Optimized Hybrid Learning Model for Strength Prediction of Textile Effluent Sludge‐Based Concrete

ABSTRACT In previous concrete applications, fly ash (FA), silica fume (SF), metakaolin (MK), ground granulated blast furnace slag (GGBS), waste glass powder (WGP), rice husk ash (RHA), ceramic waste powder (CWP), and marble powder (MP) have all been proven as potential industrial materials that can be utilized as supplementary cementitious material (SCM). Recently, the use of textile effluent sludge (TES) as SCM has drawn significant attention of several researchers for promoting sustainability. This study examines the prediction of compressive strength (CS) and tensile strength (TS) of concrete utilizing TES through several machine learning (ML) techniques, particularly random forest (RF), support vector machine (SVM), extreme gradient boost (XGBoost), and K‐nearest neighbors (KNN). Furthermore, deep learning techniques, involving convolutional neural networks and long short‐term memory networks, are utilized. Additionally, a hybrid machine learning (HML) model integrating RF and SVM algorithms as well as hybrid deep learning (HDL) models incorporating CNN and LSTM networks were developed for strength prediction. After hyperparameter tuning with the grid searching method, the standalone LSTM model has demonstrated superior performance in CS prediction (), achieving the highest accuracy compared to all ML, DL, and hybrid models whereas the standalone SVM model exhibited the highest accuracy among all models after tuning for TS prediction (). Notable, both hybrid frameworks exhibited competitive performance, demonstrating predictive accuracies comparable to the best standalone models, hybrid CNN‐LSTM model has shown the second‐highest accuracy () in terms of CS prediction the hybrid RF‐SVM model has been proven to possess greater predictive accuracy () than CNN‐LSTM in terms of TS prediction. In fact, this study has been designed to promote the high‐scale utilization of TES as SCM in concrete, which will be helpful for environmental pollution control.