Skip to main content

Comparative review of data-driven landslide susceptibility models: case study in the Eastern Andes mountain range of Colombia


Estimating the likelihood of landslides has proven to be critical for development and protection of infrastructure (e.g. pipelines, roads) and urban settlements. Currently, for regional studies of landslide susceptibility only qualitative or statistical evaluations are possible due to the large spatial variability of geological properties, topography, rainfall patterns, etc. In this paper, we explore an alternative to these approaches using data-driven methodologies to determine landslide susceptibility. We give special attention to the use of geographical information systems, machine learning and statistical techniques to build landslide susceptibility maps. These methods have input as fourteen key causative factors that might influence landslides occurrence. Additionally, feature extraction and feature selection are performed to evaluate if dimensionality reduction increases the prediction accuracy of the machine learning models. The models were compared using a case study in the Eastern Cordillera of Colombia, where the best performing model achieved a predictive performance of \(93.07\%\).

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13


  • Abadi Martín,Agarwal A, Barham P, Brevdo E, Chen Z,Citro C, Corrado GS,Davis A, Dean J, Devin M,Ghemawat S, Goodfellow I, Harp A, Irving G,Isard M, Jia Y, Jozefowicz R, Kaiser L,Kudlur M, Levenberg J, Mané D, Monga R,Moore S, Murray D, Olah C, Schuster M,Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P,Vanhoucke V, Vasudevan V, Viégas F,Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y,Zheng X (2015) TensorFlow: large-scale machine learning onheterogeneous systems, 2015. URL

  • Abu-Jamous B, Fa R, Nandi A (2015) Feature selection, chapter 8, pages 109–117. John Wiley & Sons, Ltd, ISBN 9781118906545.

  • Achour Y, Pourghasemi HR (2020) How do machine learning techniques help in increasing accuracy of landslide susceptibility maps? Geosci Front, 11(3):871–883, ISSN 1674-9871.

  • Alvarado-Franco JP, Castro D, Estrada N, Caicedo B, ánchez-Silva MS, Camacho LA, Muñoz F (2017) Quantitative-mechanistic model for assessing landslide probability and pipeline failure probability due to landslides. Eng Geol, 222:212–224, ISSN 0013-7952.

  • Bedoya-González DA, Vargas-Jiménez CA, Chicangana G (2014) Modelos de atenuación para una zona del piedemonte llanero colombiano utilizando atenuación de ondas coda. Boletin de Geología, 36:91–100, ISSN 0120-0283. URL

  • Böhner Jürgen, Selige Thomas (2002) Spatial prediction of soil attributes using terrain analysis and climate regionalization. Gottinger Geograpihsche Abhandlungen, 115, jan

  • Bonham-Carter GF (2002) Geographic information systems for geoscientist: modelling with GIS. In Merriam, D.F. (Ed.), Computer methods in the geosciences., pages 302–334. Pergamon/Elsevier, New York

  • Bragagnolo L, da Silva RV, Grzybowski JMV (2020) Artificial neural network ensembles applied to the mapping of landslide susceptibility. CATENA, 184:104240, ISSN 0341-8162.

  • Breiman L (2001) Random Forests. Mach Learn, 45(1):5–32, ISSN 1573-0565.

  • Chae B-G, Park H-J, Catani F, Simoni A, Berti M (2017) Landslide prediction, monitoring and early warning: a concise review of state-of-the-art. Geosci J, 21(6):1033–1070, ISSN 1598-7477.

  • Chen W, Xie X, Wang J, Pradhan B, Hong H, Bui D T, Duan Z, Ma J (2017) A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility. CATENA, 151:147–160, ISSN 0341-8162.

  • Chen W, Zhang S, Li R, Shahabi H (2018) Performance evaluation of the GIS-based data mining techniques of best-first decision tree, random forest, and naïve Bayes tree for landslide susceptibility modeling. Sci Total Environ, 644:1006–1018, ISSN 0048-9697.

  • Conforti M, Pascale S, Robustelli G, Sdao F (2014) Evaluation of prediction capability of the artificial neural networks for mapping landslide susceptibility in the Turbolo River catchment (northern Calabria, Italy). CATENA, 113:236–250, ISSN 0341-8162.

  • Cooper MA , Addison FT , Alvarez R, Coral M, Graham RH , Hayward AB , Howe S, Martinez J, Naar J, Peñas R, Pulham AJ , Taborda A (1995) Basin development and tectonic history of the llanos basin, eastern cordillera, and middle magdalena valley, Colombia1. AAPG Bull, 79(10):1421–1442, oct ISSN 0149-1423.

  • Cruden DM, Varnes DJ (1996) Landslide types and processes. Spec Rep-Natl Res Counc, Transp Res Board 247:36–57

    Google Scholar 

  • Dahal RK, Hasegawa S, Nonomura A, Yamanaka M, Dhakal S, Paudyal P (2008) Predictive modelling of rainfall-induced landslide hazard in the Lesser Himalaya of Nepal based on weights-of-evidence. Geomorphology, 102(3):496–510, ISSN 0169-555X.

  • Dou J, Tien BD, Yunus AP, Jia K, Song X, Revhaug I, Xia H, Zhu Z (2015) Optimization of causative factors for landslide susceptibility evaluation using remote sensing and GIS data in parts of Niigata, Japan. PLOS ONE.

    Article  Google Scholar 

  • Dou J, Yunus AP, Tien BD, Merghadi A, Sahana M, Zhu Z, Chen CW, Khosravi K, Yang Y, Pham BT (2019) Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan. Sci Total Environ, 662:332–346, ISSN 0048-9697.

  • Duque-Escobar G (2019) Qué hacer con la vía al Llano? Razón Pública, sep

  • Erener A, Mutlu A, Düzgün HS (2016) A comparative study for landslide susceptibility mapping using GIS-based multi-criteria decision analysis (MCDA), logistic regression (LR) and association rule mining (ARM). Eng Geol, 203:45–55, ISSN 0013-7952.

  • Goetz J N, Brenning A, Petschko H, Leopold P (2015) Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling. Comput & Geosci, 81:1–11, ISSN 0098-3004.

  • Gómez J, Montes NE, Nivia A, Diederix H, Geológico Mapa, de Colombia, (2015) Escala 1:1 000 000. Technical report, Servicio Geológico Colombiano, Bogotá, p 2015

  • Gómez J, Schobbenhaus C, Montes NE, Map Geological, of South America, (2019) Scale 1:5 000 000. Colombian geological survey, and geological survey of Brazil., Paris, Technical report, Commission for the Geological Map of the World (CGMW), p 2019

  • Greenwell brandon , Boehmke B, Cunningham J , Developers GBM (2019) gbm: generalized boosted regression models, URL

  • Guzmán D, Ruiz JF, Cadena M (2014) Regionalización de Colombia según la estacionalidad de la precipitación media mensual, a través de análisis de componentes principales (ACP). Technical report, IDEAM, Bogotá, URL

  • Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction. Springer, New York, New York, NY. 978-0-387-84857-0.

  • Hervás J, Bobrowsky P (2009) Mapping: inventories, susceptibility, hazard and risk. In Kyoji Sassa and Paolo Canuti, editors, Landslides - Disaster Risk Reduction, pages 321–349. Springer Berlin Heidelberg, Berlin, Heidelberg, ISBN 978-3-540-69970-5.

  • Huang F, Yin K , Huang J, Gui L, Wang P (2017) Landslide susceptibility mapping based on self-organizing-map network and extreme learning machine. Eng Geol, 223:11–22, ISSN 0013-7952.

  • IGAC. Vector database of Colombia. Scale 1:100,000, 2019. URL

  • Krauss C, Do XA , Huck N (2017) Deep neural networks, gradient-boosted trees, random forests: statistical arbitrage on the S&P 500. Euro J Op Res, 259 (2):689–702, ISSN 0377-2217.

  • Kuhn M (2020) caret: classification and regression training,

  • Latif ZA, Aman SNA, Pradhan B (2012) Landslide susceptibility mapping using LiDAR derived factors and frequency ratio model: Ulu Klang area, Malaysia. In 2012 IEEE 8th international colloquium on signal processing and its applications, pages 378–382,

  • Lee JH, Sameen MI, Pradhan B, Park HJ (2018) Modeling landslide susceptibility in data-scarce environments using optimized data mining and statistical methods. Geomorphology, 303:284–298, ISSN 0169-555X.

  • Liaw A, Wiener M (2002) Classification and Regression by randomForest. R News, 2(3):18–22,

  • Lin GF , Chang MJ, Huang YC , Ho JY (2017) Assessment of susceptibility to rainfall-induced landslides using improved self-organizing linear output map, support vector machine, and logistic regression. Eng Geol, 224:62–74, ISSN 0013-7952.

  • Mattivi P, Franci F, Lambertini A, Bitelli G (2019) TWI computation: a comparison of different open source GISs. Open Geospatial Data, Softw Stand, 4 (1):6, ISSN 2363-7501.

  • Nefeslioglu HA , Gokceoglu C, Sonmez H (2008) An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps. Eng Geol, 97(3):171–191, ISSN 0013-7952.

  • Olaya V, Conrad O (2009)Chapter 12 Geomorphometry in SAGA. Dev Soil Sci,

  • Othman AA, Gloaguen R, Andreani L, Rahnama M (2018) Improving landslide susceptibility mapping using morphometric features in the Mawat area, Kurdistan region, NE Iraq: comparison of different statistical models. Geomorphology, 319:147–160, ISSN 0169-555X.

  • Ozdemir A (2020) A comparative study of the frequency ratio, analytical hierarchy process, artificial neural networks and fuzzy logic methods for landslide susceptibility mapping: Taşkent (Konya), Turkey. Geotech Geol Eng, ISSN 1573-1529.

  • Pabón José D, Zea J, León G, Hurtado G, González OC, Montealegre JE (1998) 3. La atmósfera, el tiempo y el clima. In: Pablo Leyva Franco and IDEAM, editors, El medio ambiente en Colombia, chapter 3, pages 34–91. IDEAM (Instituto de Hidrología Meteorología y EstudiosAmbientales), Santa Fe de Bogotá :. ISBN 9589585094. URL

  • Park Soyoung, Kim Jinsoo (2019) Landslide susceptibility mapping based on random forest and boosted regression tree models, and a comparison of their performance. Appl Sci 9:942.

    Article  Google Scholar 

  • Park Y-S, Lek S (2016) Chapter 7 - Artificial neural networks: multilayer perceptron for ecological modeling. In: Sven Erik Jørgensen, editor, Ecological Model Types, volume 28 of Developments in environmental modelling, pages 123–140. Elsevier,

  • Parravano V, Teixell A, Mora A (2015) Influence of salt in the tectonic development of the frontal thrust belt of the eastern Cordillera (Guatiquía area, Colombian Andes). Interpretation, 3(4):SAA17–SAA27, jul ISSN 2324-8858.

  • Pham B, Tien BD, Pourghasemi HR, Prakash I, Dholakia M (2015) Landslide susceptibility assessment in the Uttarakhand area (India) using GIS: a comparison study of prediction capability of naïve bayes, multilayer perceptron neural networks, and functional trees methods. Theor Appl Climatol.

    Article  Google Scholar 

  • Pradhan B, Seeni MI, Kalantar B (2017) Performance evaluation and densitivity analysis of expert-based, statistical, machine learning, and hybrid models for producing landslide susceptibility maps, chapter 11, pages 193–232. Springer International Publishing, Cham, ISBN 978-3-319-55342-9.

  • Profillidis VA, Botzoris GN (2019) Chapter 8 - artificial intelligence-neural network methods. In: V A Profillidis and G N Botzoris (eds), Modeling of Transport Demand, pages 353–382. Elsevier, ISBN 978-0-12-811513-8.

  • Regmi NR, Giardino JR , Vitek JD (2010) Modeling susceptibility to landslides using the weight of evidence approach: Western Colorado, USA. Geomorphology, 115(1):172–187, ISSN 0169-555X.

  • Reichenbach P, Rossi M, Malamud BD, Mihir M, Guzzetti F (2018) A review of statistically-based landslide susceptibility models. Earth-Sci Rev, 180:60–91, ISSN 0012-8252.

  • Schaathun HG (2012) Feature selection and evaluation, chapter 13, pages 217–243. John Wiley & Sons, Ltd, ISBN 9781118437957.

  • Serra N, Rea T, Di CP, Sergi C (2019) Continuity correction of Pearson’s chi-square test in 2x2 contingency tables: a mini-review on recent development. Epidemiol, Biostat Public Health.

    Article  Google Scholar 

  • Servicio Geológico Colombiano (2015) Zonificación geomecánica y de amenaza por movimientos en masa del municipio de popayán - cauca. Technical report, Servicio Geológico Colombiano, Bogotá

  • Servicio Geológico Colombiano. Memoria explicativa de la zonificación de la susceptibilidad y amenaza relativa por movimientos en masa escala 1:100.000 PLANCHA 266 - VILLAVICENCIO. Technical report, Servicio Geológico Colombiano, Bogotá, 2016

  • Sidle RC, Bogaard TA (2016) Dynamic earth system and ecological controls of rainfall-initiated landslides. Earth-Sci Rev, 159:275–291, ISSN 0012-8252.

  • Suleiman A, Tight MR, Quinn AD (2016) Hybrid neural networks and boosted regression tree models for predicting roadside particulate matter. Environ Model Assess, 21 (6):731–750, ISSN 1573-2967.

  • Taalab K, Cheng T, Zhang Y (2018) Mapping landslide susceptibility and types using random forest. Big Earth Data, 2(2):159–178, ISSN 2096-4471.

  • Thuro K, Singer J, Menschik B, Breuninger T, Gamperl M (2020) Development of an early warning system for landslides in the tropical Andes (Medellín; Colombia). Geomech Tunnel, 13(1): 103–115, feb . ISSN 1865-7362.

  • Tien BD , Tuan TA, Klempe H, Pradhan B, Revhaug I (2016) 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, 13(2):361–378, ISSN 1612-5118.

  • Torgo Luís (2016) Data mining with R: learning with case studies, second edition.

  • van Westen CJ , and Terlien MJT. An approach towards deterministic landslide hazard analysis in GIS. A case study from manizales (colombia). Earth Surface Processes and Landforms, 21 (9):853–868, ISSN 0197-9337.;2-C

  • Varnes DJ (1978) Slope movement types and processes. Special report-transportation research board, pages 11–33,

  • Vega JA, Hidalgo CA (2016) Quantitative risk assessment of landslides triggered by earthquakes and rainfall based on direct costs of urban buildings. Geomorphology, 273:217–235, ISSN 0169-555X.

  • Wang Q, Li W, Xing M, Wu Y, Pei Y, Yang D, Bai H (2016) Landslide susceptibility mapping at Gongliu county, China using artificial neural network and weight of evidence models. Geosci J, 20(5):705–718, ISSN 1598-7477.

  • Yilmaz I (2009) Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: a case study from Kat landslides (Tokat-Turkey). Comp Geosci, 35(6): 1125–1138, ISSN 0098-3004.

  • Youssef AM, Pourghasemi HR, Pourtaghi ZS, Al-Katheeri MM (2016) 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. Landslides, 13(5):839–856, ISSN 1612-5118.

  • Zhang K, Wu , Niu R, Yang Ke, Zhao Lingran (2017) The assessment of landslide susceptibility mapping using random forest and decision tree methods in the Three Gorges Reservoir area, China. Environ Earth Sci, 76(11):405, ISSN 1866-6299.

  • Zhu L, Huang JF (2006) GIS-based logistic regression method for landslide susceptibility mapping in regional scale. J Zhejiang Univ-Sci A, 7 (12):2007–2017, ISSN 1862-1775.

Download references


The authors would like to thank the anonymous reviewer who provided numerous comments and suggestions, resulting in an improved manuscript.


This work was supported by Universidad de los Andes (FAPA fund PR.3.2020.7367 granted to Dr. Nitescu).

Author information

Authors and Affiliations



Wilmar Calderón Guevara prepared, processed the data, and executed the GBM, RF and WOE methods. Daniel Villarraga executed the ANN method. Mauricio Sánchez-Silva, Bogdan Nitescu and Wilmar Calderón-Guevara wrote the manuscript and supported the analysis and discussion. All authors have checked and revised the manuscript.

Corresponding author

Correspondence to Wilmar Calderón-Guevara.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Calderón-Guevara, W., Sánchez-Silva, M., Nitescu, B. et al. Comparative review of data-driven landslide susceptibility models: case study in the Eastern Andes mountain range of Colombia. Nat Hazards 113, 1105–1132 (2022).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


  • Landslides
  • Susceptibility
  • Machine learning
  • Data-analytics
  • GIS