Predictive modeling of sustainable recycled materials for stone column construction
Open Access
- 5 October 2024
- journal article
- research article
- Published by Springer Nature in Innovative Infrastructure Solutions
- Vol. 9 (11) , 1-19
Abstract
Climate change due to carbon dioxide emissions is one of the most significant global challenges. Sustainable recycled materials are recognized as a critical factor in mitigating climate change, representing a fundamental strategy for reducing gas emissions and preserving the environment. Promising sustainable recycled materials in construction, such as crushed asphalt, crushed concrete, crushed ceramic, and treated concrete offer numerous advantages, including reduced carbon dioxide $${\text{(CO}}_{2} )$$ emissions, cost-effectiveness, increased strength, and enhanced mechanical properties. In this study, various machine learning techniques, including the support vector machine (SVM), multiple linear regression (MLR), gaussian process regression (GPR), and artificial neural network (ANN), are used to assess the effectiveness of sustainable recycled materials within stone columns. The MLR model was specifically utilized to predict the ultimate stress equation for these materials within stone columns. Forty-five constructed samples were used in developing the models. The effectiveness of each model was evaluated using various statistical assessment measures, including mean absolute error (MAE), absolute fraction of variation ( $${\text{R}}^{2}$$ ), and root mean square error (RMSE). The predictive model’s performance was validated using the k-fold cross-validation method. The ANN model with an $${\text{R}}^{2}$$ value of 0.962 and an RMSE value of 7.268 kPa, performed better compared to GPR, SVM and MLR models. In summary, the results of the study indicate that the MLR model, utilizing the identified input parameters, can accurately predict the ultimate stress for different sustainable recycled materials. Implementing such technologies within the construction sector can expedite and reduce the cost of assessing material characteristics and the influence of input parameters.
Keywords
Funding Information
- Delta University for Science and Technology
This publication has 42 references indexed in Scilit:
- Innovative Approaches to Soft Clay Stabilization: Utilizing Sustainable Materials for the Stone Column TechniqueGeotechnical and Geological Engineering, 2024
- Using Artificial Neural Networks to predict the Unconfined Compressive Strength of Clayey Soils Stabilized by Various Stabilization AgentsKSCE Journal of Civil Engineering, 2023
- Application of KRR, K-NN and GPR Algorithms for Predicting the Soaked CBR of Fine-Grained Plastic SoilsArabian Journal for Science and Engineering, 2023
- Innovative modeling techniques including MEP, ANN and FQ to forecast the compressive strength of geopolymer concrete modified with nanoparticlesNeural Computing and Applications, 2023
- Empirical approach for bearing capacity prediction of geogrid-reinforced sand over vertically encased stone columns floating in soft clay using support vector regressionNeural Computing and Applications, 2019
- Experimental study on soil improvement with stone columns and granular blanketsJournal of Central South University, 2018
- Determination of Bearing Capacity of Stone Column with Application of Neuro-fuzzy SystemKSCE Journal of Civil Engineering, 2017
- An artificial neural network approach for under-reamed piles subjected to uplift forces in dry sandNeural Computing and Applications, 2017
- Support vector regression-based model for prediction of behavior stone column parameters in soft clay under highway embankmentNeural Computing and Applications, 2017
- Tenfold cross validation artificial neural network modeling of the settlement behavior of a stone column under a highway embankmentArabian Journal of Geosciences, 2013