Landslide susceptibility mapping at Dodangeh watershed, Iran using LR and ANN models in GIS

Bahareh Kalantar; Naonori Ueda; Husam Abdulrasool H. Al-Najjar; Mohammed Oludare Idrees; Alireza Motevalli; Biswajeet Pradhan

doi:10.1117/12.2501473

9 October 2018 Landslide susceptibility mapping at Dodangeh watershed, Iran using LR and ANN models in GIS

Bahareh Kalantar, Naonori Ueda, Husam Abdulrasool H. Al-Najjar, Mohammed Oludare Idrees, Alireza Motevalli, Biswajeet Pradhan

Author Affiliations +

Proceedings Volume 10790, Earth Resources and Environmental Remote Sensing/GIS Applications IX; 107901D (2018) https://doi.org/10.1117/12.2501473
Event: SPIE Remote Sensing, 2018, Berlin, Germany

Abstract

Landslide is among the most common geologic hazard around the world. They cause many formidable damages and numerous deaths annually. There are multiple causes for every landslide. Landslide causes are classified into three categories, namely, physical, natural, and human. Maps are a valuable and appropriate tool for presenting information on landslide. Landslide susceptibility maps is one of the most useful source of information for landuse planners. A landslide susceptibility map represents zones that have the potential for landslide. These zones are identified by correlation between the past distribution of landslide occurrence and conditioning factors that contribute to landslide. This study employs logistic regression (LR) and artificial neural networks (ANN) models to assess landslide susceptibility in Dodangeh Watershed, Mazandaran Province, Iran. The spatial database included landslide inventory, altitude, slope angle and aspect, plan and profile curvatures, distance from faults and from stream, stream power index (SPI), topographic wetness index (TWI), sediment transport index (STI), terrain roughness index (TRI), landuse and lithology. Validation of the models using receiver operating characteristics and overall accuracy indicates that both models display satisfactory performance, and LR model exhibits the most stable and best performance. Given the outcomes of the study, the LR model, which has an AUC value of 0.872 and an overall accuracy of 82.59%, and the ANN model, which has a AUC value of 0.77 and an overall accuracy of 71% are promising techniques for landslide susceptibility mapping.

Conference Presentation

Citation Download Citation

Bahareh Kalantar, Naonori Ueda, Husam Abdulrasool H. Al-Najjar, Mohammed Oludare Idrees, Alireza Motevalli, and Biswajeet Pradhan "Landslide susceptibility mapping at Dodangeh watershed, Iran using LR and ANN models in GIS", Proc. SPIE 10790, Earth Resources and Environmental Remote Sensing/GIS Applications IX, 107901D (9 October 2018); https://doi.org/10.1117/12.2501473

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available