A Supervied Machine Learning Approach to Predict the Compressive Strength of Eco-Friendly Concrete Incorporating Waste Glass Powder

DOI

10.2991/978-94-6463-884-4_27How to use a DOI?

Keywords

Waste Glass Powder; Compressive Strength; Eco Friendly Concrete; Machine Learning Algoritms; Shapley Analysis; Bagging Regressor

Abstract

Use of wasteglass as a partial replacement to cement in concrete has potentially a significant potential in materials innovation to produce a sustainable infrastruct system that is not only environmentally friendly but also energy and cost efficient. This research shows how it is effective using waste glass powder (WGP), as an alternative to cement to drive green concrete activities. To determine the mechanical characteristics of concrete and specifically, its compressive strength complex machine learning (ML) techniques and models including, but not limited to, the level of linear regression, support-vector machine, bagging regressor, visual analysis, such as SHAP visualization, and feature contribution heat-maps were used. Cementitious composites which included WGP were tested using these methods. In the relevant studies, a total of 335 data points has been obtained. The experiment analyses some of the parameters of input i.e. the binder content, water, superplasticizer, limestone, supplementary cementitious material, waste glass powder, coarse aggregate and fine aggregate to get the finished product which is the compressive strength. The coefficient of determination (R²) and parameters MSE, RMSE and MAE were utilized to assess the efficiency of the ML models. The modeling methods showed that the degree of accuracy presented by the support vector machine and the linear regression method was moderate. Then the bagging regressor was more accurate in forecasting compressive strength as compared to others. The findings show that it is highly effective to determine the mechanical properties with better levels of precision as compared to the simple run-and-test of massive experimentation.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Abrar M. Shahariar
AU  - Shuvo Dip Datta
PY  - 2025
DA  - 2025/11/18
TI  - A Supervied Machine Learning Approach to Predict the Compressive Strength of Eco-Friendly Concrete Incorporating Waste Glass Powder
BT  - Proceedings of the 8th International Conference on Engineering Research, Innovation, and Education 2025 (ICERIE 2025)
PB  - Atlantis Press
SP  - 222
EP  - 230
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-884-4_27
DO  - 10.2991/978-94-6463-884-4_27
ID  - Shahariar2025
ER  -