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

Institutions

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Stability Assessment of Engineered Slopes Along NH ‐9 Using Extensions of Slope Mass Rating and Artificial Neural Network‐Based Prediction

M. E. A. Mondal, Tariq Siddique, Pirzada Mohammad Haris, Harsh Varshney et al.
Geological Journal
Geotechnical Engineering and Analysis
article

Stability Assessment of Engineered Slopes Along NH ‐9 Using Extensions of Slope Mass Rating and Artificial Neural Network‐Based Prediction

M. E. A. Mondal, Tariq Siddique, Pirzada Mohammad Haris, Harsh Varshney, Farrukh Hasan
article en

Abstract

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.

Geological Journal
Aligarh Muslim University (IN)
Geotechnical Engineering and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Stability Assessment of Engineered Slopes Along NH ‐9 Using Extensions of Slope Mass Rating and Artificial Neural Network‐Based Prediction — M. E. A. Mondal, Tariq Siddique, et al. · Geological Journal (2026) | TGRS Research Map | TGRS