TY  - JOUR
AU  - Marjanović, Miloš
AU  - Kovačević, Miloš
AU  - Bajat, Branislav
AU  - Vozenilek, Vit
PY  - 2011
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/356
AB  - This paper introduces the current machine learning approach to solving spatial modeling problems in the domain of landslide susceptibility assessment. The latter is introduced as a classification problem, having multiple (geological, morphological, environmental etc.) attributes and one referent landslide inventory map from which to devise the classification rules. Three different machine learning algorithms were compared: Support Vector Machines, Decision Trees and Logistic Regression. A specific area of the Fruska Gora Mountain (Serbia) was selected to perform the entire modeling procedure, from attribute and referent data preparation/processing, through the classifiers' implementation to the evaluation, carried out in terms of the model's performance and agreement with the referent data. The experiments showed that Support Vector Machines outperformed the other proposed methods, and hence this algorithm was selected as the model of choice to be compared with a common knowledge-driven method - the Analytical Hierarchy Process - to create a landslide susceptibility map of the relevant area. The SVM classifier outperformed the AHP approach in all evaluation metrics (kappa index, area under ROC curve and false positive rate in stable ground class).
T2  - Engineering Geology
T1  - Landslide susceptibility assessment using SVM machine learning algorithm
EP  - 234
IS  - 3
SP  - 225
VL  - 123
DO  - 10.1016/j.enggeo.2011.09.006
ER  - 

@article{
author = "Marjanović, Miloš and Kovačević, Miloš and Bajat, Branislav and Vozenilek, Vit",
year = "2011",
abstract = "This paper introduces the current machine learning approach to solving spatial modeling problems in the domain of landslide susceptibility assessment. The latter is introduced as a classification problem, having multiple (geological, morphological, environmental etc.) attributes and one referent landslide inventory map from which to devise the classification rules. Three different machine learning algorithms were compared: Support Vector Machines, Decision Trees and Logistic Regression. A specific area of the Fruska Gora Mountain (Serbia) was selected to perform the entire modeling procedure, from attribute and referent data preparation/processing, through the classifiers' implementation to the evaluation, carried out in terms of the model's performance and agreement with the referent data. The experiments showed that Support Vector Machines outperformed the other proposed methods, and hence this algorithm was selected as the model of choice to be compared with a common knowledge-driven method - the Analytical Hierarchy Process - to create a landslide susceptibility map of the relevant area. The SVM classifier outperformed the AHP approach in all evaluation metrics (kappa index, area under ROC curve and false positive rate in stable ground class).",
journal = "Engineering Geology",
title = "Landslide susceptibility assessment using SVM machine learning algorithm",
pages = "234-225",
number = "3",
volume = "123",
doi = "10.1016/j.enggeo.2011.09.006"
}

Marjanović, M., Kovačević, M., Bajat, B.,& Vozenilek, V.. (2011). Landslide susceptibility assessment using SVM machine learning algorithm. in Engineering Geology, 123(3), 225-234.
https://doi.org/10.1016/j.enggeo.2011.09.006

Marjanović M, Kovačević M, Bajat B, Vozenilek V. Landslide susceptibility assessment using SVM machine learning algorithm. in Engineering Geology. 2011;123(3):225-234.
doi:10.1016/j.enggeo.2011.09.006 .

Marjanović, Miloš, Kovačević, Miloš, Bajat, Branislav, Vozenilek, Vit, "Landslide susceptibility assessment using SVM machine learning algorithm" in Engineering Geology, 123, no. 3 (2011):225-234,
https://doi.org/10.1016/j.enggeo.2011.09.006 . .