Stability Assessment of Engineered Slopes Along NH ‐9 Using Extensions of Slope Mass Rating and Artificial Neural Network‐Based Prediction
ABSTRACT The present study aims to develop an artificial neural network (ANN)‐based predictive model for slope mass rating (SMR) values. The study further presents a detailed geotechnical investigation of 13 vulnerable slopes along national highway‐9 (NH‐9) using SMR and its extensions, including Continuous SMR (CoSMR), Chinese SMR (ChSMR) and Continuous Chinese SMR (CoChSMR). For these slopes, a linear regression analysis indicated strong correlations among different extensions of SMR ( R 2 values of 0.90 for SMR vs. CoSMR, 0.97 for SMR vs. ChSMR and 0.85 for SMR vs. CoChSMR). Furthermore, an ANN‐based machine learning model was developed using Python‐generated synthetic data derived from SMR input parameters to predict SMR values. The model demonstrated high predictive performance, with a correlation coefficient ( R > 0.99) during training, validation and testing and achieves R = 0.98 when the model was applied to a dataset of cut slopes along NH‐9. Furthermore, ANN‐based feature importance analysis reveals that SMR prediction is dominantly controlled by F 1 and F 3 parameters of SMR, which are related to relative dip direction and amount of discontinuity‐slope. Rock mass quality and discontinuity characteristics have relatively less influence. The results demonstrated that ML models can reliably supplement the empirical classification systems, providing a rapid and robust tool for slope stability assessment in the Himalaya and regions of similar geo‐structural setup.
Authors
- M. E. A. Mondal (ORCID: https://orcid.org/0000-0001-5610-1319)
- Tariq Siddique (ORCID: https://orcid.org/0000-0001-9852-6737)
- Pirzada Mohammad Haris (ORCID: https://orcid.org/0000-0003-4896-3079)
- Harsh Varshney (ORCID: https://orcid.org/0000-0003-2914-473X)
- Farrukh Hasan (ORCID: https://orcid.org/0009-0008-1012-3115)
Institutions
- Aligarh Muslim University (IN)
Publication Details
- Journal
- Geological Journal
- Published
- 2026-11-15
- DOI
- https://doi.org/10.1002/gj.70553
- Primary Topic
- Geotechnical Engineering and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00