Inge CuC

Mapa de susceptibilidad por movimiento en masa en la localidad Rafael Uribe Uribe de Bogotá Colombia, mediante Máquinas de Vectores de Soporte

Miguel Alfonso Solano Padilla

Universidad Nacional Autónoma de México

Carlos Arturo Peña Rincón

Universidad Sergio Arboleda

DOI: https://doi.org/10.17981/ingecuc.21.2.2025.11

Palabras clave: Aprendizaje de Máquina, Máquinas de Vectores de Soporte, Sistemas de Información Geográfica (SIG), mapa de susceptibilidad, variables condicionantes, Núcleo

---

Resumen

Introducción: La susceptibilidad a la ocurrencia de deslizamientos fue reconocida como un factor clave para contribuir a la elaboración de escenarios de riesgo y al fortalecimiento del conocimiento sobre el riesgo de desastres, lo que respaldó la gestión del uso del suelo en áreas urbanas. Un reto de las metodologías es contribuir al fortalecimiento de los sistemas de alerta temprana.

Objetivo: Se integraron los datos de las variables condicionantes para producir el mapa de susceptibilidad a deslizamientos en la localidad de ‘Rafael Uribe Uribe’, en la ciudad de Bogotá, mediante la aplicación de la técnica de Máquinas de Vectores de Soporte (SVM).

Metodología: Se utilizó un registro histórico de 430 eventos ocurridos entre 2008 y 2015, junto con variables relacionadas con la topografía, uso del suelo, distancia a vías, geología y precipitación del área de estudio. Con esta información se construyó una base de datos con 12 variables condicionantes. Los datos fueron divididos aleatoriamente: el 75 % se empleó para generar el modelo mediante la técnica de Máquinas de Vectores de Soporte (SVM) con validación cruzada K-fold y búsqueda en malla (grid search), mientras que el restante 25 % se destinó a la validación del modelo.

Resultados:  Se obtuvo el mapa de susceptibilidad de la localidad con un nivel de precisión del 98 % utilizando el núcleo RBF y del 97 % para el núcleo lineal, validado mediante la curva Característica Operativa del Receptor (ROC). La técnica de Máquinas de Vectores de Soporte (SVM) fue aplicada exitosamente para clasificar las zonas del área de estudio en categorías de estabilidad e inestabilidad.
Conclusiones: Los resultados respaldaron la aplicabilidad del Aprendizaje de Máquina en el análisis de susceptibilidad, en concordancia con los avances promovidos por la comunidad científica internacional.

 

---

Citas

Hungr, O., Leroueil, S., & Picarelli, L, “The Varnes classification of landslide types, an update”. Landslides., vol. 11, pp. 167-194. 2014. https://doi.org/10.1007/s10346-013-0436-y.

Li, Y., & Mo, P. ,“A unified landslide classification system for loess slopes: A critical review”. Geomorphology, vol. 340, pp. 67-83. 2019. https://doi.org/10.1016/j.geomorph.2019.04.020.

Fan, X., Dufresne, A., Subramanian, S. S., Strom, A., Hermanns, R., Stefanelli, C. T. & Xu, Q., “The formation and impact of landslide dams–State of the art”. Earth-Science Reviews, vol. 203, pp. 103116. ,2020 https://doi.org/10.1016/j.earscirev.2020.103116.

Froude, M. J., & Petley, D. N. ,“Global fatal landslide occurrence from 2004 to 2016”. Natural Hazards and Earth System Sciences, vol.18, no. 8, pp. 2161-2181.2018. https://doi.org/10.5194/nhess-18-2161-2018.

Haque, U., Da Silva, P. F., Devoli, G., Pilz, J., Zhao, B., Khaloua, A. & Glass, G. E, “The human cost of global warming: Deadly landslides and their triggers (1995–2014)”. Science of the Total Environment, vol. 682, pp. 673-684. 2019. https://doi.org/10.1016/j.scitotenv.2019.03.415.

Segoni, S., Piciullo, L., & Gariano, S. L., “A review of the recent literature on rainfall thresholds for landslide occurrence”. Landslides, vol. 15, no. (8), pp. 1483-1501.2018. https://doi.org/10.1007/s10346-018-0966-4.

Villegas-González, P. A., Ramos-Cañón, A. M., González-Méndez, M., González-Salazar, R. E., & De Plaza-Solórzano, J. S.,”Territorial vulnerability assessment frame in Colombia: Disaster risk management”. International journal of disaster risk reduction, vol. 21, pp. 384-395. 2017. https://doi.org/10.1016/j.ijdrr.2017.01.003.

Sarmiento, J. P., Hoberman, G., Ilcheva, M., Asgary, A., Majano, A. M., Poggione, S., & Duran, L. R. , “Private sector and disaster risk reduction: the cases of Bogota, Miami, Kingston, San Jose, Santiago, and Vancouver”. International Journal of Disaster Risk Reduction, vol. 14, pp. 225-237,2015.https://doi.org/10.1016/j.ijdrr.2014.09.008.

Guzman, L. A., Escobar, F., Peña, J., & Cardona, R., “A cellular automata-based land-use model as an integrated spatial decision support system for urban planning in developing cities: The case of the Bogotá region”. Land use policy, vol. 92, pp.104445, 2020. https://doi.org/10.1016/j.landusepol.2019.104445.

Korup, O., & Stolle, A., “Landslide prediction from machine learning”. Geology today, vol. 30, no. 1, pp. 26-33,2014. https://doi.org/10.1111/gto.12034.

Scheidegger, A.E. (1998). “Tectonic predesign of mass movements with examples from the Chinese Himalaya”. Geomorphology, vol. 26, no. (1-3), pp. 37-46,1988. https://doi.org/10.1016/S0169-555X(98)00050-6.

Colombian Geological Survey. (2017). Methodological Guide for the Zoning of Mass Movement Hazard Scale (“Guía Metodológica para la Zonificación de Amenaza por Movimiento en Masa Escala”) 1:25.000, Available on: https://doi.org/10.32685/9789585978225.

Corominas, J., van Westen, C., Frattini, P., Cascini, L., Malet, J. P., Fotopoulou, S., ... & Smith, J. T., “Recommendations for the quantitative analysis of landslide risk”. Bulletin of engineering geology and the environment, vol. 73, pp. 209-263, 2014. https://doi.org/10.1007/s10064-013-0538-8.

Peña Rincón, C. A., Precipitation Data with the HSB Model for Forecasting Shallow Landslide Susceptibility (“Datos de Precipitación con el modelo HSB para pronóstico de deslizamiento de suelos superficiales”), Boletín de Geología, vol. 39, no. 2, pp. 49-56, 2017. https://doi.org/10.18273/revbol.v39n2-2017003.

Reichenbach, P., Rossi, M., Malamud, B. D., Mihir, M., & Guzzetti, F., “A review of statistically-based landslide susceptibility models”, Earth-Science Reviews, vol. 180, pp. 60-91, 2018. https://doi.org/10.1016/j.earscirev.2018.03.001.

James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112, p. 18). New York: springer. Available on: https://www.statlearning.com.

Feizizadeh, B., Roodposhti, M. S., Blaschke, T., & Aryal, J., “Comparing GIS-based support vector machine kernel functions for landslide susceptibility mapping”. Arabian Journal of Geosciences, vol. 10, no. 5, pp. 1-13, 2017..https://doi.org/10.1007/s12517-017-2918-z.

Yao, X., Tham, L. G., & Dai, F. C. (2008). Landslide susceptibility mapping based on support vector machine: a case study on natural slopes of Hong Kong, China. Geomorphology, vol. 101, no. 4, pp. 572-582. 2008. https://doi.org/10.1016/j.geomorph.2008.02.011.

Pourghasemi, H. R., Jirandeh, A. G., Pradhan, B., Xu, C., & Gokceoglu, C., “Landslide susceptibility mapping using support vector machine and GIS at the Golestan Province, Iran”. Journal of Earth System Science, vol. 122, no.2, pp. 349-369, 2013,https://doi.org/10.1007/s12040-013-0282-2.

Lee, S., Hong, S. M., & Jung, H. S. (2017). A support vector machine for landslide susceptibility mapping in Gangwon Province, Korea. Sustainability, vol. 9, no. 1, pp. 48, 2017. https://doi.org/10.3390/su9010048.

Hong, H., Pradhan, B., Jebur, M. N., Bui, D. T., Xu, C., & Akgun, A., Spatial prediction of landslide hazard at the Luxi area (China) using support vector machines. Environmental Earth Sciences, vol.75, no. 1, pp. 1-14, 2016. https://doi.org/10.1007/s12665-015-4866-9.

Ballabio, C., & Sterlacchini, S., “Support vector machines for landslide susceptibility mapping: the Staffora River Basin case study, Italy”. Mathematical geosciences, vol. 44, no. 1, pp.47-70, 2012. https://doi.org/10.1007/s11004-011-9379-9.

Kumar, D., Thakur, M., Dubey, C. S., & Shukla, D. P., “Landslide susceptibility mapping & prediction using support vector machine for Mandakini River Basin, Garhwal Himalaya, India. Geomorphology”, vol. 295, pp. 115-125, 2017.https://doi.org/10.1016/j.geomorph.2017.06.013.

Althuwaynee, O. F., Pradhan, B., & Lee, S., “Application of an evidential belief function model in landslide susceptibility mapping”. Computers & Geosciences, vol. 44, pp. 120-135, 2012. https://doi.org/10.1016/j.cageo.2012.03.003.

Micheletti, N., Foresti, L., Robert, S., Leuenberger, M., Pedrazzini, A., Jaboyedoff, M., & Kanevski, M., “Machine learning feature selection methods for landslide susceptibility mapping. Mathematical geosciences”, vol.46, no.1, pp. 33-57, 2014. https://doi.org/10.1007/s11004-013-9511-0.

Pradhan, B., “A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS”. Computers & Geosciences, vol.51, pp. 350-365, 2013.https://doi.org/10.1016/j.cageo.2012.08.023.

Tehrani, F. S., Calvello, M., Liu, Z., Zhang, L., & Lacasse, S., “Machine learning and landslide studies: recent advances and applications”. Natural Hazards, vol. 114 ,no. 2, pp. 1197-1245, 2022. https://doi.org/10.1007/s11069-022-05423-7.

DANE (2022), Total GDP by Departments, Sheet:charts 1.Available on: https://www.dane.gov.co/index.php/estadisticas-por-tema/cuentas-nacionales/cuentas-nacionales-departamentales.

District Secretariat of Government Bogotá D.C. (2013). Statement of Reasons for Draft Agreement 279, whereby the District System for Prevention and Emergency Care, SDPAE, is transformed into the District System for Risk Management and Climate Change, SDGR–CC, and its instances are updated. Available on: https://www.alcaldiabogota.gov.co/sisjur/normas/Norma1.jsp?i=55279.

District Planning Secretariat Bogotá D.C. (2017). Monographs of the Localities of the Capital District; Rafael Uribe Uribe. Available on: https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://www.sdp.gov.co/system/tdf/repositorio-dice/dice080-monografiarafaeluribe-2017_vf.pdf%3Ffile%3D1%26type%3Dnode%26id%3D18982%26force%3D1&ved=2ahUKEwiU8_yMzJyFAxUAbzABHXQBDBIQFnoECBEQAQ&usg=AOvVaw2gshXbVrt2y6xcPqHMZYOW.

Acosta Jiménez, Y., & Peña Rincón, C. A., “Physical Vulnerability Index before the Landsliding Hazard in Houses Located in the Locality of Rafael Uribe Uribe, Bogotá DC”. Tecciencia, vol. 14, no. 27, pp. 1-9, 2019. https://doi.org/10.18180/tecciencia.2019.27.1

Hospital “Rafael Uribe Uribe” (HRUU) E:S:E, local diagnosis “Rafael Uribe”. (2012). Available on: http://www.saludcapital.gov.co/DSP/Diagnsticos%20Locales/Locales%20Preliminares/18_Rafael_Uribe.pdf.

QGIS Team. (2009). QGIS Development Team. Geographic Information System Software. Open-source Geospatial Foundation. Available on: http://qgis.org.

ArcGIS, (2018). ArcGIS geoprocessing tool reference. Available on: https://pro.arcgis.com/en/pro-app/latest/tool-reference/main/arcgis-pro-tool-reference.htm.

Montoya, S. (29 November 2013). Saga GIS Tools in QGIS for Hydrological Analysis (“Herramientas de Saga Gis en QGis para análisis hidrológico”). Available on: https://gidahatari.com/ih-es/herramientas-saga-gis-en-qgis-para-analisis-hidrologico.

Gruber, S.; Peckham, S. “Land-surface parameters and objects in hydrology”. Vol. 33, Elsevier, 2009, pp. 171-194.

Conrad, O., Bechtel, B., Bock, M., Dietrich, H., Fischer, E., Gerlitz, L., Wehberg, J., Wichmann, V., and Böhner, J. (2015): System for Automated Geoscientific Analyses (SAGA) v. 2.1.4, Geosci. Model Dev., 8, pp. 1991-2007, Available on: doi:10.5194/gmd-8-1991-2015.

Cortes, C., & Vapnik, V., “Support-vector networks”. Machine learning, vol. 20, no.3, pp. 273-297,1995. https://doi.org/10.1007/BF00994018.

Vapnik, V.N, The Nature of Statistical Learning Theory. Springer, New York.2000, pp. 225-265.

Zaki M, Meira Jr W, Data Mining and Analysis: Fundamental Concepts and Algorithms. Cambridge University Press. 2020, pp. 134-161, pp.517-523.

Hastie, T., Tibshirani, R. and Freidman, J., The Elements of Statistical Learning: Data Mining, Inference and Prediction. Springer-Verlag, New York, 2001, pp. 165-192.

Cristianini N, Shawe-Taylor J, An introduction to support vector machine and other kernel-based learning methods. Cambridge University Press, 2000, pp. 26-51, pp. 93-124.

Rudin, C. (2012).15.097 Prediction: Machine Learning and Statistics, lecture 13. Kernel. https://ocw.mit.edu/courses/15-097-prediction-machine-learning-and-statistics-spring-2012/resources/mit15_097s12_lec13/.

Hsu Chih-Wei, Chih-Chung Chang, and Chih-Jen Lin.(2003), A practical guide to support vector classification. Technical report, Department of Computer Science, National Taiwan University. Available on: http://www.datascienceassn.org/sites/default/files/Practical%20Guide%20to%20Support%20Vector%20Classification.pdf.

Abraham, M. T., Satyam, N., Jain, P, Pradhan, B., & Alamri, A. (2021). Effect of spatial resolution and data splitting on landslide susceptibility mapping using different machine learning algorithms. Geomatics, Natural Hazards and Risk, 12(1), 3381-3408. https://doi.org/10.1080/19475705.2021.2011791.

Aristizábal, E., Morales-García, P., Vásquez-Guarín, M., Ruíz-Vásquez, D., Palacio-Córdoba, J., Ángel-Cárdenas, F. P. & Ordóñez-Carmona, O., Methodologies for the evaluation of landslide hazard as part of the basic hazard studies: case study municipality of Andes, Antioquia, Colombia. (“Metodologías para la evaluación de la amenaza por movimientos en masa como parte de los estudios básico de amenaza: caso de estudio municipio de Andes, Antioquia, Colombia”), Boletín de Geología, vol. 44, no.3, pp. 199-217, 2022. https://doi.org/10.18273/revbol.v44n3-2022009.

Refaeilzadeh P., Tang L., Liu H. (2009) Cross-Validation. In: LIU L., ÖZSU M.T. (eds) Encyclopedia of Database Systems. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-39940-9_565.

Shahabi, H., & Hashim, M.,” Landslide susceptibility mapping using GIS-based statistical models and Remote sensing data in tropical environment”. Scientific reports, vol. 5, no. 1, pp. 1-15, 2015. https://doi.org/10.1038/srep09899.

Huang, Y., & Zhao, L., “Review on landslide susceptibility mapping using support vector machines”. Catena, vol. 165, pp. 520-529, 2018. https://doi.org/10.1016/j.catena.2018.03.003.

Pham, B.T., Tien Bui, D., Prakash, I., Nguyen, L.H., Dholakia, M.B., “A comparative study of sequential minimal optimization-based support vector machines, vote feature intervals, and logistic regression in landslide susceptibility assessment using GIS”. Environ. Earth Sci. vol. 76, no. 10, pp. 1-15, 2017. https://doi.org/10.1007/s12665-017-6689-3.

Dikshit, A., Sarkar, R., Pradhan, B., Acharya, S., & Alamri, A. M.,”Spatial landslide risk assessment at Phuentsholing, Bhutan”. Geosciences, vol.10, no. 4, pp. 131, 2020. https://doi.org/10.3390/geosciences10040131.

Merghadi, A., Yunus, A. P., Dou, J., Whiteley, J., ThaiPham, B., Bui, D. T., ... & Abderrahmane, B., “Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance”. Earth-Science Reviews, vol. 207, pp. 103225, 2020. https://doi.org/10.1016/j.earscirev.2020.103225.

Zhu, A. X., Miao, Y., Liu, J., Bai, S., Zeng, C., Ma, T., & Hong, H., “A similarity-based approach to sampling absence data for landslide susceptibility mapping using data-driven methods”. Catena, vol. 183, pp. 104188, 2019. https://doi.org/10.1016/j.catena.2019.104188.