Landslide Susceptibility Assessment in Constantine Region (NE Algeria) By Means of Statistical Models
Author:
Manchar Nabil12, Benabbas Chaouki3, Hadji Riheb4, Bouaicha Foued5, Grecu Florina6
Affiliation:
1. Department of Geological Sciences, University of Frères Mentouri-Constantine 1 , Postbox 325, Ain El Bey Street, 25017 Constantine , Algeria 2. Department of Geology, Larbi Ben M‘Hidi University , Oum El Bouaghi 04000 , Algeria 3. Institute of Urban Technology Management, Constantine 3 University , Constantine Algeria 4. Department of Earth Sciences , Institute of Architecture and Earth Sciences , Setif 1 University , Setif Algeria 5. Department of applied biology, Université Frères Mentouri – Constantine 1 BP , 325 Route de Ain El Bey , Constantine , Algérie , 25017 6. Faculty of Geography, Geomorphology- Pedology-Geomatics Department University of Bucharest , Bucharest Romania
Abstract
Abstract
The purpose of the present study was to compare the prediction performances of three statistical methods, namely, information value (IV), weight of evidence (WoE) and frequency ratio (FR), for landslide susceptibility mapping (LSM) at the east of Constantine region. A detailed landslide inventory of the study area with a total of 81 landslide locations was compiled from aerial photographs, satellite images and field surveys. This landslide inventory was randomly split into a testing dataset (70%) for training the models, and the remaining (30%) was used for validation purpose. Nine landslide-related factors such as slope gradient, slope aspect, elevation, distance to streams, lithology, distance to lineaments, precipitation, Normalized Difference Vegetation Index (NDVI) and stream density were used in the landslide susceptibility analyses. The inventory was adopted to analyse the spatial relationship between these landslide factors and landslide occurrences. Based on IV, WoE and FR approaches, three landslide susceptibility zonation maps were categorized, namely, “very high, high, moderate, low, and very low”. The results were compared and validated by computing area under Road the receiver operating characteristic (ROC) curve (AUC). From the statistics, it is noted that prediction scores of the FR, IV and WoE models are relatively similar with 73.32%, 73.95% and 79.07%, respectively. However, the map, obtained using the WoE technique, was experienced to be more suitable for the study area. Based on the results, the produced LSM can serve as a reference for planning and decision-making regarding the general use of the land.
Publisher
Walter de Gruyter GmbH
Subject
Computers in Earth Sciences,Mechanics of Materials,Geotechnical Engineering and Engineering Geology,Civil and Structural Engineering
Reference47 articles.
1. Pradhan, B. (2013). A comparative study on the predictive ability of the decision tree, support vector machine and NF models in landslide susceptibility mapping using GIS. Computers & Geosciences 51, 350-365. 2. Van Westen, C.J. (2013). Remote sensing and GIS for natural hazards assessment and disaster risk management. In Treatise on Geomorphology Edited by: Shroder, J., Bishop, MP, Academic Press, San Diego, CA, 3, 259-298. 3. Park, S., Choi, C., Kim, B., Kim, J. (2013). Landslide susceptibility mapping using frequency ratio, analytic hierarchy process, logistic regression, and artificial neural network methods at the Inje area, Korea. Environmental Earth Sciences 68(5), 1443-1464. 4. Gadri, L., Hadji, R., Zahri, F., Benghazi, Z., Boumezbeur, A., Laid, B.M., et al. (2015). The quarries edges stability in opencast mines: a case study of the Jebel Onk phosphate mine, NE Algeria. Arabian Journal of Geosciences 8(11), 8987-8997. 5. Zahri, F., Boukelloul, M.L., Hadji, R., Talhi, K. (2016). Slope stability analysis in open pit mines of Jebel Gustar career, NE Algeria–a multi-steps approach. Mining Science 23, 137-146.
Cited by
49 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|