Authors :
Divya P, Geetha D S, Sivagami H, Sivagami S.
Volume/Issue :
Volume 3 - 2018, Issue 3 - March
Google Scholar :
https://goo.gl/DF9R4u
Scribd :
https://goo.gl/GgPofy
Thomson Reuters ResearcherID :
https://goo.gl/3bkzwv
Abstract :
Landslides are more prone in high altitude regions and determining them is challenging due to their unforeseen and sudden occurrence. As the technology is,improving day by day, the landslides are determined based on their spatial extent and the socio-economic losses can thereby be reduced. Many factors such as altitude, rainfall level, ground water level, reservoir water level, latitude, longitude, etc. ascertain their occurrence. One of the supervised Machine learning approaches called the Support Vector Machine (SVM) isused to predict whether there is a high probability of landslide occurrence in the given region. Time Series Analysis is used to find the direction and periodic propagation of landslides and the total amount of their deformation. Furthermore, Genetic Algorithm (GA) is for the further optimization and to reduce the mean square error of landslide susceptibility mapping. The prediction and validation results reveal that the proposed model can help in land use planning for shrinking the losses.
Keywords :
Landslides; Support Vector Machine (SVM); Genetic algorithm (GA); prediction; trend component; periodic component.
Landslides are more prone in high altitude regions and determining them is challenging due to their unforeseen and sudden occurrence. As the technology is,improving day by day, the landslides are determined based on their spatial extent and the socio-economic losses can thereby be reduced. Many factors such as altitude, rainfall level, ground water level, reservoir water level, latitude, longitude, etc. ascertain their occurrence. One of the supervised Machine learning approaches called the Support Vector Machine (SVM) isused to predict whether there is a high probability of landslide occurrence in the given region. Time Series Analysis is used to find the direction and periodic propagation of landslides and the total amount of their deformation. Furthermore, Genetic Algorithm (GA) is for the further optimization and to reduce the mean square error of landslide susceptibility mapping. The prediction and validation results reveal that the proposed model can help in land use planning for shrinking the losses.
Keywords :
Landslides; Support Vector Machine (SVM); Genetic algorithm (GA); prediction; trend component; periodic component.
