Publicación: Zonificación de la susceptibilidad relativa a movimientos en masa de la plancha 136-ii-c, escala 1:25.000, aplicando redes neuronales artificiales
| dc.contributor.advisor | Camargo Daza, Jorge Leonardo | |
| dc.contributor.advisor | Valencia Ortiz, Joaquín Andrés | |
| dc.contributor.author | Rivera Rivera, Jhonatan Steven | |
| dc.contributor.author | Jacome Julio, Diego Fernando | |
| dc.date.accessioned | 2024-03-03T22:43:54Z | |
| dc.date.available | 2016 | |
| dc.date.available | 2024-03-03T22:43:54Z | |
| dc.date.created | 2016 | |
| dc.date.issued | 2016 | |
| dc.description.abstract | La estimación de la susceptibilidad se basa en la correlación de los principales factores causantes (intrínsecos) que contribuyen a la formación de movimientos en masa; un método eficiente y exacto para generar dicha correlación son las Redes Neuronales Artificiales (RNA). En este trabajo de investigación fueron evaluados once factores causantes (geología, densidad de fracturamiento, unidades geológicas superficiales, morfogenética, morfodinámica, acuenca, curvatura, pendientes, rugosidad, cobertura de la tierra y suelos); con el objetivo de realizar la zonificación, a escala 1:25.000, de la susceptibilidad relativa a los movimientos en masa de la plancha 136-II-C, mediante el algoritmo de entrenamiento Back-Propagation de Redes Neuronales Artificiales. La arquitectura 11-18-1 entrenada con el algoritmo Variable Learning Rate Gradient Descent (GDX), arrojó un buen rendimiento con ACC = 0,8817 y ROC = 0,9841. El análisis de la importancia relativa de las entradas de la red, aplicando el métod indicó que los factores causantes de rugosidad (MSE=0,1874) y morfodinámica (MSE=0,1891) son los más influyentes en la ocurrencia de movimientos en masa. Finalmente el mapa de susceptibilidad a los movimientos en masa de la plancha 136-II-C indicó que las zonas de susceptibilidad muy alta son las más | |
| dc.description.abstractenglish | Relative susceptibility zoning to landslide of plate 136-ii-c, at 125.000 scale, implemented by artificial neural networks. a case astudy from carcasi and enciso, santander | |
| dc.description.degreelevel | Pregrado | |
| dc.description.degreename | Geólogo | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.instname | Universidad Industrial de Santander | |
| dc.identifier.reponame | Universidad Industrial de Santander | |
| dc.identifier.repourl | https://noesis.uis.edu.co | |
| dc.identifier.uri | https://noesis.uis.edu.co/handle/20.500.14071/35015 | |
| dc.language.iso | spa | |
| dc.publisher | Universidad Industrial de Santander | |
| dc.publisher.faculty | Facultad de Ingenierías Fisicoquímicas | |
| dc.publisher.program | Geología | |
| dc.publisher.school | Escuela de Geología | |
| dc.rights | http://creativecommons.org/licenses/by/4.0/ | |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | |
| dc.rights.creativecommons | Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0) | |
| dc.rights.license | Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) | |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc/4.0 | |
| dc.subject | Zonificación | |
| dc.subject | Susceptibilidad | |
| dc.subject | Geomorfología | |
| dc.subject | Movimientos En Masa | |
| dc.subject | Redes Neuronales Artificiales | |
| dc.subject | Backpropagation | |
| dc.subject | Plancha 136-Ii-C | |
| dc.subject | Carcasí. | |
| dc.subject.keyword | The estimation of susceptibility is based on the correlation of the main causing factors contributing to the formation of mass movements; an efficient and accurate method | |
| dc.subject.keyword | in order to stablish such correlation | |
| dc.subject.keyword | is the Artificial Neural Networks (ANN). In this research were evaluated eleven causing factors (geology | |
| dc.subject.keyword | density of fracturing | |
| dc.subject.keyword | surface geological units | |
| dc.subject.keyword | morphogenetic | |
| dc.subject.keyword | morphodynamics | |
| dc.subject.keyword | mining area | |
| dc.subject.keyword | bend | |
| dc.subject.keyword | slope | |
| dc.subject.keyword | roughness | |
| dc.subject.keyword | land cover and soil); with the aim of zoning the mass movements susceptibility | |
| dc.subject.keyword | of a 1:25.000 layer (136-II-C) | |
| dc.subject.keyword | using Back-Propagation-Artificial Neural Networks training algorithm. The model 11-18-1 architecture | |
| dc.subject.keyword | which was ran with the Variable Learning Rate Gradient Descent (GDX) algorithm | |
| dc.subject.keyword | showed a good performance | |
| dc.subject.keyword | with ACC = 0.8817 and ROC = 0. 841. The relative importance analysis of ANN inputs | |
| dc.subject.keyword | using stepwise method | |
| dc.subject.keyword | indicated that roughness (MSE=0.1874) and morphodynamics (0.1891) are the most influential causing factors when mass movements happened. Finally | |
| dc.subject.keyword | the susceptibility map | |
| dc.subject.keyword | which showed this movements of the plate 136-II-C | |
| dc.subject.keyword | indicated that the highest susceptibility zones are the most frequent ones (41.53%) | |
| dc.subject.keyword | followed in descending order by: high susceptibility areas (18.3%) | |
| dc.subject.keyword | low susceptibility areas (14.67%) | |
| dc.subject.keyword | moderate susceptibility areas (13.53%) and very low susceptibility areas (11.96%); consequently it is important and necessary to perform threat and risk studies | |
| dc.subject.keyword | that allow to settle zones where is necessary to intervene in order to prevent and mitigate damage caused by such natural disaster | |
| dc.title | Zonificación de la susceptibilidad relativa a movimientos en masa de la plancha 136-ii-c, escala 1:25.000, aplicando redes neuronales artificiales | |
| dc.title.english | Zoning, Susceptibility, Geomorphology, Mass Movements, Artificial Neural Network, Backpropagation, Plate 136-Ii-C, Carcasí. | |
| dc.type.coar | http://purl.org/coar/version/c_b1a7d7d4d402bcce | |
| dc.type.hasversion | http://purl.org/coar/resource_type/c_7a1f | |
| dc.type.local | Tesis/Trabajo de grado - Monografía - Pregrado | |
| dspace.entity.type | Publication |
Archivos
Bloque original
1 - 3 de 3
Cargando...
- Nombre:
- Carta de autorización.pdf
- Tamaño:
- 232.01 KB
- Formato:
- Adobe Portable Document Format
Cargando...
- Nombre:
- Documento.pdf
- Tamaño:
- 17.54 MB
- Formato:
- Adobe Portable Document Format
Cargando...
- Nombre:
- Nota de proyecto.pdf
- Tamaño:
- 191.39 KB
- Formato:
- Adobe Portable Document Format
