Welcome to Scholar Publishing Group

International Journal of Engineering Technology and Construction, 2023, 4(1); doi: 10.38007/IJETC.2023.040104.

Evaluation of Machine Learning Algorithm for Landslide Sensitive Spatial Model Based on GIS Taking the Area along Sichuan-Tibet Railway as an Example

Author(s)

Feng Zou and Rong Liu

Corresponding Author:
Rong Liu
Affiliation(s)

Northwestern Polytechnical University, Xi’an, China

Abstract

With the development of GIS-based geospatial information technology, new methods have been provided for landslide disaster research. However, there is currently no suitable way to combine GIS technology with machine algorithms. In order to construct a highly accurate landslide sensitivity spatial model, this paper statistically analyzes the relationship between landslide disasters and various influencing factors in the study area through the GIS spatial analysis function, especially for the actual situation along the Sichuan-Tibet Railway. In this paper, a cross-check method is used to construct a landslide sensitivity evaluation model, and the accuracy of different models is quantitatively evaluated. The results of the fitting accuracy of the logistic regression model and the support vector machine model are: the average accuracy in the modeling stage is 75.722 and 75.65, and the average accuracy in the verification stage is 71.34 and 71.21. At the modeling stage, the SVM model has a fitting accuracy of about 3% higher than that of the logistic regression model; at the verification stage, the fitting accuracy is 0.13% higher than that of the logistic regression model; the AUC results show that the SVM model performs optimally, its AUC value is above 0.9, which achieves a higher accuracy. Compared with the logistic regression model, this value is 0.111 higher in the modeling stage and 0.111 higher in the verification stage.

Keywords

GIS Technology, Landslide Sensitivity, Spatial Model, Support Vector Machine (SVM), Logistic Regression Model

Cite This Paper

Feng Zou and Rong Liu. Evaluation of Machine Learning Algorithm for Landslide Sensitive Spatial Model Based on GIS Taking the Area along Sichuan-Tibet Railway as an Example. International Journal of Engineering Technology and Construction (2023), Vol. 4, Issue 1: 48-64. https://doi.org/10.38007/IJETC.2023.040104.

References

[1] Ruan, Y. K. , Zhan, J. W. , Chen, J. P. , & Li, Y. Y. . (2017). Landslide sensitivity based on k-pso clustering algorithm and entropy method. Dongbei Daxue Xuebao/Journal of Northeastern University, 38(4), 571-575.

[2] D. Qiu, & R. Niu. (2017). Susceptibility analysis of earthquake-induced landslides based on slope units. Journal of Natural Disasters, 26(2), 144-151.

[3] N Gorshkov, S Zhdanova, & M Dobromyslov. (2018). Formation of landslide bodies at numerical calculations of making soil constructions (cut and embankment). IOP Conference Series Materials Science and Engineering, 463(4), 042068.

[4] Songtang He, Daojie Wang, Yingchao Fang, & Huijuan Lan. (2017). Guidelines for integrating ecological and biological engineering technologies for control of severe erosion in mountainous areas – a case study of the xiaojiang river basin, china. International Soil & Water Conservation Research, 5(4), 335-344.

[5] Jewgenij Torizin, Michael Fuchs, Adnan Alam Awan, Ijaz Ahmad, & Ahsan Jamal Khan. (2017). Statistical landslide susceptibility assessment of the mansehra and torghar districts, khyber pakhtunkhwa province, pakistan. Natural Hazards, 89(4), 757-784.

[6] Chao, G. , Bang, L. , Yong-Cai, G. , & Zheng-Wei, Z. . (2017). Five mn force sensor based on fiber bragg grating. Optics & Precision Engineering, 25(4), 857-866.

[7] Saied Pirasteh, & Jonathan Li. (2017). Probabilistic frequency ratio (pfr) model for quality improvement of landslide susceptibility mapping from lidar-derived dems. Geoenvironmental Disasters, 4(1), 19.

[8] Binh Thai Pham, Khabat Khosravi, & Indra Prakash. (2017). Application and comparison of decision tree-based machine learning methods in landside susceptibility assessment at pauri garhwal area, uttarakhand, india. Environmental Processes, 4(3), 711-730.

[9] Ekrem Canli, Bernd Loigge, & Thomas Glade. (2018). Spatially distributed rainfall information and its potential for regional landslide early warning systems. Natural Hazards, 91(Suppl. 1), 103-127.

[10] Zhi Yong Lv, Wenzhong Shi, Xiaokang Zhang, & Jon Atli Benediktsson. (2018). Landslide inventory mapping from bitemporal high-resolution remote sensing images using change detection and multiscale segmentation. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 11(5), 1520-1532.

[11] Michele Calvello, Dario Peduto, & Livia Arena. (2016). Combined use of statistical and dinsar data analyses to define the state of activity of slow-moving landslides. Landslides, 14(2), 1-17.

[12] Lou, Y. , Clark, D. , Marks, P. , Muellerschoen, R. J. , & Wang, C. C. . (2016). Onboard radar processor development for rapid response to natural hazards. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(6), 2770-2776.

[13] Zhou Zhou, Xiao-qun Wang, Yu-feng Wei, Jun-hui Shen, & Man Shen. (2019). Simulation study of the void space gas effect on slope instability triggered by an earthquake. Journal of Mountain Science, 16(6), 1300-1317.

[14] L. Wang, Y. Shen, & C.-N. Bai. (2017). Three-dimensional analysis of force and deformation characteristics of oblique crossing of railway tunnel with landslide. Journal of Railway Engineering Society, 34(1), 16-22.

[15] Rwanga, S. S. , & Ndambuki, J. M. . (2017). Accuracy assessment of land use/land cover classification using remote sensing and gis. International Journal of Geosciences, 8(4), 611-622.

[16] Nhat-Duc Hoang, & Dieu Tien Bui. (2018). Spatial prediction of rainfall-induced shallow landslides using gene expression programming integrated with gis: a case study in vietnam. Natural Hazards, 92(3), 1871–1887.

[17] Chen Shengli, Qiao Hongbo, Wang Hongqi, Jiang Jinwei, Ma Jisheng, & Li Qingchang. (2017). Soil nutrient management of tobacco field based on gis and gps. Tobacco Science & Technology,50(3), 23-30.

[18] Francesca Franci, Gabriele Bitelli, Emanuele Mandanici, Diofantos Hadjimitsis, & Athos Agapiou. (2016). Satellite remote sensing and gis-based multi-criteria analysis for flood hazard mapping. Natural Hazards,83(1), 31-51.

[19] Gilbert, J. T. , Macfarlane, W. W. , & Wheaton, J. M. . (2016). The valley bottom extraction tool (v-bet): a gis tool for delineating valley bottoms across entire drainage networks. Computers & Geosciences, 97(December), 1-14.

[20] Hanne Glas, M. Jonckheere, A. Mandal, S. James-Williamson, & Greet Deruyter. (2017). A gis-based tool for flood damage assessment and delineation of a methodology for future risk assessment: case study for annotto bay, jamaica. Natural Hazards, 88(8), 1867-1891.

[21] Aldo Clerici, & Susanna Perego. (2016). A set of grass gis-based shell scripts for the calculation and graphical display of the main morphometric parameters of a river channel. International Journal of Geosciences, 7(7), 135-143.

[22] Szewczyk, M. , Kutorasinski, K. , Wronski, M. , & Florkowski, M. . (2017). Full-maxwell simulations of very fast transients in gis: case study to compare 3d and 2d-axisymmetric models of 1100 kv test set-up. IEEE Transactions on Power Delivery, 32(2), 733-739.

[23] D. Thinh Nguyen, Iskhaq Iskandar, & Son Ho. (2016). Land cover change and the co2 stock in the palembang city, indonesia: a study using remote sensing, gis technique and lumens. Egyptian Journal of Remote Sensing & Space Science, 19(2), 313-321.

[24] Abdel Rahman Al-Shabeeb, Rida Al-Adamat, & Atef Mashagbah. (2016). Ahp with gis for a preliminary site selection of wind turbines in the north west of jordan. International Journal of Geosciences, 07(10), 1208-1221.

[25] Raju Thapa, Srimanta Gupta, D. V. Reddy, & Harjeet Kaur. (2017). An evaluation of irrigation water suitability in the dwarka river basin through the use of gis-based modelling. Environmental Earth Sciences, 76(14), 471.

[26] Zou, J. , Zhang, W. , & Yang, Y. . (2016). Evaluation of water resources system vulnerability in southern hilly rural region based on the gis/rs take hengyang basin as an example. Scientia Geographica Sinica, 34(8), 1010-1017.

[27] James, P. , Jankowska, M. , Marx, C. , Hart, J. E. , Berrigan, D. , & Kerr, J. , et al. (2016). “spatial energetics”: integrating data from gps, accelerometry, and gis to address obesity and inactivity. American Journal of Preventive Medicine, 51(5), 792-800.