Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN)
Landslide is a natural hazard that results in many economic damages and human losses every year. Numerous researchers have studied landslide susceptibility mapping (LSM), each attempting to improve the accuracy of the final outputs. However, few studies have been published on the training data selec...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2018-01-01
|
| Series: | Geomatics, Natural Hazards & Risk |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/19475705.2017.1407368 |
| _version_ | 1819088122707705856 |
|---|---|
| author | Bahareh Kalantar Biswajeet Pradhan Seyed Amir Naghibi Alireza Motevalli Shattri Mansor |
| author_facet | Bahareh Kalantar Biswajeet Pradhan Seyed Amir Naghibi Alireza Motevalli Shattri Mansor |
| author_sort | Bahareh Kalantar |
| collection | DOAJ |
| description | Landslide is a natural hazard that results in many economic damages and human losses every year. Numerous researchers have studied landslide susceptibility mapping (LSM), each attempting to improve the accuracy of the final outputs. However, few studies have been published on the training data selection effects on the LSM. Thus, this study assesses the training landslides random selection effects on support vector machine (SVM) accuracy, logistic regression (LR) and artificial neural networks (ANN) models for LSM in a catchment at the Dodangeh watershed, Mazandaran province, Iran. A 160 landslide locations inventory was collected by Geological Survey of Iran for this investigation. Different methods were implemented to define the landslide locations, such as inventory reports, satellite images and field survey. Moreover, 14 landslide conditioning factors were considered in the analysis of landslide susceptibility. These factors include curvature, plan curvature, profile curvature, altitude, slope angle, slope aspect, distance to faults, distance to stream, topographic wetness index, stream power index, terrain roughness index, sediment transport index, lithology and land use. The results show that the random landslide training data selection affected the parameter estimations of the SVM, LR and ANN algorithms. The results also show that the training samples selection had an effect on the accuracy of the susceptibility model because landslide conditioning factors vary according to the geographic locations in the study area. The LR model was found to be less sensitive than the SVM and ANN models to the training samples selection. Validation results showed that SVM and LR models outperformed the ANN model for all scenarios. The average overall accuracy of LR, SVM and ANN models are 81.42%, 79.82% and 70.2%, respectively. |
| first_indexed | 2024-12-21T21:47:01Z |
| format | Article |
| id | doaj.art-787e8c65416e47ebb30d672ebdbe231d |
| institution | Directory Open Access Journal |
| issn | 1947-5705 1947-5713 |
| language | English |
| last_indexed | 2024-12-21T21:47:01Z |
| publishDate | 2018-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geomatics, Natural Hazards & Risk |
| spelling | doaj.art-787e8c65416e47ebb30d672ebdbe231d2022-12-21T18:49:11ZengTaylor & Francis GroupGeomatics, Natural Hazards & Risk1947-57051947-57132018-01-0191496910.1080/19475705.2017.14073681407368Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN)Bahareh Kalantar0Biswajeet Pradhan1Seyed Amir Naghibi2Alireza Motevalli3Shattri Mansor4University Putra MalaysiaUniversity Putra MalaysiaTarbiat Modares UniversityTarbiat Modares UniversityUniversity Putra MalaysiaLandslide is a natural hazard that results in many economic damages and human losses every year. Numerous researchers have studied landslide susceptibility mapping (LSM), each attempting to improve the accuracy of the final outputs. However, few studies have been published on the training data selection effects on the LSM. Thus, this study assesses the training landslides random selection effects on support vector machine (SVM) accuracy, logistic regression (LR) and artificial neural networks (ANN) models for LSM in a catchment at the Dodangeh watershed, Mazandaran province, Iran. A 160 landslide locations inventory was collected by Geological Survey of Iran for this investigation. Different methods were implemented to define the landslide locations, such as inventory reports, satellite images and field survey. Moreover, 14 landslide conditioning factors were considered in the analysis of landslide susceptibility. These factors include curvature, plan curvature, profile curvature, altitude, slope angle, slope aspect, distance to faults, distance to stream, topographic wetness index, stream power index, terrain roughness index, sediment transport index, lithology and land use. The results show that the random landslide training data selection affected the parameter estimations of the SVM, LR and ANN algorithms. The results also show that the training samples selection had an effect on the accuracy of the susceptibility model because landslide conditioning factors vary according to the geographic locations in the study area. The LR model was found to be less sensitive than the SVM and ANN models to the training samples selection. Validation results showed that SVM and LR models outperformed the ANN model for all scenarios. The average overall accuracy of LR, SVM and ANN models are 81.42%, 79.82% and 70.2%, respectively.http://dx.doi.org/10.1080/19475705.2017.1407368LandslideSVMANNLRremote sensingtraining dataGIS |
| spellingShingle | Bahareh Kalantar Biswajeet Pradhan Seyed Amir Naghibi Alireza Motevalli Shattri Mansor Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN) Geomatics, Natural Hazards & Risk Landslide SVM ANN LR remote sensing training data GIS |
| title | Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN) |
| title_full | Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN) |
| title_fullStr | Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN) |
| title_full_unstemmed | Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN) |
| title_short | Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN) |
| title_sort | assessment of the effects of training data selection on the landslide susceptibility mapping a comparison between support vector machine svm logistic regression lr and artificial neural networks ann |
| topic | Landslide SVM ANN LR remote sensing training data GIS |
| url | http://dx.doi.org/10.1080/19475705.2017.1407368 |
| work_keys_str_mv | AT baharehkalantar assessmentoftheeffectsoftrainingdataselectiononthelandslidesusceptibilitymappingacomparisonbetweensupportvectormachinesvmlogisticregressionlrandartificialneuralnetworksann AT biswajeetpradhan assessmentoftheeffectsoftrainingdataselectiononthelandslidesusceptibilitymappingacomparisonbetweensupportvectormachinesvmlogisticregressionlrandartificialneuralnetworksann AT seyedamirnaghibi assessmentoftheeffectsoftrainingdataselectiononthelandslidesusceptibilitymappingacomparisonbetweensupportvectormachinesvmlogisticregressionlrandartificialneuralnetworksann AT alirezamotevalli assessmentoftheeffectsoftrainingdataselectiononthelandslidesusceptibilitymappingacomparisonbetweensupportvectormachinesvmlogisticregressionlrandartificialneuralnetworksann AT shattrimansor assessmentoftheeffectsoftrainingdataselectiononthelandslidesusceptibilitymappingacomparisonbetweensupportvectormachinesvmlogisticregressionlrandartificialneuralnetworksann |