Volume 8, Issue 2 (2020)
ECOPERSIA 2020, 8(2): 65-76 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Adineh F, Motamedvaziri B, Ahmadi H, Moeini A. Successive Intermodal Ensembling: A Promising Approach to Improve the Performance of Data Mining Models for Landslide Susceptibility Assessment (A case study: Kolijan Rostaq Watershed, Iran). ECOPERSIA 2020; 8 (2) :65-76
URL: http://ecopersia.modares.ac.ir/article-24-36478-en.html
URL: http://ecopersia.modares.ac.ir/article-24-36478-en.html
1- Forest, Range & Watershed Management Department, Natural Resources and Environment Faculty, Science and Research Branch, Islamic Azad University, Tehran, Iran
2- Forest, Range & Watershed Management Department, Natural Resources and Environment Faculty, Science and Research Branch, Islamic Azad University, Tehran, Iran ,bmvaziri@gmail.com
3- Reclamation of Arid & Mountainous Regions Department, Agriculture Faculty, University of Tehran, Karaj, Iran
2- Forest, Range & Watershed Management Department, Natural Resources and Environment Faculty, Science and Research Branch, Islamic Azad University, Tehran, Iran ,
3- Reclamation of Arid & Mountainous Regions Department, Agriculture Faculty, University of Tehran, Karaj, Iran
Abstract: (3312 Views)
Aims: In the present study, random forest (RF) and support vector machine (SVM) were used to assess the applicability of ensemble modeling in landslide susceptibility assessment across the Kolijan Rostaq Watershed in Mazandaran Province, Iran.
Materials & Methods: Both models were used in two modeling modes: 1) A solitary use (i.e., SVM and RF) and 2) Their ensemble with a bivariate statistical model named the weights of evidence (WofE) which then generated two more models, namely SVM-WofE and RF-WofE. Further, the resulting maps of each stage were dually coupled using the weighted arithmetic mean operation and an intermodal blending of the previous stages.
Findings: Accuracy of the models was assessed via the receiver operating characteristic (ROC) curves based on which the goodness-of-fit of the SVM and the SVM-WofE models were 0.817 and 0.841, respectively, while their respective prediction accuracy values were found to be 0.848 and 0.825. The goodness-of-fit of the RF and the RF-WofE models respectively was 0.9 and 0.823, while their respective prediction accuracy values were found to be 0.886 and 0.823. The goodness-of-fit and prediction power of SVM and SVM-WofE ensemble were respectively 0.859 and 0.873. The same increasing pattern was evident for the ensemble of RF and RF-WofE where their goodness-of-fit and prediction power increased, respectively, up to 0.928 and 0.873. Moreover, the goodness-of-fit and prediction power of RF-SVM ensemble were increased up to 0.932 and 0.899, respectively. The results of the averaged Kappa values throughout a 10-fold cross-validation test as an auxiliary accuracy assessment attested to the same results obtained from the ROC curves.
Conclusion: Successive intermodal ensembling approach is a simple and self-explanatory method so far as the context of many data mining techniques with a highly complex structure has been simply benefitted from the weighted averaging technique.
Materials & Methods: Both models were used in two modeling modes: 1) A solitary use (i.e., SVM and RF) and 2) Their ensemble with a bivariate statistical model named the weights of evidence (WofE) which then generated two more models, namely SVM-WofE and RF-WofE. Further, the resulting maps of each stage were dually coupled using the weighted arithmetic mean operation and an intermodal blending of the previous stages.
Findings: Accuracy of the models was assessed via the receiver operating characteristic (ROC) curves based on which the goodness-of-fit of the SVM and the SVM-WofE models were 0.817 and 0.841, respectively, while their respective prediction accuracy values were found to be 0.848 and 0.825. The goodness-of-fit of the RF and the RF-WofE models respectively was 0.9 and 0.823, while their respective prediction accuracy values were found to be 0.886 and 0.823. The goodness-of-fit and prediction power of SVM and SVM-WofE ensemble were respectively 0.859 and 0.873. The same increasing pattern was evident for the ensemble of RF and RF-WofE where their goodness-of-fit and prediction power increased, respectively, up to 0.928 and 0.873. Moreover, the goodness-of-fit and prediction power of RF-SVM ensemble were increased up to 0.932 and 0.899, respectively. The results of the averaged Kappa values throughout a 10-fold cross-validation test as an auxiliary accuracy assessment attested to the same results obtained from the ROC curves.
Conclusion: Successive intermodal ensembling approach is a simple and self-explanatory method so far as the context of many data mining techniques with a highly complex structure has been simply benefitted from the weighted averaging technique.
Article Type: Original Research |
Subject:
Watershed Management
Received: 2019/09/19 | Accepted: 2019/12/7 | Published: 2020/05/19
Received: 2019/09/19 | Accepted: 2019/12/7 | Published: 2020/05/19
References
1. Radbruch-Hall DH, Varnes DJ. Landslides-cause and effect. Bull Int Assoc Eng Geol. 1976;13(1):205-16. [Link] [DOI:10.1007/BF02634797]
2. Van Westen CJ, Van Asch TW, Soeters R. Landslide hazard and risk zonation-why is it still so difficult?. Bull Engi Geol Environt. 2006;65(2):167-84. [Link] [DOI:10.1007/s10064-005-0023-0]
3. Brenning A. Spatial prediction models for landslide hazards: Review, comparison and evaluation. Nat Hazards Earth Syst Sci, Copernic Publ Eur Geosci :union:. 2005;5(6):853-62. [Link] [DOI:10.5194/nhess-5-853-2005]
4. Yao X, Tham LG, Dai FC. Landslide susceptibility mapping based on support vector machine: A case study on natural slopes of Hong Kong, China. Geomorphology. 2008;101(4):572-82. [Link] [DOI:10.1016/j.geomorph.2008.02.011]
5. Pourghasemi HR, Jirandeh AG, Pradhan B, Xu C, Gokceoglu C. Landslide susceptibility mapping using support vector machine and GIS at the Golestan Province, Iran. J Earth Syst Sci. 2013;122(2):349-69. [Link] [DOI:10.1007/s12040-013-0282-2]
6. Jebur MN, Pradhan B, Tehrany MS. Manifestation of LiDAR-derived parameters in the spatial prediction of landslides using novel ensemble evidential belief functions and support vector machine models in GIS. IEEE J Sel Top Appl Earth Obse Remote Sens. 2014;8(2):674-90. [Link] [DOI:10.1109/JSTARS.2014.2341276]
7. Ren F, Wu X, Zhang K, Niu R. Application of wavelet analysis and a particle swarm-optimized support vector machine to predict the displacement of the Shuping landslide in the Three Gorges, China. Environ Earth Sci. 2015;73(8):4791-804. [Link] [DOI:10.1007/s12665-014-3764-x]
8. Bui DT, Tuan TA, Klempe H, Pradhan B, Revhaug I. Spatial prediction models for shallow landslide hazards: A comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree. Landslides. 2016;13(2):361-78. [Link] [DOI:10.1007/s10346-015-0557-6]
9. Huang Y, Zhao L. Review on landslide susceptibility mapping using support vector machines. CATENA. 2018;165:520-9. [Link] [DOI:10.1016/j.catena.2018.03.003]
10. Mohammady M, Pourghasemi HR, Amiri M. Assessment of land subsidence susceptibility in Semnan plain (Iran): A comparison of support vector machine and weights of evidence data mining algorithms. Nat Hazards. 2019;99(2):951-71. [Link] [DOI:10.1007/s11069-019-03785-z]
11. Prasad AM, Iverson LR, Liaw A. Newer classification and regression tree techniques: Bagging and random forests for ecological prediction. Ecosystems. 2006;9(2):181-99. [Link] [DOI:10.1007/s10021-005-0054-1]
12. Strobl C, Boulesteix AL, Kneib T, Augustin T, Zeileis A. Conditional variable importance for random forests. BMC Bioinform. 2008;9(1):307. [Link] [DOI:10.1186/1471-2105-9-307]
13. Bachmair S, Weiler M. Hillslope characteristics as controls of subsurface flow variability. Hydrol Earth Syst Sci. 2012;16(10):3699. [Link] [DOI:10.5194/hess-16-3699-2012]
14. Vorpahl P, Elsenbeer H, Märker M, Schröder B. How can statistical models help to determine driving factors of landslides?. Ecol Model. 2012;239:27-39. [Link] [DOI:10.1016/j.ecolmodel.2011.12.007]
15. Catani F, Lagomarsino D, Segoni S, Tofani V. Landslide susceptibility estimation by random forests technique: Sensitivity and scaling issues. Nat Hazards Earth Syst Sci. 2013;13(11):2815-31. [Link] [DOI:10.5194/nhess-13-2815-2013]
16. Pourghasemi HR, Kerle N. Random forests and evidential belief function-based landslide susceptibility assessment in western Mazandaran Province, Iran. Environ Earth Sci. 2016;75(3):185. [Link] [DOI:10.1007/s12665-015-4950-1]
17. Naghibi SA, Pourghasemi HR, Dixon B. GIS-based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran. Environ Monit Assess. 2016;188(1):44. [Link] [DOI:10.1007/s10661-015-5049-6]
18. Pourtaghi ZS, Pourghasemi HR, Aretano R, Semeraro T. Investigation of general indicators influencing on forest fire and its susceptibility modeling using different data mining techniques. Ecol Indic. 2016;64:72-84. [Link] [DOI:10.1016/j.ecolind.2015.12.030]
19. Golkarian A, Naghibi SA, Kalantar B, Pradhan B. Groundwater potential mapping using C5. 0, random forest, and multivariate adaptive regression spline models in GIS. Environ Monit Assess. 2018;190(3):149. [Link] [DOI:10.1007/s10661-018-6507-8]
20. Mohammady M, Pourghasemi HR, Amiri M. Land subsidence susceptibility assessment using random forest machine learning algorithm. Environ Earth Sci. 2019;78(16):503. [Link] [DOI:10.1007/s12665-019-8518-3]
21. Zarei P, Talebi A, Alaie Taleghani M. Sensitivity analysis of effective factors in hillslopes instability; a Case Study of Javanrud region, Kermanshah province. Ecopersia. 2018;6(4):259-68. [Link]
22. Nafarzadegan AR, Talebi A, Malekinezhad H, Emami N. Antecedent rainfall thresholds for the triggering of deep-seated landslides (case study: Chaharmahal & Bakhtiari Province, Iran). Ecopersia. 2013;1(1):23-39. [Link]
23. O'brien RM. A caution regarding rules of thumb for variance inflation factors. Qual Quant. 2007;41(5):673-90. [Link] [DOI:10.1007/s11135-006-9018-6]
24. Breiman L. Random forests. Mach Learn. 2001;45(1):5-32. [Link] [DOI:10.1023/A:1010933404324]
25. Calle ML, Urrea V. Letter to the editor: Stability of random forest importance measures. Brief Bioinform. 2010; 12(1):86-9. [Link] [DOI:10.1093/bib/bbq011]
26. Nicodemus KK. Letter to the editor: On the stability and ranking of predictors from random forest variable importance measures. Brief Bioinform. 2011;12(4):369-73. [Link] [DOI:10.1093/bib/bbr016]
27. Jakkula V. Tutorial on support vector machine (svm). Washington DC.; 2006. [Link]
28. Joachims T. Text categorization with support vector machines: Learning with many relevant features. European Conference on Machine Learning, 1998 April 21-23, Chemnitz, Germany. Berlin: Springer; 1998. [Link]
29. Brown MP, Grundy WN, Lin D, Cristianini N, Sugnet CW, Furey TS, et al. Knowledge-based analysis of microarray gene expression data by using support vector machines. Proc Natl Acad Sci. 2000;97(1):262-7. [Link] [DOI:10.1073/pnas.97.1.262]
30. Cristianini N, Scholkopf B. Support vector machines and kernel methods: The new generation of learning machines. AI Magazine. 2002;23(3):31. [Link]
31. Huang C, Davis LS, Townshend JR. An assessment of support vector machines for land cover classification. Int J Remote Sens. 2002;23(4):725-49. [Link] [DOI:10.1080/01431160110040323]
32. Guo Q, Kelly M, Graham CH. Support vector machines for predicting distribution of Sudden Oak Death in California. Ecol Model. 2005;182(1):75-90. [Link] [DOI:10.1016/j.ecolmodel.2004.07.012]
33. Statnikov A. A gentle introduction to support vector machines in biomedicine: Theory and methods. Singapore: World Scientific; 2011. [Link] [DOI:10.1142/7922]
34. Statnikov A, Aliferis CF, Hardin DP, Guyon I. A gentle introduction to support vector machines in biomedicine. Singapore: World Scientific Publishing Company; 2013. [Link] [DOI:10.1142/7923]
35. Kecman V. Support vector machines-an introduction. In: Support vector machines: theory and applications. Berlin: Springer; 2005. pp. 1-47 [Link] [DOI:10.1007/10984697_1]
36. Marjanović M, Kovačević M, Bajat B, Voženílek V. Landslide susceptibility assessment using SVM machine learning algorithm. Engi Geol. 2011;123(3):225-34. [Link] [DOI:10.1016/j.enggeo.2011.09.006]
37. Bonham-Carter GF, Agterberg FP, Wright DF. Integration of geological datasets for gold exploration in Nova Scotia. Photogramm Eng Remote Sens. 1988;54(11):1585-92. [Link]
38. Van Westen CJ. Geo-information tools for landslide risk assessment: An overview of recent developments. Landslides Eval Stab. 2004;1:39-56. [Link] [DOI:10.1201/b16816-6]
39. Kornejady A, Ownegh M, Rahmati O, Bahremand A. Landslide susceptibility assessment using three bivariate models considering the new topo-hydrological factor: HAND. Geocarto Int. 2018;33(11):1155-85. [Link] [DOI:10.1080/10106049.2017.1334832]
40. Pontius Jr RG, Schneider LC. Land-cover change model validation by an ROC method for the Ipswich watershed, Massachusetts, USA. Agric Ecosyst Environ. 2001;85(1-3):239-48. [Link] [DOI:10.1016/S0167-8809(01)00187-6]
41. Kuhn M. The caret package. R Foundation for Statistical Computing [Internet]. Vienna; 2012 [cited 2019, June 20]. [Link] [DOI:10.5813/www.ieit-web.org/IJADC/2012.4.5]
42. Lombardo L, Cama M, Maerker M, Rotigliano E. A test of transferability for landslides susceptibility models under extreme climatic events: Application to the Messina 2009 disaster. Nat Hazards. 2014;74(3):1951-89. [Link] [DOI:10.1007/s11069-014-1285-2]
43. Lombardo L, Cama M, Conoscenti C, Märker M, Rotigliano EJ. Binary logistic regression versus stochastic gradient boosted decision trees in assessing landslide susceptibility for multiple-occurring landslide events: Application to the 2009 storm event in Messina (Sicily, southern Italy). Nat Hazards. 2015;79(3):1621-48. [Link] [DOI:10.1007/s11069-015-1915-3]
44. Lombardo L, Fubelli G, Amato G, Bonasera M. Presence-only approach to assess landslide triggering-thickness susceptibility: A test for the Mili catchment (north-eastern Sicily, Italy). Nat Hazards. 2016;84(1):565-88. [Link] [DOI:10.1007/s11069-016-2443-5]
45. Hosmer DW, Lemeshow S. Applied logistic regression. New York: JohnWiley& Sons; 2000. [Link] [DOI:10.1002/0471722146]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |