Urban areas face increasing challenges in constructing resilient infrastructure on weak or unstable soils, especially amid the impacts of climate change and rapid urbanization. This study introduces an innovative AI-driven framework that integrates advanced hybrid deep learning architectures namely Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Transformer models for accurately predicting the Unconfined Compressive Strength (UCS) of Nano-silica (NS) stabilized soils. A key innovation of this research lies in the development of a novel CNN-Transformer hybrid model, which outperforms traditional and standalone AI models, achieving an R2 of 0.97 and RMSE of 0.22 reducing prediction error by over 49%. Robustness was further validated using a 10,000-iteration Monte Carlo simulation. In addition to predictive modeling, this study pioneers a comparative Life Cycle Assessment (LCA) between NS and cement-based stabilization, revealing that NS reduces CO₂ emissions by 55%, lowers energy consumption by 73%, and improves material efficiency. Furthermore, a user-friendly Graphical User Interface (GUI) tool has been developed, enabling real-time optimization of NS dosage for practical implementation in urban projects. This research not only contributes a high-performance predictive tool but also supports sustainable construction practices, aligning with SDG 9 (Industry, Innovation, and Infrastructure) and SDG 12 (Responsible Consumption and Production).

This study presents a novel approach to predicting the factor of safety (FOS) for infinite slopes stabilized with nano-silica (NS), leveraging machine learning (ML) models to address limitations of traditional geotechnical assessments. A unique dataset, consisting of 1053 samples, was compiled to capture critical parameters, including NS content and curing time, thereby enhancing model accuracy across diverse conditions. Six ML models were evaluated, with the gradient boosting (GB) model emerging as the most robust, achieving an R ² value of 0.99, mean absolute error of 0.03 and root mean squared error of 0.04. A reliability analysis quantified a failure probability of 29.66% and a reliability index of 1.64 for NS-treated soils, underscoring the model’s applicability in real-world geotechnical design. Additionally, a parabolic regression equation was derived, offering practitioners a reliable tool for FOS estimation. To facilitate practical implementation, an intuitive graphical user interface (GUI) was developed, allowing for accurate FOS predictions based on user-defined inputs. This study provides a comprehensive, data-driven model for NS-stabilized slopes, advancing the field with a user-friendly predictive tool that supports sustainable engineering practices in challenging geotechnical environments.