Slope reliability analysis using Bayesian optimized convolutional neural networks

Abstract

PurposeThis paper aims to develop an effective framework which combines Bayesian optimized convolutional neural networks (BOCNN) with Monte Carlo simulation for slope reliability analysis.Design/methodology/approachThe Bayesian optimization technique is firstly used to find the optimal structure of CNN based on the empirical CNN model established in a trial and error manner. The proposed methodology is illustrated through a two-layered soil slope and a cohesive slope with spatially variable soils at different scales of fluctuation.FindingsThe size of training data suite, T, has a significant influence on the performance of trained CNN. In general, a trained CNN with larger T tends to have higher coefficient of determination (R2) and smaller root mean square error (RMSE). The artificial neural networks (ANN) and response surface method (RSM) can provide comparable results to CNN models for the slope reliability where only two random variables are involved whereas a significant discrepancy between the slope failure probability (Pf) by RSM and that predicted by CNN has been observed for slope with spatially variable soils. The RSM cannot fully capture the complicated relationship between the factor of safety (FS) and spatially variable soils in an effective and efficient manner. The trained CNN at a smaller the scale of fluctuation (λ) exhibits a fairly good performance in predicting the Pf for spatially variable soils at higher λ with a maximum percentage error not more than 10%. The BOCNN has a larger R2 and a smaller RMSE than empirical CNN and it can provide results fairly equivalent to a direct Monte Carlo Simulation and therefore serves a promising tool for slope reliability analysis within spatially variable soils.Practical implicationsA geotechnical engineer could use the proposed method to perform slope reliability analysis.Originality/valueSlope reliability can be efficiently and accurately analyzed by the proposed framework.

Stability evaluation of open-pit mine slope based on Bayesian optimization 1D-CNN

“…To assess the developed model even further, an experiment is set up in 3.3 that also compares its performance with the four fundamental neural network computational methods developed by the authors of previous research [50][51][52] . This is done using the same dataset on the Bayesian optimization of the optimized 1D-CNN model, the 1D-CNN model optimized by the Genetic Algorithm, the optimized 1D-CNN model, the standard 1D-CNN model, and the BP neural network model on the test set to determine the accuracy.…”

“…The following is the procedure for feeding the dataset into the CNN model and utilizing a Bayesian optimizer to optimize the hyperparameters: What 1D-CNN hyperparameters need to be optimized is listed in Table 5: The hyperparameters that will be automatically changed during the Bayesian optimization process to optimize the CNN model's performance are the number of convolutional kernels (Filters), convolutional kernel size (Kernelsize), maximum pooling-window size (Pooling-size), number of neurons in the fully-connected layer (Units), batch size (Batch-size), and number of training repetitions (Epochs).Based on the findings of earlier studies, each hyperparameter's search range is determined. The prior distributions of the hyperparameters were selected www.nature.com/scientificreports/ based on statistical prior knowledge to guarantee that the search space included all hypothetical possibilities and was hence comprehensive,the range of every hyperparameter was subsequently determined by numerous iterative trials and errors 50,51 .…”

A Soybean Classification Method Based on Data Balance and Deep Learning

“…Laura Gómez-Zamanillo and others put forward a damage-assessment method, which can identify crops and weeds in the greenhouse with high accuracy [20]. In industry, it is mainly used to detect surface defects of workpieces, and through machine vision technology, it can identify small defects on the surface of workpieces [21] and diagnose faults in rotating parts [22].…”