Prediction of the Unconfined Compressive Strength of a One-Part Geopolymer-Stabilized Soil Using Deep Learning Methods with Combined Real and Synthetic Data

• Published in: Buildings (Basel) 2024-09, Vol.14 (9), p.2894
• Main Authors: Chen, Qinyi, Hu, Guo, Wu, Jun
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Back propagation networks; Brain; By products; Cement; Compressive strength; Concrete; Cost analysis; Datasets; Deep learning; deep learning method; Electron microscopes; Generative Adversarial Networks; Geopolymers; interpretable machine learning method; Long short-term memory; Machine learning; Mechanical properties; Methods; Neural networks; Neurons; one-part geopolymer; Portland cement; Portland cements; Sensitivity analysis; Shear strength; Soft clay; Soil properties; Soil stabilization; Soil strength; Stabilization; Synthetic data; unconfined compressive strength
• ISSN: 2075-5309; 2075-5309
• DOI: 10.3390/buildings14092894

This study focused on exploring the utilization of a one-part geopolymer (OPG) as a sustainable alternative binder to ordinary Portland cement (OPC) in soil stabilization, offering significant environmental advantages. The unconfined compressive strength (UCS) was the key index for evaluating the efficacy of OPG in soil stabilization, traditionally demanding substantial resources in terms of cost and time. In this research, four distinct deep learning (DL) models (Artificial Neural Network [ANN], Backpropagation Neural Network [BPNN], Convolutional Neural Network [CNN], and Long Short-Term Memory [LSTM]) were employed to predict the UCS of OPG-stabilized soft clay, providing a more efficient and precise methodology. Among these models, CNN exhibited the highest performance (MAE = 0.022, R2 = 0.9938), followed by LSTM (MAE = 0.0274, R2 = 0.9924) and BPNN (MAE = 0.0272, R2 = 0.9921). The Wasserstein Generative Adversarial Network (WGAN) was further utilized to generate additional synthetic samples for expanding the training dataset. The incorporation of the synthetic samples generated by WGAN models into the training set for the DL models led to improved performance. When the number of synthetic samples achieved 200, the WGAN-CNN model provided the most accurate results, with an R2 value of 0.9978 and MAE value of 0.9978. Furthermore, to assess the reliability of the DL models and gain insights into the influence of input variables on the predicted outcomes, interpretable Machine Learning techniques, including a sensitivity analysis, Shapley Additive Explanation (SHAP), and 1D Partial Dependence Plot (PDP) were employed for analyzing and interpreting the CNN and WGAN-CNN models. This research illuminates new aspects of the application of DL models with training on real and synthetic data in evaluating the strength properties of the OPG-stabilized soil, contributing to saving time and cost.