RESUMEN
Shallow landslides damage buildings and other infrastructure, disrupt agriculture practices, and can cause social upheaval and loss of life. As a result, many scientists study the phenomenon, and some of them have focused on producing landslide susceptibility maps that can be used by land-use managers to reduce injury and damage. This paper contributes to this effort by comparing the power and effectiveness of five machine learning, benchmark algorithms-Logistic Model Tree, Logistic Regression, Naïve Bayes Tree, Artificial Neural Network, and Support Vector Machine-in creating a reliable shallow landslide susceptibility map for Bijar City in Kurdistan province, Iran. Twenty conditioning factors were applied to 111 shallow landslides and tested using the One-R attribute evaluation (ORAE) technique for modeling and validation processes. The performance of the models was assessed by statistical-based indexes including sensitivity, specificity, accuracy, mean absolute error (MAE), root mean square error (RMSE), and area under the receiver operatic characteristic curve (AUC). Results indicate that all the five machine learning models performed well for shallow landslide susceptibility assessment, but the Logistic Model Tree model (AUC = 0.932) had the highest goodness-of-fit and prediction accuracy, followed by the Logistic Regression (AUC = 0.932), Naïve Bayes Tree (AUC = 0.864), ANN (AUC = 0.860), and Support Vector Machine (AUC = 0.834) models. Therefore, we recommend the use of the Logistic Model Tree model in shallow landslide mapping programs in semi-arid regions to help decision makers, planners, land-use managers, and government agencies mitigate the hazard and risk.
Asunto(s)
Algoritmos , Teorema de Bayes , Deslizamientos de Tierra , Modelos Logísticos , Redes Neurales de la Computación , Máquina de Vectores de Soporte , IránRESUMEN
This study is devoted to the modeling and simulation of uncertainties in the constitutive elastic properties of material constituting a circular column under axial compression. To this aim, a probabilistic model dedicated to the construction of positive-definite random elasticity matrices was first used, involving two stochastic parameters: the mean value and a dispersion parameter. In order to compute the nonlinear effects between load and lateral deflection for the buckling problem of the column, a finite element framework combining a Newton-Raphson solver was developed. The finite element tool was validated by comparing the as-obtained critical buckling loads with those from Euler's formula at zero-fluctuation of the elasticity matrix. Three levels of fluctuations of material uncertainties were then propagated through the validated finite element tool using the probabilistic method as a stochastic solver. Results showed that uncertain material properties considerably influenced the buckling behavior of columns under axial loading. The coefficient of variation of a critical buckling load over 500 realizations were 15.477%, 26.713% and 41.555% when applying dispersion parameters of 0.3, 0.5 and 0.7, respectively. The 95% confidence intervals of column buckling response were finally given. The methodology of modeling presented in this paper is a potential candidate for accounting material uncertainties with some instabilities of structural elements under compression.
RESUMEN
The main objective of this research was to introduce a novel machine learning algorithm of alternating decision tree (ADTree) based on the multiboost (MB), bagging (BA), rotation forest (RF) and random subspace (RS) ensemble algorithms under two scenarios of different sample sizes and raster resolutions for spatial prediction of shallow landslides around Bijar City, Kurdistan Province, Iran. The evaluation of modeling process was checked by some statistical measures and area under the receiver operating characteristic curve (AUROC). Results show that, for combination of sample sizes of 60%/40% and 70%/30% with a raster resolution of 10 m, the RS model, while, for 80%/20% and 90%/10% with a raster resolution of 20 m, the MB model obtained a high goodness-of-fit and prediction accuracy. The RS-ADTree and MB-ADTree ensemble models outperformed the ADTree model in two scenarios. Overall, MB-ADTree in sample size of 80%/20% with a resolution of 20 m (area under the curve (AUC) = 0.942) and sample size of 60%/40% with a resolution of 10 m (AUC = 0.845) had the highest and lowest prediction accuracy, respectively. The findings confirm that the newly proposed models are very promising alternative tools to assist planners and decision makers in the task of managing landslide prone areas.