Combining neural networks andgeostatistics for landslide hazardassessment of San Salvador metropolitan area, El Salvador

Ríos, Ricardo; Ribó, Alexandre; Mejía, Roberto; Molina, Giovanni; Ríos, Ricardo; Ribó, Alexandre; Mejía, Roberto; Molina, Giovanni

Services on Demand

Journal

Article

Indicators

Cited by SciELO
Access statistics

Revista de Matemática Teoría y Aplicaciones

Print version ISSN 1409-2433

Rev. Mat vol.23 n.1 San José Jan./Jun. 2016

Artículos

Combining neural networks andgeostatistics for landslide hazardassessment of San Salvador metropolitan area, El Salvador

Combinando redes neuronales ygeoestadística para evaluación dedeslizamientos de tierra del áreametropolitana de San Salvador, El Salvador

Ricardo Ríos¹

Alexandre Ribó²

Roberto Mejía³

Giovanni Molina⁴

^¹Department of Mathematics, Science and Mathematics Faculty, University of El Salvador, ElSalvador. E-Mail: ricardo.sv@gmail.com

^²National Institute of Health, Ministry of Health of El Salvador, El Salvador.E-Mail:alexandre4rt@gmail.com

^³Department of Mathematics, Science and Mathematics Faculty, University of El Salvador, ElSalvador. E-Mail: robertomejia1685@gmail.com

^⁴Ministry of Environment and Natural Resources of El Salvador, El Salvador. E-Mail: giova.molina@gmail.com

Abstract

This contribution describes the creation of a landslide hazard assessment model for San Salvador, a department in El Salvador. The analysis started with an aerial photointerpretation from Ministry of Environment and Natural Resources of El Salvador (MARN Spanish acronym), where 4792 landslides were identified and georeferenced along with 7 conditioning factors including: geomorphology, geology, rainfall intensity, peak ground acceleration, slope angle, distance to road, and distance to geological fault. Artificial Neural Networks (ANN) were utilized to assess the susceptibility to landslides, achieving results where more than 80% of landslide were properly classified using in-sample and out of sample criteria. Logistic regression was used as base of comparison. Logistic regression obtained a lower performance. To complete the analysis we have performed interpolation of the points using the kriging method from geostatistical approach. Finally, the results show that is possible to derive a landslide hazard map, making use of a combination of ANNs and geostatistical techniques, thus the present study can help landslide mitigation in El Salvador.

Keywords: landslide; hazard assessment; El Salvador; ANN; geostatistics; artificial neural networks; kriging

Resumen

Esta contribución describe la creación de un modelo de evaluación de deslizamiento de tierra para el Área Metropolitana de San Salvador, departamento de El Salvador. El análisis inició con la obtención de una foto aérea del Ministerio de Medio Ambiente y Recursos Naturales (MARN) en donde 4792 deslizamientos fueron identificados y georeferrenciados junto con 7 factores condicionantes incluyendo: geomorfología, geología, precipitaciones máximas, aceleraciones sísmicas, pendiente del terreno, distancia a carretera y falla geológica. Redes Neuronales Artificiales (RNA) fueron utilizadas para la evaluación de la susceptibilidad a deslizamiento de tierra, logrando que más del 80% de deslizamientos fueran apropiadamente clasificados usando un criterio dentro y fuera de la muestra con la que se estimaron los parámetros del modelo. Regresión Logística fue usada como base de comparación, obteniendo este modelo un rendimiento inferior. Para completar el análisis se realizó la interpolación de puntos usando el método kriging proveniente del enfoque geoestadístico. Finalmente, los resultados muestran que es posible obtener un mapa de riesgo a deslizamiento de tierra, haciendo uso de una combinación de RNA y técnicas geoestadísticas con lo cual la presente investigación puede ayudar a la mitigación de deslizamientos de tierra en El Salvador.

Palabras clave: deslizamiento de tierra; evaluación de riesgo; El Salvador; RNA; geoestadística

Ver contenido en pdf.

Acknowledgment

The authors are indebted with MARN for providing the data and Geographic Information System software such as ILWIS and ArcGISR of ESRI.

REFERENCES

Akgun, A.(2012) "A comparison of landslide susceptibility maps produced by logistic regression, multi criteria decision, and likelihood ratio methods: a case study at Izmir, Turkey", Landslides 9(1): 93-106. [ Links ]

Aki, K.(1993) "Local site effects on weak and strong ground motion", in: F.Lund(Ed.) New Horizons in Strong Motion: Seismic Studies and Engineering Practice, Tectonophysics 218(1): 93-111. [ Links ]

Ballabio, C.; Sterlacchini, S.(2012) "Support vector machines for landslide susceptibility mapping: the Staffora river basin case study, Italy", Mathematical Geosciences 44(1): 47-70. [ Links ]

Benito, M.B.; Lindholm, C.; Camacho, E.; Climent, Á.; Marroquín, G.; Molina, E.; Rojas, W.; Escobar, J.J.; Talavera, E.; Alvarado, G.E.; Torres, Y.(2012) "A new evaluation of seismic hazard for the Central America region", Bulletin of the Seismological Society of America102(2): 504-523. [ Links ]

Bivand, R.S.; Pebesma, E.J.; Gomez-Rubio, V.; Pebesma, E.J.(2008) Applied Spatial Data Analysis with R. Springer, New York. [ Links ]

Bommer, J.J.; Rodriguez, C.E. (2002) "Earthquake-induced landslides in Central America", Engineering Geology 63(3): 189-220. [ Links ]

Campbell, R.H.; Brookshire, D.S.; Bernknopf, R.L.; Shapiro, C.D. (1988) "A probabilistic approach to landslide hazard mapping in Cincinnati, Ohio, with application for economic evaluation", Bulletin of the Association of Engineering Geologists25(1): 39-56. [ Links ]

Capparelli, G.; Versace, P.P. (2013) "Landslide susceptibility from mathematical model in Sarno area", Hydrology and Earth System Sciences Discussions10(10): 12643-12662. [ Links ]

Carrara, A.(1983) "Multivariate models for landslide hazard evaluation", Journal of the International Association for Mathematical Geology15(3): 403-426. [ Links ]

Chávez, J.A.; Landaverde,J.M.; Ayala,O.E.; Mendoza,L.E.(2014) "Application of constitutive models in the volcanic tephra "Tierra Blanca Joven", Ingeniería 24(2): 53-78. [ Links ]

Chávez, J.A.; Sebesta, J.; Kopecky, L.; López, R.(2014) "Application of geomorphologic knowledge for erosion hazard mapping", Natural Hazards71(3): 1323-1354. [ Links ]

Christou, N.(2013) "Ordinary kriging in terms of the covariance function", in: (2013) "Ordinary kriging in terms of the covariance function", in: http://goo.gl/0J1RkO , consulted 23-Jun-2013, 5:30 p.m. [ Links ]

Chung, C.J.F.; Fabbri, A. G.(2003). "Validation of spatial prediction models for landslide hazard mapping", Natural Hazards30(3): 451-472. [ Links ]

Crone, A.J.; Baum, R.L.; Lidke, D.J.; Sather, D.N.D.; Bradley, L.A.; Tarr, A.C.(2002) "LandslidesInduced by Hurricane Mitch in El Salvador-An Inventory and Description of Selected Features", Preprint, USGS Open File Report 01-444, available in http://pdf.usaid.gov/pdf_docs/Pnacr105.pdf [ Links ]

Crosta, G. B.; Imposimato, S.; Roddeman, D.; Chiesa, S.; Moia, F.(2005) "Small fast-moving flow-like landslides in volcanic deposits: the 2001 Las Colinas Landslide (El Salvador)", Engineering geology79(3): 185-214. [ Links ]

Dewey, J.W.; White, R.A.; Hernández, D.A.(2004) "Seismicity and tectonics of El Salvador", Geological Society of America Special Papers375: 367-378. [ Links ]

Dull, R.A.(2004) "Lessons from the mud, lessons from the Maya: Paleoecological records of the Tierra Blanca Joven eruption", Geological Society of America Special Papers375: 237-244. [ Links ]

Ermini, L.; Catani, F.; Casagli, N.(2005) "Artificial neural networks applied to landslide susceptibility assessment", Geomorphology 66(1): 327- 343. [ Links ]

Evans, S.G.; Bent, A.L.(2004) "Las Colinas landslide, Santa Tecla: A higly destructive flowslide triggered by January 13, 2001, El Salvador earthquake", Geological Society of America Special Papers375: 25-37. [ Links ]

Fernández-Lavado, C.; Sánchez, A.; Amenós, M.; Barrio, J. (2008) "Caracterización de la susceptibilidad y de la amenaza por movimientos de ladera del Área Metropolitana de San Salvador (AMSS). Scale 1: 75000 (1 Sheet)", Preprint, Project IPGARAMSS framework. Geólogos del Mundo. San Salvador, El Salvador. [ Links ]

García-Rodríguez, M.J.; Malpica, J.A.; Benito, B.; Díaz, M.(2008) "Susceptibility assessment of earthquake-triggered landslides in El Salvador using logistic regression", Geomorphology 95(3): 172-191. [ Links ]

García-Rodríguez, M.J.; Malpica, J.A.(2010) "Assessment of earthquaketriggered landslide susceptibility in El Salvador based on an Artificial Neural Network model", Natural Hazards and Earth System Science10(6): 1307-1315. [ Links ]

Gaskill, J.; Zuber, B.; Nordman, E.(2015) "Analyzing landslide susceptibility in St. Vincent and the Grenadines using co-kriging and logistic regression", Preprint, The 2015 IMAGIN Award, Michigan United States. Presentation available in: http://www.imagin.org/awards/sppc/2015/papers/jacob_gaskill_presentation.pdf [ Links ]

Hernández, W.E. (2004) Características Geomecánicas y Vulcanologicas de las Tefras Tierra Blanca Joven, Caldera de Ilopango, El Salvador. M.Sc. Thesis, Universidad Politécnica de Madrid-Universidad Politécnica de El Salvador. [ Links ]

Jibson, R.W.; Crone, A.J.; Harp, E.L.; Baum, R.L.; Major, J.J.; Pullinguer, C.R.; Escobar, D.; Martinez, M: Smith, M.E.(2004) "Landslidestriggered by the 13 January and 13 February 2001, earthquakes", Geological Society of America Special Papers375: 69-88. [ Links ]

Lee, S.; Choi, J.: Min, K.(2004) "Probabilistic landslide hazard mapping using GIS and remote sensing data at Boun, Korea", International Journal of Remote Sensing 25(11): 2037-2052. [ Links ]

Major, J.J.; Chilling, S.P.; Pullinguer, C.R.; Escobar, C.D.(2004) "Debrisflow hazards at San Salvador, San Vicente, and San Miguel volcanoes, El Salvador", Geological Society of America Special Papers375: 89-108. [ Links ]

McNelis, P.D. (2005) Estimation of a Network with Evolutionary Computation. Academic Press, New York. [ Links ]

Melchiorre, C.; Abella, E. C.; van Westen, C. J.; Matteucci, M. (2011) "Evaluation of prediction capability, robustness, and sensitivity in nonlinear landslide susceptibility models, Guantánamo, Cuba", Computers & Geosciences37(4): 410-425. [ Links ]

Ministerio de Economía-Dirección General de Estadística y Censos (2013) "VI Censo de Población y V de Vivienda", El Salvador, in: Ministerio de Economía-Dirección General de Estadística y Censos (2013) "VI Censo de Población y V de Vivienda", El Salvador, in: http:// goo.gl/yvjzPy , consulted 23-Dec-2013, 2:30 p.m. [ Links ]

Neuhäuser, B.; Damm, B.; Terhorst, B.(2012) "GIS-based assessment of landslide susceptibility on the base of the weights-of-evidence model", Landslides 9(4): 511-528. [ Links ]

Pradhan, B.; Oh, H.; Buchroithner, M.(2010) "Weights-of-evidence model applied to landslide susceptibility mapping in a tropical hilly area", Geomatics, Natural Hazards and Risk1(3): 199-223. [ Links ]

R Core Team. (2014) R: A Language and Environment for Statistical Computing. Vienna: R Foundation for Statistical Computing. [ Links ]

Rolo, R.; Bommer, J.J.; Houghton, B.F.; Vallance, J.W.; Berdousis, P.; Mavrommati, C.; Morphy, W.(2004) "Geologic and engineering characterization of Tierra Blanca pyroclastic ash deposits", Geological Society of America Special Papers375: 55-68. [ Links ]

Rymer, M.J.(1987) "The San Salvador earthquake of October 10, 1986geologic aspects", Earthquake Spectra3(3): 435-463. [ Links ]

Schmidt-Thomé,M.(1975) "The geology in the San Salvador area (El Salvador, Central America), a basis for city development and planning", Geologisches Jahrbuch13: 207-228. [ Links ]

SNET-MARN, Servicio Nacional de Estudios Territoriales-Ministerio de Ambiente y Recursos Naturales (2013) "Memoria técnica para el mapa de susceptibilidad de deslizamientos de tierra en El Salvador", in: SNET-MARN, Servicio Nacional de Estudios Territoriales-Ministerio de Ambiente y Recursos Naturales (2013) "Memoria técnica para el mapa de susceptibilidad de deslizamientos de tierra en El Salvador", in: http://www.snet.gob.sv/ver/geologia/susceptibilidad+actual/ , consulted 12-Sep-2013, 2:30 p.m. [ Links ]

Sofield, D. (2004) "Eruptive history and volcanic hazards of Volcan San Salvador", Geological Society of America Special Papers 375: 147-158. [ Links ]

Tien Bui, D.; Pradhan, B.; Lofman, O.; Revhaug, I.(2012) "Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and naive Bayes models", Mathematical Problems in Engineering2012, 26 pp. Available in: http://www.hindawi.com/journals/ mpe/2012/974638/ [ Links ]

Van Westen, C.J.; Van Asch, T.W.; Soeters, R.(2006) "Landslide hazard and risk zonation why is it still so difficult?", Bulletin of Engineering Geologyand the Environment65(2): 167-184. [ Links ]

Warren, S.(2002) "Neural network FAQ", in: (2002) "Neural network FAQ", in: ftp://ftp.sas.com/pub/neural/FAQ.html , consulted 10-Jan-2014, 10:30 a.m. [ Links ]

Weber, H.S.; Wiesemann, G.; Lorenz, W.; Schmidt-Thomé, M.(1978) "Mapa geológico de la República de El Salvador", Preprint, Bundesanstalt für Geowissenschaften und Rohstoffe, Hannover, Germany. [ Links ]

Yesilnacar, E.; Topal, T. (2005) "Landslide susceptibility mapping: A comparison of logistic regression and neural networks methods in a mediumscale study, Hendek region (Turkey)", Engineering Geology 79(3): 251- 266. [ Links ]

Zeng-Wang, X.U.(2001) "GIS and ANN model for landslide susceptibility mapping", Journal of Geographical Sciences11(3): 374-381. [ Links ]

Received: February 19, 2014; Revised: August 28, 2015; Accepted: September 29, 2015

This is an open-access article distributed under the terms of the Creative Commons Attribution License