• Saurabh Kumar Anuragi
• D.Kishan
• S.K.Saritha

The study presents a comparative analysis of three prediction models, Logistic Regression (LR), Random Forest (RF), and Multi-Layer Perceptron Neural Networks (MLPNN). It employs a trial and error method for optimizing hyperparameters in slope stability prediction. The study utilizes a dataset comprising 108 slope cases with various influencing factors, including unit weight (Ƴ), cohesion (c), angle of internal friction (ɸ), slope angle (β), height (H), pore water pressure coefficient (ru), and factor of safety (FS) as inputs, while slope status (S) serves as the output variable. Based on the confusion matrix and ROC curves, the RF model demonstrated superior performance over the other models. The utilization of RF enhances the capacity and efficiency of slope deformation prediction models, establishing it as the most accurate tool for forecasting slope stability.

Machine Learning, Slope Stability, Limit Equilibrium, Logistic Regression, Neural Networks, Artificial Intelligence

"Comparative Analysis of Slope Stability Prediction using Logistic Regression and Random Forest Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 1, page no.f564-f570, January-2024, Available :http://www.jetir.org/papers/JETIR2401568.pdf

"Comparative Analysis of Slope Stability Prediction using Logistic Regression and Random Forest Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 1, page no. ppf564-f570, January-2024, Available at : http://www.jetir.org/papers/JETIR2401568.pdf