Landslide Susceptibility Mapping Based on Random Forest and Boosted Regression Tree Models, and a Comparison of Their Performance
Source abstract
Abstract
This study aims to analyze and compare landslide susceptibility at Woomyeon Mountain, South Korea, based on the random forest (RF) model and the boosted regression tree (BRT) model. Through the construction of a landslide inventory map, 140 landslide locations were found. Among these, 42 (30%) were reserved to validate the model after 98 (70%) had been selected at random for model training. Fourteen landslide explanatory variables related to topography, hydrology, and forestry factors were considered and selected, based on the results of information gain for the modeling. The results were evaluated and compared using the receiver operating characteristic curve and statistical indices. The analysis showed that the RF model was better than the BRT model. The RF model yielded higher specificity, overall accuracy, and kappa index than the BRT model. In addition, the RF model, with a prediction rate of 0.865, performed slightly better than the BRT model, which had a prediction rate of 0.851. These results indicate that the landslide susceptibility maps (LSMs) produced in this study had good performance for predicting the spatial landslide distribution in the study area. These LSMs could be helpful for establishing mitigation strategies and for land use planning.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Landslides and related hazards · Cryospheric studies and observations · Tree Root and Stability Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
BK21 Plus Project of the Graduate School of Earth Environmental Hazard System, Pukyong National University, Busan 48513, Korea
Department of Spatial Information Engineering, Pukyong National University, Busan 48513, Korea
References (58)
Show source-provided references
1. Landslide susceptibility mapping along road corridors in the Indian Himalayas using Bayesian logistic regression models10.1016/j.geomorph.2012.08.004 ↗
2. Climate change effects on landslides along the southwest coast of British Columbia10.1016/j.geomorph.2008.12.009 ↗
3. A hybrid feature selection algorithm integrating an extreme learning machine for landslide susceptibility modeling of Mt Woomyeon, South Korea10.1016/j.geomorph.2016.03.023 ↗
4. Landslide susceptibility mapping using frequency ratio, analytic hierarchy process, logistic regression, and artificial neural network methods at the Inje area, Korea10.1007/s12665-012-1842-5 ↗
5. Schuster, R.L. (1996). Socioeconomic Significance of Landslides: Investigation and Mitigation, National Academy Press. National Academy Press Transportation Research Board Special Report.
6. Estimating the quality of landslide susceptibility models10.1016/j.geomorph.2006.04.007 ↗
7. Landslide susceptibility mapping at Golestan Province, Iran: A comparison between frequency ratio, Dempster–Shafer, and weights-of-evidence models10.1016/j.jseaes.2012.10.005 ↗
8. Landslide susceptibility mapping for a landslide-prone area (Findikli, NE of Turkey) by likelihood-frequency ratio and weighted linear combination models10.1007/s00254-007-0882-8 ↗
9. Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: A case study from Kat landslides (Tokat—Turkey)10.1016/j.cageo.2008.08.007 ↗
10. Combining neural network with fuzzy, certainty factor and likelihood ratio concepts for spatial prediction of landslides10.1007/s11069-011-9847-z ↗
11. Landslide susceptibility analysis in the Hoa Binh Province of Vietnam using statistical index and logistic regression10.1007/s11069-011-9844-2 ↗
12. Integration of the statistical index method and the analytic hierarchy process technique for the assessment of landslide susceptibility in Huizhou, China10.1016/j.catena.2016.03.028 ↗
13. A comparative study of frequency ratio, weights of evidence and logistic regression methods for landslide susceptibility mapping: Sultan Mountains, SW Turkey10.1016/j.jseaes.2012.12.014 ↗
14. The 2010 Yushu earthquake triggered landslide hazard mapping using GIS and weight of evidence modeling10.1007/s12665-012-1624-0 ↗
15. Landslide susceptibility mapping by binary logistic regression, analytical hierarchy process, and statistical index models and assessment of their performances10.1007/s11069-013-0728-5 ↗
16. A GIS-based comparative study of frequency ratio, analytical hierarchy process, bivariate statistics and logistics regression methods for landslide susceptibility mapping in Trabzon, NE Turkey10.1016/j.catena.2011.01.014 ↗
17. A novel hybrid artificial intelligence approach based on the rotation forest ensemble and naïve Bayes tree classifiers for a landslide susceptibility assessment in Langao County, China10.1080/19475705.2017.1401560 ↗
18. Machine learning: Trend, perspectives, and prospects10.1126/science.aaa8415 ↗
19. Assessment of shallow landslide susceptibility using artificial neural networks in Jabonosa River Basin, Venezuela10.1016/j.enggeo.2004.10.004 ↗
20. An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps10.1016/j.enggeo.2008.01.004 ↗
21. Remote sensing and GIS-based landslide susceptibility mapping using frequency ratio, logistic regression, and fuzzy logic methods at the central Zab basin, Iran10.1007/s12665-015-4028-0 ↗
22. An expert knowledge-based approach to landslide susceptibility mapping using GIS and fuzzy logic10.1016/j.geomorph.2014.02.003 ↗
23. A GIS-based neuro-fuzzy procedure for integrating knowledge and data in landslide susceptibility mapping10.1016/j.cageo.2010.04.004 ↗
24. GIS-based modeling of rainfall-induced landslides using data mining-based functional trees classifier with AdaBoost, Bagging, and MultiBoost ensemble frameworks10.1007/s12665-016-5919-4 ↗
25. An assessment of multivariate and bivariate approaches in landslide susceptibility mapping: A case study of Duzkoy district10.1007/s11069-014-1506-8 ↗
26. Random forests and evidential belief function-based landslide susceptibility assessment in Western Mazandaran Province, Iran10.1007/s12665-015-4950-1 ↗
27. Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia
28. Comparison of a logistic regression and Naïve Bayes classifier in landslide susceptibility assessments: The influence of models complexity and training dataset size10.1016/j.catena.2016.06.004 ↗
29. Landslide susceptibility mapping using J48 Decision Tree with AdaBoost, Bagging and Rotation Forest ensembles in the Guangchang area (China)10.1016/j.catena.2018.01.005 ↗
30. A novel ensemble classifier of rotation forest and Naïve Bayer for landslide susceptibility assessment at the Luc Yen district, Yen Bai Province (Viet Nam) using GIS10.1080/19475705.2016.1255667 ↗
31. Korean Geotechnical Society (KGS) (2011). The Study on Investigation of Cause and Development of Restoration Policy about Landslide in Wumyon Area, Korean Geotechnical Society. (In Korean).
32. Cao, C., Xu, P., Wang, Y., Chen, J., Zheng, L., and Niu, C. (2016). Flash flood hazard susceptibility mapping using frequency ratio and statistical index methods in coalmine subsidence areas. Sustainability, 8.10.3390/su8090948 ↗
33. Assessment of the effects of training data selection on the landslide susceptibility mapping: A comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN)10.1080/19475705.2017.1407368 ↗
34. A physically based, variable contributing area model of basin hydrology/Un modèle à base physique de zone d’appel variable de l’hydrologie du bassin versant10.1080/02626667909491834 ↗
35. Landslide susceptibility maps comparing frequency ratio and artificial neural networks: A case study from the Nepal Himalaya10.1007/s12665-009-0426-5 ↗
36. Digital terrain modelling: A review of hydrological, geomorphological, and biological applications10.1002/hyp.3360050103 ↗
37. Sediment transport capacity of sheet and rill flow: Application of unit stream power theory10.1029/WR022i008p01350 ↗
38. A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process and multivariate statistical logistic regression for landslide susceptibility mapping10.1016/j.catena.2013.10.011 ↗
39. Liu, H., and Motoda, H. (2007). Ensemble-based variable selection using independent probes. Computational Methods of Feature Selection, Chapman and Hall/CRC.10.1201/9781584888796 ↗
40. Quinlan, J.T. (1993). C4.5: Programs for Machine Learning, Morgan Kaufmann Publishers.
41. Significance of variable selection and scaling issues for probabilistic modeling of rainfall-induced landslide susceptibility10.1007/s41324-017-0154-y ↗
42. Witten, I.G., and Frank, E. (2005). Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann Publishers. [2nd ed.].
43. Random forests10.1023/A:1010933404324 ↗
44. Mapping landslide susceptibility and types using Random Forest10.1080/20964471.2018.1472392 ↗
45. Groundwater spring potential modelling: Comprising the capability and robustness of three different modeling approaches10.1016/j.jhydrol.2018.08.027 ↗
46. Machine learning feature selection methods for landslide susceptibility mapping10.1007/s11004-013-9511-0 ↗
47. Letter to the editor: Stability of random forest importance measures10.1093/bib/bbq011 ↗
48. Schapire, R.E. (2003). The boosting approach to machine learning: An overview. Nonlinear Estimation and Classification, Springer.10.1007/978-0-387-21579-2_9 ↗
49. A working guide to boosted regression trees10.1111/j.1365-2656.2008.01390.x ↗
50. Comparison and ranking of different modelling techniques for prediction of site index in Mediterranean mountain forests10.1016/j.ecolmodel.2010.01.007 ↗
51. The boosting: A new idea of building models10.1016/j.chemolab.2009.09.002 ↗
52. A comparison between ten advanced and soft computing models for groundwater qanat potential assessment in Iran using R and GIS10.1007/s00704-016-2022-4 ↗
53. Predicting fish species richness in estuaries: Which modelling technique to use?10.1016/j.envsoft.2014.12.010 ↗
54. A novel geographical information system-based Ant Miner algorithm model for delineating groundwater flowing artesian well boundary: A case study from Iraqi southern and western deserts10.1007/s12665-017-6876-2 ↗
55. Techniques for evaluating the performance of landslide susceptibility models10.1016/j.enggeo.2009.12.004 ↗
56. A comparative study of least square support vector machines and multiclass alternating decision trees for spatial prediction of rainfall-induced landslides in a tropical cyclones area10.1007/s10706-016-9990-0 ↗
57. Characterising performance of environmental models10.1016/j.envsoft.2012.09.011 ↗
58. Classification of rockburst in underground projects: Comparison of ten supervised learning methods10.1061/(ASCE)CP.1943-5487.0000553 ↗