Methods for the construction of DEMs of artificial slopes considering morphological features and semantic information

As human activities increase,artificially modified terrain is increasingly widely distributed in road,hydrological,and urban construction.Artificially modified terrain plays an important role in protecting from geological disasters and in the planning and design of urban landscapes.Compared with natural slopes,artificial slopes have obvious morphological characteristics.Traditional modeling methods are no longer suitable for digital elevation model(DEM)modeling of artificial slopes because they often seriously distort the DEM results.In this paper,from the perspective of morphological characteristics,artificial slopes are divided into two types,namely,regular slopes and irregular slopes,based on whether the top and bottom lines of the artificial slope are parallel.Then,according to the morphological characteristics of the two types of slopes,the following DEM construction methods are designed:the first method(perpendicular+inverse distance weighted)is suitable for regular slopes,and the second method(perpendicular+high-accuracy surface modeling)is suitable for irregular slopes.Finally,a DEM construction test is carried out using the artificial slopes in the study area.The results show that for the regular and irregular slopes in the study area,the construction method proposed in this paper has significant advantages in morphological accuracy over the traditional method(triangulated irregular network),and the elevation accuracy method is also superior to the traditional method(using this method,the mean error and standard deviation error of the regular slope DEM are 0.08 m and 0.13 m,respectively,and those of the irregular slope DEM are 0.08 m and 0.06 m).In addition,the top lines and bottom lines can be included in the DEM construction of the background area after processing the elevation information of the boundary line to realize a smooth transition in the boundary between the artificial slope and the background area.

An Artificial Neural Network-Based Response Surface Method for Reliability Analyses of c-φ Slopes with Spatially Variable Soil

This paper presents an artificial neural network（ANN）-based response surface method that can be used to predict the failure probability of c-φslopes with spatially variable soil.In this method,the Latin hypercube sampling technique is adopted to generate input datasets for establishing an ANN model;the random finite element method is then utilized to calculate the corresponding output datasets considering the spatial variability of soil properties;and finally,an ANN model is trained to construct the response surface of failure probability and obtain an approximate function that incorporates the relevant variables.The results of the illustrated example indicate that the proposed method provides credible and accurate estimations of failure probability.As a result,the obtained approximate function can be used as an alternative to the specific analysis process in c-φslope reliability analyses.