techniques and their application in a multi-scale study, Central Italy
The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, Central Japan
Landslide hazard assessment: summary review and new perspectives
Related Papers (5)
A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS
Application of fuzzy logic and analytical hierarchy process (AHP) to landslide susceptibility mapping at Haraz watershed, Iran
Frequently Asked Questions (16)
Q2. What was the aim of the present study?
The aim of the present study was to produce landslide susceptibility maps of the Haraz watershed in Iran by employing a weights-of-evidence and certainty factor models.
Q3. What are the triggering factors for landslide occurrences?
The triggering factors, such as rainfall and earthquake, set the movement off by shifting the slope from a marginally stable to an actively unstable area.
Q4. How many landslide deaths are caused by mass movements in Iran?
Losses resulting from mass movements in Iran until the end of September 2007 have been estimated at 126,893 billion Iranian Rials (about USD 12,700 million) using the 4,900 landslide database.
Q5. What is the simplest way to measure the relative certainty of the posterior probability?
The studentised value of C, the ratio of C to standard deviation or C/S(C), serves as a guide to the significance of the spatial association and acts as a measure of the relative certainty of the posterior probability (Bonham-Carter 1991).
Q6. What is the advantage of Bayesian probabilistic modelling?
;VmðrÞgjALð Þ.An advantage of Bayesian probabilistic modelling is the possibility of incorporating uncertainty into the susceptibility model and considering expert knowledge explicitly (Chung and Fabbri 1998).
Q7. How many locations were selected for the landslide map?
Of the 78landslides identified, randomly 55 (70%) locations were chosen for the landslide susceptibility maps, while the remaining 23 (30%) cases were used for the model validation.
Q8. What is the important information about landslide damage?
In spite of improvements in recognition, mitigative measures, and prediction and warning systems, landslide damage is still increasing worldwide (Schuster 1996).
Q9. What are the CF values of the distances to faults?
In the case distance to faults, distances between 0 and 100, 100–200 and 200–300 m have weight (CF) of 0.28, 0.482 and 0.654, respectively.
Q10. How many landslides were identified and mapped in the study area?
A total of 78 landslides were identified and mapped in the study area by evaluating aerial photos in 1:25,000 scale and by field survey (Fig. 2).
Q11. What is the method for determining the landslide susceptibility maps?
In this study, the landslide locations which were not used during the model building process were used to verify the landslide susceptibility maps.
Q12. What were the main factors used for identifying the areas susceptible to landslides?
In this research, both weights-of-evidence and CF models were used for identifying the areas susceptible to landslides at the Haraz Mountains of Iran.
Q13. What is the probability of a landslide in the study area?
the mixture of environmental conditions is special to the mapping unit r. Equation 2 showed that the probability that a mappingunit r in the study area will be influenced by a landslide which is equivalent to the probability of a landslide in the study area, P(AL), multiplied by the probability of a particular (unique) mixture of environmental factors given the presence of a landslide, divided by the probability of the same mixture of environmental factors in the whole study area.
Q14. What was the ROC curve for the weights-of-evidence model?
The validation results showed that the weights-of-evidence model has slightly higher predication accuracy, i.e. 7.85% (79.87–72.02%), which is better than the CF model.
Q15. What were the main factors used to produce a detailed and reliable landslide inventory map?
To produce a detailed and reliable landslide inventory map, extensive field surveys and observations were performed in the study area.
Q16. What was the ROC curve for the landslide inventory map?
For this purpose, a landslide inventory database that is used to assess the landslide susceptibility of the study area, with a total of 78 landslides, was mapped in the study area.