Identifying factors affecting landslides on Astara road to Nemin tunnel using MLP model

Document Type : Research Article


1 Professor of Geomorphology, Faculty of Social Sciences, University of Mohaghegh Ardabili, Ardabil, Iran.

2 Masters graduate, Geomorphology and Environmental Management, Faculty of Social Sciences University of Mohaghegh Ardabili. Ardabil, Iran

3 Master's student in remote sensing, Faculty of Earth Sciences, Shahid Beheshti University, Tehran, Iran

4 phd student of Geomorphology, Faculty of Social Sciences, university of Mohaghegh Ardabili, Ardabil, Iran,



Landslide is one of the phenomena that causes a lot of damage, especially in mountainous areas. Therefore, it is essential to evaluate and recognize the factors affecting the occurrence of landslides in mountainous areas. The purpose of this research is to identify the factors affecting landslides on Astara road to Nemin tunnel using MLP model. The MLP model is one of the efficient neural network models that has the ability to solve complex problems. To identify the important factors in the occurrence of landslides, according to field studies, 8 factors have been identified, including: geology, vegetation, distance from the road, satisfactory use, slope, direction of slope, height, real points of landslides have been used. After pre-processing, all layers are entered into SPSS MODELER software and Modeling is designed with 8 input neurons, 6 intermediate neurons and 1 output. The results of this research showed that the weighted output of the MLP model assigned the highest weighted value for the geological layer with a value of 0.26 for the land use layer and the distance from the road with values of 0.14 and 0.13 respectively. Also, in the validation section of the model, it shows the AUC value of 0.948 in the training section and 0.962 in the testing section of the network, which indicates that the model has high reliability in both the training section and the testing section, so it can be concluded that The geological factor has a great impact on the occurrence of landslides in the region compared to other factors, and finally, it is suggested to use machine learning models and artificial intelligence in future studies to study and evaluate landslides and range movements.


Main Subjects


Articles in Press, Accepted Manuscript
Available Online from 27 April 2024
  • Receive Date: 27 March 2024
  • Revise Date: 21 April 2024
  • Accept Date: 27 April 2024