Integrating Random FEM and CNN for Efficient Slope Stability Analysis with Spatially Variable Soil Properties
Bibliographic record
Abstract
Slope stability analysis that accounts for spatial variability of soil properties is computationally intensive.This study presents a hybrid approach integrating the Random Finite Element Method (RFEM) with Convolutional Neural Networks (CNN) and data augmentation to address this challenge.Using random field theory, random field samples for soil cohesion and friction angle are generated, for which RFEM is used to calculate the factor of safety.A data augmentation technique was applied to expand the RFEM dataset, generating up to 10,000 training samples from 200 initial simulations, significantly enhancing model performance.The CNN model, trained on this augmented dataset with a magnification factor of 50, achieved an R-squared value of 0.82 on cross-validation, demonstrating high accuracy.This approach drastically reduces computational time, with 200 RFEM simulations requiring about 10 hours while enabling the CNN to perform 10,000 stochastic analyses in mere minutes.The hybrid RFEM-CNN model was applied to a typical 𝑐𝑐-𝜙𝜙 slope and predicted a probability of failure of 0.12%, closely aligning with reliability estimates from established finite difference methods and avoiding overestimations common in limit equilibrium methods.The findings highlight the model's potential as an efficient and robust tool for slope reliability studies, reducing computational costs while maintaining high prediction accuracy.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".