Geotechnical Risk Assessment using Graph Convolutional Networks and Hybrid LSTM-FEA Models in Mega Highway Projects
| International Journal of Civil Engineering |
| © 2026 by SSRG - IJCE Journal |
| Volume 13 Issue 2 |
| Year of Publication : 2026 |
| Authors : Radhika S Thakre, Uday P Waghe, Yogesh P Kherde, Rajesh M. Dhoble, Mangesh P Bhorkar, Amar Jain |
10.14445/23488352/IJCE-V13I2P114
How to Cite?
Radhika S Thakre, Uday P Waghe, Yogesh P Kherde, Rajesh M. Dhoble, Mangesh P Bhorkar, Amar Jain, "Geotechnical Risk Assessment using Graph Convolutional Networks and Hybrid LSTM-FEA Models in Mega Highway Projects," SSRG International Journal of Civil Engineering, vol. 13, no. 2, pp. 186-207, 2026. Crossref, https://doi.org/10.14445/23488352/IJCE-V13I2P114
Abstract:
Mega highway projects are very sensitive to a number of geotechnical risks in the form of soil instability, seismic events, and environmental change, leading to costly failures. The current risk assessment methods are not capable of integrating the range of datasets—spatial data, temporal data, and real-time streams of data—and thus lack good levels of predictability, combined with a lack of response time. Thus, with a view to addressing these barriers, we introduce the new concept of Big Data Geotechnical Risk Assessment Model (BD-GRAM), which applies big data analytics and advanced machine learning algorithms in order to better predict and mitigate geotechnical risks for different scenarios. BD-GRAM combines various methods adapted to geotechnical data samples. The Graph Convolutional Networks (GCNs) are utilized for spatial and temporal data fusion, where complex spatial dependencies and temporal variations in soil properties, as well as samples of seismic data, are considered. GCNs, with the enhancement of attention mechanisms, have the ability to increase accuracy by as much as 20% compared with the conventional methods. A hybrid model by combining LSTMs and FEA, misleading synergistic use of physical laws, as well as temporal patterns of data pertaining to predictive accuracy, with an improvement of 25%. Near real-time processing on Apache Kafka & Apache Spark enables near real-time continuous monitoring of risk with alerting on. SHAP (Shapley Additive Explanations) ensures interpretability of the model outputs, as well as transparency of the factors driving the risk predictions. Lastly, the system is scalable using GPU-accelerated TensorFlow to Run Masses of datasets & samples. This fully integrated approach is optimized in this way to further enhance predictive accuracy and reduce false-positives and false-negatives, enhancing the speed and response of geotechnical risk assessment responses in real time. BD-GRAM represents an effective way to meet the early identification and mitigation of geotechnical challenges in a scalable data-driven manner for improved resilience and safety of large-scale infrastructures in any given highway scenario.
Keywords:
Big Data, Geotechnical Risk, Graph Convolutional Networks, Finite Element Analysis, Real-Time Monitoring.
References:
[1] Cuiying Zhou et al., “Early Risk Warning of Highway Soft Rock Slope Group using Fuzzy-based Machine Learning,” Sustainability, vol. 14, no. 6, pp. 1-28, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Renato Macciotta, and Michael T. Hendry, “Remote Sensing Applications for Landslide Monitoring and Investigation in Western Canada,” Remote Sensing, vol. 13, no. 3, pp. 1-23, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Kamila Amel Benachenhou, Anis Lakermi, and Mohammed Amine Allal, “Application of Bayesian Networks for Geotechnical Risk Assessment: Case of the Ghazaouet Highway Viaduct (Algeria),” Innovative Infrastructure Solutions, vol. 8, no. 1, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Yamei Li et al., “Risk Assessment of Debris Flows Along the Karakoram Highway (Kashgar-Khunjerab Section) in the Context of Climate Change,” International Journal of Disaster Risk Science, vol. 14, no. 4, pp. 586-599, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Ratan Das, and T.N. Singh, “Geotechnical Insights of the Cut Slopes Along Silchar-Haflong National Highway, Assam, India,” Geotechnical and Geological Engineering, vol. 42, no. 7, pp. 6195-6217, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Larissa Regina Costa Silveira, Milene Sabino Lana, and Tatiana Barreto dos Santos, “A Quantitative Rockfall Risk Analysis System for Highway Rock Slopes,” Geotechnical and Geological Engineering, vol. 42, no. 2, pp. 1131-1152, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] G.L. Sivakumar Babu, “Reliability and Risk Analysis in Geotechnical and Geoenvironmental Engineering,” Indian Geotechnical Journal, vol. 54, no. 5, pp. 1705-1737, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Opeyemi E. Oluwatuyi et al., “Uncertainty Reduction Strategies to Enhance Geotechnical Site Characterization: A Case Study of the Red Roof Landslide in Wyoming,” Discover Geoscience, vol. 2, no. 1, pp. 1-17, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Ahmad Abo-El-Ezz et al., “Scenario-based Earthquake Damage Assessment of Highway Bridge Networks,” Advances in Bridge Engineering, vol. 4, no. 1, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Ozgur Satici, and Esra Satici, “Theoretical Semi-Quantitative Risk Assessment Methodology for Tunnel Design and Construction Processes,” International Journal of System Assurance Engineering and Management, vol. 15, no. 7, pp. 3385-3405, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Ramandeep Kaur et al., “Geotechnical Characterization and PS-InSAR for Risk Analysis of Solang Landslide in Beas Valley, NW Himalaya: A Wake-Up Call!,” Journal of the Indian Society of Remote Sensing, vol. 52, no. 5, pp. 1045-1059, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Sinem Bozkurt, and Sami Oguzhan Akbas, “Finite Element-based Geotechnical Risk Analysis for Anchor-Supported Deep Excavations,” Arabian Journal of Geosciences, vol. 16, no. 8, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Benjamín Guajardo, Francisco Pinto, and Rodrigo Astroza, “Effects of Soil Spatial Variability on the Seismic Response of Multi-Span Simply-Supported Highway Bridges,” Bulletin of Earthquake Engineering, vol. 22, no. 5, pp. 2643-2675, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Krishna R. Reddy, Jagadeesh Kumar Janga, and Girish Kumar, “Sustainability and Resilience: A New Paradigm in Geotechnical and Geoenvironmental Engineering,” Indian Geotechnical Journal, vol. 55, no. 4, pp. 2510-2531, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Mustafa Fener, and Nehir Varol, “Quantitative Risk Assessment of Rock Instabilities Threatening Manazan Caves, Karaman, Türkiye,” Geoheritage, vol. 16, no. 2, pp. 1-16, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Falak Zahoor et al., “Geotechnical Characterisation and 2D Soil Cross-Section Model Development in the Kashmir Basin,” Arabian Journal of Geosciences, vol. 17, no. 8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Taylor Wollenberg-Barron et al., “Integrating Change Detection and Slope Assessment for Enhanced Rock Slope Asset Management,” Geotechnical and Geological Engineering, vol. 42, no. 8, pp. 7063-7083, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Yasmeen Mohammed Sameer, Adil Nuhair Abed, and Khamis Naba Sayl, “Geomatics-based Approach for Highway Route Selection,” Applied Geomatics, vol. 15, no. 1, pp. 161-176, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Abdulla Al-Rawabdeh et al., “Modeling Landslides Hazard Along Amman-Jerash-Irbid Highway, Jordan by Integrating Open Street Map (OSM) and Weighted Linear Combination (WLC) Techniques,” Modeling Earth Systems and Environment, vol. 10, no. 2, pp. 2547-2565, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[20] İbrahim Özgür Dedeoğlu et al., “January 24, 2020 Sivrice-Elazığ (Türkiye) Earthquake: The Seismic Assessment of the Earthquake Territory, Geotechnical Findings and Performance of Masonry Buildings,” Iranian Journal of Science and Technology, Transactions of Civil Engineering, vol. 48, no. 4, pp. 2393-2412, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Fu-gang Xu et al., “Risk Assessment of Geological Disasters in Beichuan County After the Wenchuan Earthquake based on ArcGIS,” Bulletin of Engineering Geology and the Environment, vol. 82, no. 11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Ankit Kumar, and Aditya Parihar, “Quantifying Suitability of Waste Foundry Sands from Different Metal Castings for Geotechnical Applications,” Sadhana, vol. 49, no. 1, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Mawuko Luke Yaw Ankah, and Cem Kincal, “Stability Analysis of Rock Slopes using Kinematic Analysis and Numerical Modeling: Foça-Bağarası State Highway, Turkey,” Modeling Earth Systems and Environment, vol. 8, no. 4, pp. 5225-5233, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Chao Li et al., “Evaluating the Impact of Highway Construction Projects on Landscape Ecological Risks in High Altitude Plateaus,” Scientific Reports, vol. 12, no. 1, pp. 1-16, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Mohamed A.H. Sakr et al., “Geospatial Technology Utilization for Geotechnical Hazard Evaluation of Sustainable Urban Development of Buraydah City, Kingdom of Saudi Arabia,” Arabian Journal of Geosciences, vol. 15, no. 15, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Ankit Kumar, and Aditya Parihar, “State-of-the-Art Review on Sustainability in Geotechnical Applications of Waste Foundry Sand,” Indian Geotechnical Journal, vol. 52, no. 2, pp. 416-436, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Chao Yin, Zhanghua Wang, and Xingkui Zhao, “Spatial Prediction of Highway Slope Disasters based on Convolution Neural Networks,” Natural Hazards, vol. 113, no. 2, pp. 813-831, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Rehan Asad et al., “Seismic Risk Assessment and Hotspots Prioritization: A Developing Country Perspective,” Natural Hazards, vol. 117, no. 3, pp. 2863-2901, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Xiaojun Liu et al., “Research on Risk Assessment on Large Deformation of Loess Tunnels Underneath Residential Areas,” KSCE Journal of Civil Engineering, vol. 26, no. 6, pp. 2826-2834, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Anders Solheim, Kjetil Sverdrup-Thygeson, and Bjørn Kalsnes, “Hazard and Risk Assessment for Early Phase Road Planning in Norway,” Natural Hazards, vol. 119, no. 2, pp. 943-963, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Zhang Songan et al., “Three-Dimensional Information Modeling based on Incomplete Data for Anchor Engineering,” IEEE Access, vol. 11, pp. 122526-122540, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Shahid Malik et al., “An Acoustic 3-D Positioning System for Robots Operating Underground,” IEEE Sensors Letters, vol. 6, no. 10, pp. 1-4, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Seunghwan Seo, Jungwoo Hwang, and Moonkyung Chung, “Supervised Domain Adaptation for Remaining Useful Life Prediction based on AdaBoost with Long Short-Term Memory,” IEEE Access, vol. 12, pp. 96757-96768, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Abdul Ghaffar et al., “Analysis of Force Sensor using Polymer Optical Fiber based on Twisting Structure,” IEEE Sensors Journal, vol. 22, no. 24, pp. 23960-23967, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Chao Fu et al., “3-D Structural Complexity-Guided Predictive Filtering: A Comparison Between Different Non-Stationary Strategies,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-15, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Wu Qi et al., “A Modified Model for the Temperature Effect-Induced Error in Hydrostatic Leveling Systems,” IEEE Sensors Journal, vol. 22, no. 10, pp. 9473-9482, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Qi Zhao et al., “A Fast and Efficient Method for 3-D Transient Electromagnetic Modeling Considering IP Effect,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-18, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Yu Liu et al., “A Novel Student Achievement Prediction Method based on Deep Learning and Attention Mechanism,” IEEE Access, vol. 11, pp. 87245-87255, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[39] Zhiming Liu et al., “Landslide Monitoring Suitability of Sensor-Enabled Piezoelectric Geocables based on Drawing Tests,” IEEE Sensors Journal, vol. 23, no. 20, pp. 25433-25439, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[40] Senlin Yang et al., “Well-Log Information-Assisted High-Resolution Waveform Inversion based on Deep Learning,” IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1-5, 2023.
[CrossRef] [Google Scholar] [Publisher Link]