A comparative study of random forests and multiple linear regression in the prediction of landslide velocity
- PDF / 12,445,497 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 72 Downloads / 215 Views
Martin Krkač I Sanja Bernat Gazibara I Željko Arbanas I Marin Sečanj I Snježana Mihalić Arbanas
A comparative study of random forests and multiple linear regression in the prediction of landslide velocity
Abstract The monitoring of landslides has a practical application for the prevention of hazards, especially in the case of large deepseated landslides. Monitoring data are necessary to understand the relationships between movement and triggers, to predict movement, and to establish an early warning system. This paper compares two phenomenological models for the prediction of the movement of the Kostanjek landslide, the largest landslide in the Republic of Croatia. The prediction models are based on a 4-year monitoring data series of landslide movement, groundwater level, and precipitation. The presented models for landslide movement prediction are divided into the model for the prediction of groundwater level from precipitation data and the model for the prediction of landslide velocity from groundwater level data. The statistical techniques used for prediction are multiple linear regression and random forests. For the prediction of groundwater level, 75 variables calculated from precipitation and evapotranspiration data were used, while for the prediction of landslide movement, 10 variables calculated from groundwater level data were used. The prediction results were mutually compared by k-fold cross-validation. The root mean square error analyses of k-fold cross-validation showed that the results obtained from random forests are just slightly better than those from multiple linear regression, in both, the groundwater level and the landslide velocity models, proofing that multiple linear regression has a potential for prediction of landslide movement. Keywords Landslide monitoring . Groundwater level prediction . Landslide movement prediction . Random forests . Multiple linear regression Introduction The most common trigger of landslide movement is rainfall (Mansour et al. 2011; Berti et al. 2012). Rain that reaches the ground surface infiltrates into the ground and influences the groundwater. The groundwater response to rainfall is complicated and depends on various factors, such as specific yield, hydraulic properties, soil moisture, evapotranspiration, antecedent water table levels, land cover or land use, natural or created drainage features (Gaalen et al. 2013), and rainfall intensity (Jan et al. 2007, Cai and Ofterdinger 2016). If the amount of groundwater recharge is greater than the amount of discharge, the groundwater level will rise. During this process, the pressure of the water that fills the void spaces between the soil particles and rock fissures rises, resulting in a decrease in the effective stress within a slope. The reduction in effective stresses due to change in the groundwater level, affecting the soil strength and consequently the stability of the slope, causes first-time failures, as well as the reactivation of landside movement. However, the relationship between landslide movements and po
Data Loading...
