Home Predicting mechanical properties of sustainable green concrete using novel machine learning: Stacking and gene expression programming
Article Open Access

Predicting mechanical properties of sustainable green concrete using novel machine learning: Stacking and gene expression programming

  • Muhammad Waqas Ashraf , Adnan Khan , Yongming Tu EMAIL logo , Chao Wang EMAIL logo , Nabil Ben Kahla , Muhammad Faisal Javed , Safi Ullah and Jawad Tariq
Published/Copyright: August 26, 2024
Download Article (PDF)
Become an author with De Gruyter Brill
Submit Manuscript Author Information
REVIEWS ON ADVANCED MATERIALS SCIENCE
From the journal REVIEWS ON ADVANCED MATERIALS SCIENCE Volume 63 Issue 1

Abstract

Using rice husk ash (RHA) as a cement substitute in concrete production has potential benefits, including cement consumption and mitigating environmental effects. The feasibility of RHA on concrete strength was investigated in this research by predicting the split tensile strength (SPT) and flexural strength (FS) of RHA concrete (RHAC). The study used machine learning (ML) methods such as ensemble stacking and gene expression programming (GEP). The stacking model was improved using base learner configurations ML models, such as, random forest (RF), support vector regression, and gradient boosting regression. The proposed models were validated by statistical tests and external validation criteria. Moreover, the effect of input parameters was investigated using Shapley adaptive exPlanations (SHAP) for RF and parametric analysis for GEP-based models. The analysis revealed that the stacking ensemble integrates base learner predictions and demonstrated superior performance, with R values greater than 0.98 and 0.96. Mean absolute error and root mean square error values for both SPT and FS were 0.23, 0.3, 0.5, and 0.7 MPA, respectively. The SHAP analysis demonstrated water, cement, superplasticizer, and age as influential parameters for the RHAC strength. Furthermore, the SPT and FS of RHAC can be predicted with an acceptable error using the GEP expressions in the standard design procedure.

Graphical abstract

Keywords: rice husk ash; stacking; gene expression programming; tensile and flexural strength; parametric analysis; SHAP analysis

1 Introduction

The construction industry prioritizes sustainable materials, particularly concrete, which is a high-energy and resource-intensive material. Consequently, researchers are exploring alternatives to traditional cement and components that minimize environmental impact. Rice husk ash (RHA), a readily available by-product from rice milling, holds promise as a sustainable concrete constituent [1]. The finished product, known as husk, is contained within the rice grain. In the paddy production cycle, 78% of the weight is received as rice and 22% is husk [2]. Approximately 750 million tons of rice husk are produced worldwide every year [3]. The research concludes that RHA consists of 85–95% amorphous silica [4]. However, this silica is not biodegradable and is commonly utilized in landfills. It is widely recognized that RHA has both filler and pozzolanic effects in mortar and concrete. The effects of RHA varied among samples due to factors such as paddy type, crop year, climate, and location [5]. Researchers found that RHA’s silica generation, carbon reduction, structure, fineness, ignition loss, increasing filler, and pozzolanic activity are influenced by incineration technique, temperature, and burning time [6]. There have been several attempts to develop and utilize RHA in practical research. According to reports, concrete’s pozzolanic and filler action with RHA results in notable microstructural changes [6,7,8].

The incorporation of RHA in concrete offers a promising approach to enhance its properties, including compressive strength (CS), split tensile strength (SPT), and durability, as demonstrated by numerous research studies. RHA not only improves concrete performance but also reduces material costs due to decreased cement demand. Additionally, it provides environmental benefits through effective waste management [9]. Chopra and Siddique [4] investigated concrete strength at various ages using RHA substitute proportions of 0, 10, 15, and 20%. Results indicate a 25, 33, and 36% improvement in concrete CS at 7, 28, and 56 days at a 15% substitution rate; similarly, cement replacement with RHA increased SPT by 15%. Singh [10] concluded that SPT increased by 3.9% with 5% replacement but decreased by 17.5% at 10% replacement. Likewise, flexural strength (FS) increased by 10.9% at 5% replacement but decreased by 3% at 10% replacement compared to the control mix. Over 10% replacement, SPT and FS decreased significantly, with 19.3% SPT decrease at 15% replacement and 31.7% SPT decrease at 20% replacement. The study observed that the highest CS, SPT, and FS values were achieved after 7, 14, and 28 days of curing when the RHA was replaced by 15%. Additionally, it was found that the percentage loss of strength and weight increased as the content of RHA increased from 0 to 25% [11]. Several types of factors can be influenced by using RHA as supplementary cementation material, including the aggregate water-to-cement ratio, particle size, waste content, and compressive loading ability [12]. Furthermore, using these materials in concrete enhances its ability to withstand compression, decreases its emission of greenhouse gases, and improves its SPT and FS, as depicted in Figure 1.

Figure 1 Manufacturing and effect of RHA concrete.
Figure 1

Manufacturing and effect of RHA concrete.

Although mechanical testing is the most typical method for evaluating concrete’s CS and SPT, it tends to be time-consuming and expensive [2]. Some researchers have developed a linear regression (LR) model to predict the SPT and FS of concrete. However, due to the quite nonlinear relationships between the concrete components and strength, it is challenging to develop accurate predictions [13]. Researchers have turned to artificial intelligence (AI) algorithms to address structural challenges [14]. AI techniques such as artificial neural networks (ANNs) are a pattern recognition system that determines the pattern between different parameters, a computational approach that is increasingly used in developing predictive models [15,16]. Another advantage of AI, in contrast to traditional regression techniques, is superior performance, and it can handle complex data and nonlinear relationships between independent and dependent parameters. Therefore, several studies have leveraged AI techniques to predict CS. Among the prevalent AI methods for analyzing concrete properties are ANN and support vector machines (SVM) [17]. Recently, a high-performance concrete strength prediction model was developed using a modified firefly approach combined with an ANN model, showcasing impressive predictive capabilities [18]. Such algorithms play a pivotal role in enhancing the design and performance of concrete mixes [19,20]. Another study also used the ANN approach to predict the CS of lightweight concrete reinforced with steel fibers [21]. Similarly, the ANN model is an effective methodology for predicting the mechanical properties of sustainable concrete [22–25]. Furthermore, ANNs have been observed to have limited external validity when employed in analyzing diverse datasets. Additionally, it is difficult to determine the optimal architecture of neural networks and the number of hidden layers in the structure. To address the aforementioned issues inherent to ANNs, it is essential to provide adequate attention to tree-based ensemble approaches. Ensemble learning approaches have become increasingly popular due to their greater prediction capabilities [26–28]. Some researchers have proposed bagging and boosting series algorithms for concrete strength prediction. To predict concrete strength, Lyngdoh et al. used significant machine learning (ML) algorithms. According to their outcomes, the XGBoost model is the most effective [29]. In another study, XGBoost and CatBoost were employed to predict the concrete strength, and it was discovered that XGBoost and CatBoost had considerably fewer mean errors between predicted and actual values [30]. Hybrid ML models were used to predict the strength of ultra-high-performance concrete and were found to have a better-predicted performance than traditional methods [31,32]. Gene expression programming (GEP) algorithm, simple and practical mathematical equations predicted ground granulated blast-furnace slag (GGBS)-based geopolymer concrete mortar CS [33]. Chu et al. [34] concluded that the accuracy and predictability of GEP and multi-expression programming (MEP) models were evaluated by comparing them with LR and nonlinear regression (NLR) models. The GEP equation demonstrated a diminished statistical error and a higher correlation coefficient than the MEP equation. Moreover, Table 1 summarizes the prediction properties presented by various researchers.

Table 1

Existing research summary of ML algorithm for sustainable concrete

Ref. ML algorithm Dataset size Material Investigated property
[35] DT, RF, SVM, K-nearest neighbors, and ANN 625 GGBFS CS
[38] Adaptive regression splines (MARS) 161 GGBFS CS
[39] Multilayer perceptron neural network (MLPNN) and bagging ensemble (BE) 145 Alkali activated concrete (AAC) Statistic and dynamic yield stress
[40] MLPNN, bagging, and XGB 676 AAC CS
[34] GEP and MEP 311 Fly-ash (FA) CS
[36] SVM and gradient boosting machine (GBM) 81 Ceramic waste and nylon fiber SPT and CS
[41] MARS, GEP, M5P Model Tree (M5P) and extreme learning machine (ELM) 449 Oil palm by-product CS
[42] XGBoost, AdaBoost, and DT 60 Ceramic waste powder CS
[37] SVM 115 FA CS
[43] MARS 21 Crumb rubber with Silica fume CS
[44] ANN, GP, M5P, SVM 137 Waste foundry sand (WFS) CS, SPT, and FS
[45] ANN 470, 295 WFS CS, SPT, FS, modulus of elasticity
[46] LR, Multilinear regression, NLR 420 Nanosilica CS
[47] LGB, XGB, RF 1,404 RHAC CS
[48] ANN 236 FA CS
[49] Neuro-imperialism and neuro-swarm) 379 FA CS

While ensemble and boosting techniques have been established as efficient modeling methodologies across various engineering applications, there remains a limited exploration of these techniques for SPT and FS [35–37]. In addition, very little scientific research has been done on using stacking ensemble techniques to predict the mechanical properties of RHA concrete (RHAC). The advantage of the stacking ensemble model is that it combines the best prediction models and achieves robust prediction results. Therefore, in this study, stacking-based ensemble models are created to predict the mechanical properties (SPT, FS) of RHAC. Ensemble learning models were utilized for base learners. For individual prediction and model hyperparameter optimization, random forest (RF), support vector regression (SVR), and gradient boosting regression (GBR) were employed. The stacking ensemble learning model has been developed employing LR as the meta-learners and RF and/or SVR and GBR models as the base learners. In addition, GEP models have been developed to establish empirical relationships with acceptable error margins for predicting SPT and FS. Furthermore, various statistical criteria, interpretations, and parametric analyses validated the models’ effectiveness.

2 Research methodology

2.1 Data acquisition

In ML-based prediction models, the greater range of data with stronger correlation and accurate choice of input variables can help create a more valuable model with higher accuracy. In this regard, the models were developed using a comprehensive database of RHAC sourced from existing literature [4,10,50–59]. This database comprises 110 and 67 data points for SPT and FS, respectively. In addition, the collected data sample experiments were carried out according to the ASTM and IS standards. For modeling SPT and FS, the independent variables included cement (C), water (W), fine aggregate (FA), RHA, SP, and age. Table 2(a) and (b) illustrates the characterizations of the comprehensive data employed for developing the models. Furthermore, the model is expected to perform optimally due to the extensive distribution of the independent variables. For clear model interpretation, it is essential to understand the interactions between the model’s parameters. This correlation among specific components is termed multi-collinearity. In this study, ensuring a correlation value below 0.8 between pertinent variables will mitigate this issue, positively influencing the model’s construction. The correlation matrix of the dataset is presented in Figure 2(a) and (b).

Table 2

Data descriptive statistics for SPT and FS

Statistics parameters C (kg·m−3) W (kg·m−3) FA (kg·m−3) RHA (kg·m−3) SP (kg·m−3) Age (days) Strength (MPa)
(a) SPT
Minimum 36.80 112.50 482.46 0.00 0.00 7.00 1.39
Mean 360.20 183.12 618.00 46.62 3.34 22.27 3.55
Maximum 550.00 238.00 910.00 165.00 15.00 28.00 8.10
Range 513.20 125.50 427.54 165.00 15.00 21.00 6.71
Standard error 6.46 3.25 11.12 3.45 0.36 0.90 0.16
Standard deviation 67.72 34.07 116.64 36.20 3.59 9.40 1.70
Sample variance 4586.65 1160.52 13604.73 1310.74 12.92 88.27 2.90
Kurtosis 4.83 −0.98 0.55 0.15 4.32 −0.95 0.10
Skewness −0.15 −0.03 1.02 0.63 1.97 −1.03 1.00
(b) FS
Minimum 36.80 112.50 492.58 0.00 0.00 7.00 1.20
Mean 358.18 177.53 596.73 48.19 2.36 22.36 5.76
Maximum 550.00 238.00 750.00 165.00 6.75 28.00 14.10
Range 513.20 125.50 257.42 165.00 6.75 21.00 12.90
Standard error 8.21 4.42 9.47 4.68 0.25 1.15 0.36
Standard deviation 67.22 36.14 77.54 38.33 2.07 9.38 2.97
Sample variance 4517.95 1306.43 6012.74 1469.56 4.29 87.96 8.81
Kurtosis 7.56 −0.84 −0.62 0.28 0.04 −0.89 1.54
Skewness −1.14 0.19 0.52 0.66 0.79 −1.07 1.28
Figure 2 Correlation metrics between input and output of (a) SPT and (b) FS.
Figure 2

Correlation metrics between input and output of (a) SPT and (b) FS.

2.2 Methods

ML methods can be categorized based on their learning type, such as supervised, unsupervised, and reinforcement learning. Regarding the known objective feature in this study, only the supervised approach was employed. Supervised learning is an approach employed in the development of ML models, where a computer algorithm is trained using input data that has been annotated with specific output labels. This section describes several supervised ML approaches, namely SVR, RF, GBR, and GEP. The main distinctness of this study is the development of a stacking model that integrates numerous algorithms for ML, based on a metamodel, to attain the utmost accuracy in prediction. The research methodology flowchart can be seen in Figure 3.

Figure 3 Research methodology flowchart.
Figure 3

Research methodology flowchart.

2.2.1 RF

The RF algorithm was developed as a robust ensemble learning technique based on classification and regression trees. The initial RF-based technique was introduced in 1995, and afterward, an improved version was published by Breiman [60]. The application of RF algorithms has been extensively utilized across various domains, demonstrating outstanding performance, particularly in tasks including classification and regression is a statistical learning theory-based methodology that uses the bootstrap resampling technique to extract multiple samples from the original data [47]. This technique is employed before modeling the decision tree (DT) for each bootstrap sample. Ultimately, the forecasts generated by the different DTs are aggregated and averaged to obtain the ultimate prediction outcome, as shown in Figure 4, which also represents the graphical view of the RF algorithm. The RF algorithm enhances the diversity of DTs by enabling the use of replacement samples and introducing random variations in predictor combinations during the evolution of distinct trees. Further details can be obtained in [61].

Figure 4 Schematic view of RF.
Figure 4

Schematic view of RF.

2.2.2 SVR

Vapnik [62] pioneered the SVM algorithm as a means of addressing classification issues, and it was subsequently extended to include the fixing of regression problems. The SVM algorithm implements the principle of structural risk minimization (SRM), which has been demonstrated to be more effective [63] compared to the usual empirical risk minimization (ERM) principle. The SRM approach aims to reduce a limit on the predicted risk, in contrast to the ERM approach, which focuses on minimizing the error, specifically on the training data. This distinction gives SVM a better baseline for generalization, which is crucial for statistical learning. SVR is a computational technique that extends the capabilities of SVM to address regression and prediction tasks. One of the key features of SVR is its objective to minimize the training error noticed throughout the learning process. Additionally, SVR aims to minimize the generalized error bound to get performance that is applicable beyond the training data. In regression tasks involving SVM, the SVR must employ a cost function C to quantify the empirical risk and then reduce the regression error. Additionally, epsilon insensitive loss ε controls the smoothness, complexity, and accuracy of the approximation function of SVR. Greater C and ε are more complex learning of SVM and vice versa [64]. Figure 5 shows the schematic view of the SVR algorithm. The SVR problem can be formalized using the following equation:

(1) min 1 2 | | ω | | 2 + c ∑ i = 1 m L ( t i , g ( x i ) ) ,

(2) 1 2 | | ω | | 2 + c ∑ i = 1 m L ( t i , g ( x i ) ) s . t . t i − g ( x i ) ≤ δ + ζ i + g ( x i ) − t i ≤ δ + ζ i − ,

where ω is a vector, which determines the slope of the fitted line; C is the regularization coefficient; L(t i , g(x i )) is the insensitive loss function; ζ + i, ζ – i (i 1, 2, …, n) relaxation variable; δ is the coefficient related to the interval band; g(x i ) is a fitted value; and t i is a sample true value.

Figure 5 Schematic view of SVR.
Figure 5

Schematic view of SVR.

2.2.3 GBR

The GBR model was introduced by Friedman in 1999 as an ensemble technique for regression and classification. The training set is chosen randomly, and the gradient boosting approach compares each iteration to the base model. Regression happens faster when the training data percentage is lower, while the GBR model fits smaller data in each iteration. The GBR model’s tuning parameters include n trees and the shrinkage rate. n trees are the number of trees that must be created, whereas the shrinkage rate is commonly known as the learning rate that is applied to each tree throughout the expansion process [65].

The core principle of this algorithm is based on the concept of boosting. The boosting procedure facilitates the transformation of predictions from a “weak” learner throughout the process of additive training. One of the main advantages of GBR algorithms is their ability to mitigate overfitting and optimize computing resources by utilizing an objective function. In addition to enhancing output performance, GBR methods also effectively minimize the specified error function, as stated in a previous study [66].

2.2.4 GEP

The GEP is a branch of GP that was developed by Ferreira [67]. A function set, a terminal set, a fitness function, a set of control parameters, and a terminal condition are the fundamental components of GEP. The first three parts control the search space for the algorithm, while the latter two deal with search speed and quality. Due to GEP’s multigenic architecture, it is possible to build nonlinear, multi-part programs. GEP’s primary functionality is the generation of chromosomes through the use of the Karva language to express any parse tree capable of decoding and expressing the chromosome’s stored data. Thus, chromosomes convert to expression tree branch structures. Karva expression (KE) transformation to expression tree (ET) begins at the initial position and extends through the string. String generation utilizes the inverse translation of ET to KE and a record of nodes from the root to the deeper layer [68]. Numerous solutions are initially created, and their fitness is determined using the basic GEP algorithm. The most appropriate chromosomes undergo operator modification before being passed on to the next generation. The problem’s answer is then illustrated by eTs. By reading ET from top to bottom and then from left to right, it is possible to acquire the mathematical formula [69]. Figure 6 illustrates the sequential stages of the GEP algorithm. The process commences by generating chromosomes of a certain length for each individual in a random manner. The fitness of every individual is evaluated after the chromosomes are expressed as eTs. Only the most suitable individuals are selected for the reproductive process. The iteration incorporates individuals from several generations until an optimal solution is achieved. Genetic operations, including mutation, crossover, and reproduction, are employed to influence the population [70].

Figure 6 Schematic view of GEP.
Figure 6

Schematic view of GEP.

2.2.5 Stacking ensemble

The stacking approach integrates the results from many learners utilizing a multilayer learning structure [71]. Base learners denote the first layer of a two-layer learning architecture, and meta-learners denote the second layer. The primary principle of the stacking model includes initial data training of the base learners. This ultimately generates a new set of data from each base learner output, which is subsequently trained on this new dataset to develop a final prediction model employing the meta-learner second layer. In other words, the ensemble stacking algorithm produces the training dataset, utilizing the base learner as a training set for the meta-learner. The meta-learn model might be susceptible to overfitting in such a case where the base learner training is done as the new training set [72]. The framework of stacking is illustrated in Figure 7.

Figure 7 Framework of stacking ensemble.
Figure 7

Framework of stacking ensemble.

2.2.6 Shapley adaptive exPlanations (SHAP)

The feature relevance of tree-based ensemble learning methods like RF is intrinsic [73]. This importance can be found by counting the number of times a characteristic appears when building the model tree. Analyzing feature importance scores in distinct ways, however, does not provide a comprehensive understanding of the overall impact of features or the positive and negative correlations between features and the corresponding output. Therefore, it is crucial to ascertain the overall importance of features inside the model and their connections to its aims. This is accomplished by SHAP analysis, as recommended by Lundberg and Lee [74]. The SHAP analytical approach is based on principles from game theory. The components of this analysis are treated as agents that influence the goal variables. The analysis provides a comprehensive overview of the gaming engagement of each participant [74]. The outcome is determined by the SHAP analysis process using Shapley values, which are based on well-established models. Global feature relevance in SHAP analysis is calculated by taking the average of the Shapley values for all features in the dataset. The values are presented on a plot after being organized in descending order. Each data point on the figure represents the Shapley value attributed to a particular feature and instance. The Shapley values are represented on the x-axis, while the feature importance is represented on the y-axis. The vertical position on the y-axis corresponds to the influence of the attributes on the target variable, while the color gradient reflects their level of importance. Moreover, SHAP-feature dependence plots clearly illustrate the impact of feature interactions on the target variable using color-coded representations. This approach provides a more extensive range of information compared to traditional partial dependence charts. Additional details regarding the SHAP plots [73].

Lundberg and Lee [74] proposed multiple versions of the SHAP analysis, including DeepSHAP, LinearSHAP, Kernel SHAP, and TreeSHAP. This study employed TreeSHAP, a method that utilizes a linear explanatory model and Shapley values [28]. The initial prediction model has been formulated as

(3) j ( r ′ ) = ∅ o + ∑ q = 1 n ∅ qr ′ q ,

where j, r′, and N denote the explanation model, basic features, and maximum size of the collection, respectively. The symbol ∅ is used to represent feature attribution. The estimation of the attribution of each attribute is performed using the following equations [74]:

(4) ∅ q = ∑ H ⊆ Z { q } | H | ! ( M | H | 1 ) ! M ! [ kc ( H ∪ { q } ) kc ( H ) ] ,

(5) kc ( H ) = E [ k ( c ) | cH ] ,

where H, Z, and E[k(c)|cH] indicate a subset of features, the entire set of inputs, and the desired result of the function on subset S, respectively.

2.3 Model development and performance evaluation

2.3.1 Stacking model development

Before developing the prediction model, it is important to determine the best data split so that the model has a higher generalization capability. Since the established database differs in size, numerous data splits, such as the ratio of 70:30, 75:25, and 80:20 for model training and testing, were investigated in this study. Finally, the dataset was randomly split into training and testing sets for SPT and FS at 80, 20, 70, and 30%, respectively. The precision of the model is significantly influenced by the hyperparameters. Through optimization, the ML model’s performance can be improved by identifying the hyperparameters that work best on the dataset. The grid search technique was utilized to optimize the hyperparameters of the ML model. The grid search method is a methodical strategy that entails extensively exploring a range of hyperparameter variations and training the model numerous times. The configuration that yields the best outcomes throughout several training sessions is referred to as the ideal combination of hyperparameters.

The most effective hyperparameter combinations for predicting SPT in RHAC are as follows: RF model parameters: n estimators = 80, min samples leaf = 2, max depth = 10, min samples split = 3, and max features = 5. In the SVR model, the most effective combination of hyperparameters is degree = 3, gamma = 0.1, C = 10.0, epsilon = 0.3, and tol = 0.001. In the GBR model, the most effective hyperparameter combination is max depth = 3, learning rate = 0.02, and n estimators = 100.

Similarly, for the FS prediction models, the most effective hyperparameter combination in the RF model is n estimators = 100, min samples leaf = 2, min samples split = 4, and max features = 8. In the SVR model, the most effective combination of hyperparameters is degree = 3, gamma = 0.05, C = 20.0, epsilon = 0.15, and tol = 0.001. In the GBR model, the most effective hyperparameter combination is max depth = 3, learning rate = 0.05, and n estimators = 100.

2.3.2 GEP model development

The SPT and FS of RHAC were considered to be functions of the following parameters:

(6) SPT , TS = f ( RHA , C , SP , Age , CA ) .

The GEP models were developed in GeneXproTools 5.0. The parameters, such as population size, were deduced based on a trial-and-error approach. The program’s execution time is determined by the population size, which refers to the number of chromosomes. The population size evaluated for the prediction models was either 50, 100, or 150, considering their number and complexity. The design of various models in the program is contingent upon the size of the head and the number of genes, with the former deciding the intricacy of each component and the latter dictating the number of sub-ETs in the model. In this study, the number of genes was set to 6 for both SPT and TS and two different head sizes: 6 and 8. The linkage functions for both models are multiplications, and the function sets considered for the models are addition, multiplication, subtraction, division, power, square root, and trigonometric functions. The precise parameters employed in the GEP method for both models are given in Table 3.

Table 3

Hyperparameters of the GEP model for SPT and FS

GEP
Hyperparameters Tuned value for SPT Tuned value for FS
Linkage function Multiplication Multiplication
Chromosomes 150 125
Head size 6 8
Genes 6 6
Tail size 7 9
Gene size 20 26
Dc size 7 9

Several statistical metrics, including root mean square error (RMSE), relative root mean square error (RRMSE), mean absolute error (MAE), and correlation coefficient (R), were used to evaluate the performance of the developed models. The range of values for R is bounded between 0 and 1, where a higher R-value indicates a superior model. Conversely, when the values of RMSE, MAE, and RRMSE are lower, it suggests that the model exhibits better performance. Furthermore, the researchers also estimated a performance index (ρ) [75], which served as a composite measure of the model’s effectiveness by incorporating both the RRMSE and R. The variable ρ assumes values within the range of zero to positive infinity, with a lower value indicating a higher level of model performance. Eqs. (7)–(11) representing these metrics are as follows:

(7) RMSE = ∑ i = 0 n ( ye i − yp i ) 2 n ,

(8) RRMSE = 1 | ye ¯ i ¯ | ∑ i = 0 n ( ye i − yp i ) 2 n ,

(9) MAE = ∑ i = 0 n | y e i − yp i | n ,

(10) R = ∑ i = 1 n ( ye i − yp ¯ i ) ( yp i − yp ¯ i ) ∑ i = 1 n ( ye i − yp ¯ i ) 2 ∑ i = 1 n ( yp i − yp ¯ i ) 2 ,

(11) ρ = RRMSE 1 + R ,

where ye i is the experimental value, yp i is the predicted value associated with each of the parameters, ye ¯ i is the average experimental value, yp ¯ i is the average predicted value, and n is the total quantity of data.

3 Results and discussion

3.1 Base-learner and GEP prediction outcomes for SPT

In Figure 8, the experimental and predicted values for SPT for all models are shown juxtaposed with the absolute error and statistical metrics such RMSE, MAE, etc. Figure 8 illustrates the efficacy of the models in precisely predicting the SPT of RHAC. Determining the GBR, RF, SVR, and GEP models’ robustness was executed by analyzing their prediction outcomes and associated errors. During the training phase, the GBR, RF, SVR, and GEP models obtained R values of 0.992, 0.987, 0.939, and 0.918, respectively. During the testing phase, the recorded values were 0.991, 0.981, 0.973, and 0.966, respectively. These results indicate a significant relationship between the experimental and predicted outcomes. The RMSE values for the models during the training phase were 0.21, 0.28, 0.57, and 0.65, respectively. Similarly, during the testing phase, the RMSE values were 0.31, 0.36, 0.62, and 0.47. During the training phase, the MAE values were recorded as 0.17, 0.20, 0.35, and 0.47. In the subsequent testing phase, the MAE values were observed to be 0.25, 0.30, 0.41, and 0.32. The statistics consistently exhibited little variance throughout all datasets.

Figure 8 Base-learner outcomes for SPT.
Figure 8

Base-learner outcomes for SPT.

3.2 Base-learner and GEP prediction outcomes for FS

The predicted and experimental results for FS can be seen in Figure 9. The performance of each ML model is gauged by the values of statistical indicators, as previously discussed. For both the training and testing phases, the GBR, RF, SVR, and GEP models exhibited high R values. Specifically during the training phase, the R-values were 0.987, 0.993, 0.981, and 0.952, respectively, while in the testing phase, they were 0.963, 0.968, 0.973, and 0.948. This demonstrates a strong correlation between the actual and predicted values. In the training phase, the RMSE values for these models were 0.60, 0.40, 0.60, and 0.99, respectively, and the MAE values were 0.46, 0.30, 0.38, and 0.74. For the testing phase, the RMSE values were 0.70, 0.66, 0.66, and 0.80, and the MAE values were 0.55, 0.53, 0.53, and 0.68. All these details are visually represented in Figure 9.

Figure 9 Base-learner outcomes for FS.
Figure 9

Base-learner outcomes for FS.

3.3 Stacking prediction outcomes for SPT and FS

RF and SVR models for SPT and RF and GBR models for FS were chosen as the base learners of the stacking model, while the LR model was used as the meta-learner. The predicted results of the stacking model for SPT on the testing and training set are as follows: RMSE = 0.21, 0.30, MAE = 0.16, 0.23, and R = 0. 991, 0.988, respectively, can be seen in Figure 10. Similarly, Figure 11 illustrates the stacking models’ outcomes for FS on the testing and training set as follows: RMSE = 0.48, 0.72, MAE = 0.34, 0.50, and R = 0.988, 0.964.

Figure 10 Stacking-based outcomes for SPT: (a) scatter, (b) residual, (c) residual histogram, and (d) comparison.
Figure 10

Stacking-based outcomes for SPT: (a) scatter, (b) residual, (c) residual histogram, and (d) comparison.

Figure 11 Stacking-based outcomes for FS: (a) scatter, (b) residual, (c) residual histogram, and (d) comparison.
Figure 11

Stacking-based outcomes for FS: (a) scatter, (b) residual, (c) residual histogram, and (d) comparison.

The relationship between the predicted and actual values of the stacking model for SPT and FS of RHAC is depicted in Figures 10 and 11. In addition, the residuals and residual histograms are depicted in the figures. The stacking model analysis revealed an error range of −0.5 to 0.5 and −1 to 1 for SPT and FS, respectively. The stacking model outperforms each basic learner evaluating metrics that are compared between each of the four base learner models (GBR, RF, SVR, and GEP). This shows that the meta-learner in the stacking model corrects the samples that the base learner inadvertent predicted and increases the model’s prediction accuracy.

3.4 GEP expressions

The effectiveness of the GEP model was assessed by analyzing the outcomes and errors of the predictions. By decoding the results from GEP, an empirical expression for calculating the SPT and FS of RHAC is derived. These expressions encompass the effects of all the independent variables considered in this study. The SPT and FS decoded equations are presented as Eqs. (12) and (13), respectively.

(12) SPT = ( g 1 × g 2 × g 3 × g 4 × g 5 × g 6 ) ,

whereas

g 1 = ( COS ( − 8.56 ) + ( ( − 8.02 / W ) / ( 5.34 − SP ) ) ) ,

g 2 = ( ( TAN ( FA ) + ( RHA + C ) ) × ( ( RHA + SP ) + C ) ) ,

g 3 = ( ( ( − 8.56 × age ) + ( W − FA ) ) + TAN ( ( FA × − 7.41 ) ) ) ,

g 4 = ( ( ( ( − 33.48 − 33.48 ) + FA ) − 2.99 ) / FA ) ,

g 5 = ( − 11.95 × ( ( ( − 28.61 × − 28.61 ) − FA ) + ( 21.12 − FA ) ) ) ,

g 6 = ( ( ( Age + SP + C ) + ( SP 2.15 ) ) / C ) ,

(13) FS = ( G 1 × G 2 × G 3 × G 4 × G 5 × G 6 ) ,

whereas

G 1 = ( 2 × 20.97 + ( ( ( RHA − W ) × ( − 3.95 ) ) + ( FA × ( − 2.41 ) ) ) ) ,

G 2 = ( FA / ( TAN ( TAN ( FA ) ) − POWER ( ( FA + C ) , ( 5.921 + ( − 1.63 ) ) ) ) ) ,

G 3 = ( ( Age + SP ) − ( − 13.21 − TAN ( ( − 6.39 × FA ) ) ) ) ,

G 4 = ( SQRT ( FA ) × ( ( ( − 15.29 × SP ) − ( − 15.29 + ( − 7.13 ) ) ) − ( C − A ) ) ) ,

G 5 = ( C − ( ( SIN ( FA ) − 1.531 ) × ( − 2 × 32.04 ) ) ) FA ,

G 6 = ( ( ( ( RHA × SP ) + ( 8.84 × W ) ) / ( SIN ( W ) − Age ) ) − C ) .

3.5 SHAP analysis

The SHAP value analysis for the models is depicted in Figure 12(a) and (b). The beeswarm plot in SHAP analysis displays color codes and the importance of feature values on the right side. The SHAP analysis, depicted in a beeswarm plot, demonstrates that the results obtained from the RF model are consistent with the experiment results. Figure 12(a) and (b) demonstrates that the W, C, and age and W, SP, and age significantly impact the SPT and FS model’s output, respectively. Lower W and higher C, SP, and age have shown a positive impact on the model output (i.e., SPT and FS)

Figure 12 SHAP analysis beeswarm plot for (a) SPT and (b) FS.
Figure 12

SHAP analysis beeswarm plot for (a) SPT and (b) FS.

The SHAP dependence plots for SPT are shown in Figure 13(a)–(f). Figure 13(a) illustrates the SHAP dependence plot for C and W, showing their direct interaction. The strength tends to decrease when both C and W are high. However, an optimal W combined with a high C results in a positive SHAP value (SPT). Figure 13(b) depicts the W and C, revealing a direct interaction. Elevated values of both W and C reduce the SHAP value. Figure 13(c) presents the interaction between FA and C. FA has a direct relationship with C. An increase in FA combined with an optimal C boosts the strength. Lower feature values of both RHA and FA diminish the strength, while their higher values enhance it, as depicted in Figure 13(d). Figure 13(e) depicts the interaction between SP and RHA. A direct relationship is evident, with an increase in both SP and RHA leading to greater strength. Figure 13(f) depicts the relationship between age and W. A higher age (A) combined with an optimal W increases strength.

Figure 13 Feature dependency of the model for SPT. (a) C, (b) W, (c) FA, (d) RHA, (e) SP, and (f) A.
Figure 13

Feature dependency of the model for SPT. (a) C, (b) W, (c) FA, (d) RHA, (e) SP, and (f) A.

Figure 14(a)–(f) display the SHAP dependence plot for FS. Figure 14(a) depicts the SHAP dependence plots for the C and W features, revealing an inverse interaction between them. Specifically, when C is high and W is low, the SHAP value (TS) decreases. However, the SHAP value turns positive with an optimal and a higher C. Figure 14(b) depicts the features W and C, indicating an inverse interaction. A combination of lower W and higher C results in increased strength. Figure 14(c) depicts diagrams for features FA and C. FA directly interacts with C. An increase in FA combined with an optimal C boosts strength, while higher FA and lower C diminish it. Figure 14(d)–(f) depict the direct interactions of RHA, SP, and age with C, respectively. In each case, higher RHA, SP, and age, when combined with a greater C, enhance the strength.

Figure 14 Feature dependency of the model for FS. (a) C, (b) W, (c) FA, (d) RHA, (e) SP, and (f) A.
Figure 14

Feature dependency of the model for FS. (a) C, (b) W, (c) FA, (d) RHA, (e) SP, and (f) A.

3.6 Parametric analysis

This study performs a parametric analysis in addition to depending on historical patterns to acquire a deeper knowledge of the mechanical properties of RHAC. This analysis aims to verify the GEP expressions and assess the influence of particular input features on the mechanical properties while maintaining other variables constant. To observe the impact on the SPT and FS, one input variable was changed from its minimum to maximum value. The results of a parametric analysis using the constructed GEP models are displayed in Figure 15. It was determined that there is a positive correlation between an increase in C, RHA, SP, and age and an increase in SPT and FS of RHAC. Additionally, it was observed that an increase in W results in a significant decrease in strength. The results of the parametric analysis are consistent with the experimental investigation and reinforce the interpretations of previous studies [76].

Figure 15 Parametric analysis for SPT and FS.
Figure 15

Parametric analysis for SPT and FS.

4 Models’ performances evaluation

The study used an extensive evaluation strategy to evaluate the effectiveness of the developed models. The evaluation used various statistical metrics, such as MAE, RMSE, and R. Tables 4 and 5, Figure 16 demonstrate that all models’ R values for both the training and testing datasets exceed 0.9. Additionally, the MAE and RMSE values for the stacking models are better than base learners and lower than 0.75 MPA. The ρ values of the training and testing datasets for all the models approach zero. Hence, it has been discovered that all the models are acceptable and can be utilized to predict the SPT and FS of RHA concrete. Furthermore, comparing the matrices results of the base learners, stacking, and GEP demonstrated that stacking outperforms GEP for both SPT and TS of RHAC. In addition, the FS stacking results are comparable to the SVR model. Moreover, considering the validation of the GEP expression using parametric analysis, the expressions are applicable and recommended for the routine design of RHAC SPT and FS.

Table 4

Performance evaluation of base learners

Training Testing
Model MAE RMSE R ρ MAE RMSE R ρ
SPT GBR 0.17 0.21 0.992 0.03 0.25 0.31 0.991 0.04
RF 0.20 0.28 0.987 0.04 0.30 0.36 0.981 0.04
SVR 0.35 0.57 0.939 0.08 0.41 0.62 0.947 0.08
GEP 0.47 0.65 0.919 0.09 0.32 0.47 0.966 0.06
FS GBR 0.46 0.60 0.987 0.05 0.55 0.70 0.963 0.06
RF 0.30 0.40 0.993 0.03 0.53 0.66 0.968 0.05
SVR 0.38 0.60 0.981 0.04 0.53 0.66 0.973 0.04
GEP 0.74 0.99 0.952 0.08 0.68 0.80 0.948 0.07
Table 5

Performance evaluation of stacking

Training Testing
Model MAE RMSE R ρ MAE RMSE R ρ
SPT Stacking 0.16 0.21 0.992 0.03 0.23 0.30 0.988 0.04
FS Stacking 0.34 0.48 0.988 0.04 0.50 0.7 0.965 0.06
Figure 16 Radar graph for model’s performance evaluation for SPT and FS.
Figure 16

Radar graph for model’s performance evaluation for SPT and FS.

4.1 External validation conditions

Golbraikh and Tropsha [77] and Roy and Roy [78] both recommended an external validation criterion to evaluate the generalization of the models. Numerous research papers [28,31,64,79] have endorsed this method. The external validation criteria and the equation to determine the model’s robustness are given in Table 6. The stacking and all base learner models have met the external validation criteria. As evidenced in Table 6, k and k′ are close to 1. In addition, the performance index values, especially m and n, register values below 0.1. Moreover, R o 2 and R o ' 2 are either nearing 1 or, in some cases, approximately equal to the R 2 of the respective models.

Table 6

External validation conditions of proposed models

S.No. Equations Condition SPT FS
Stacking GBR RF SVR GEP Stacking GBR RF SVR GEP
1 k = ∑ i = 0 n ( y e i × y p i ) ye i 2 0.85 < k < 1.15 0.994 1.009 1.019 0.994 0.994 0.972 1.006 0.972 1.040 1.047
2 k ′ = ∑ i = 0 n ( ye i × yp i ) yp i 2 0.85 < k′ < 1.15 1.014 1.000 0.994 1.041 1.014 1.038 1.007 1.038 0.987 0.986
3 m = R 2 ‒ R O 2 R 2 m < 0.1 ‒0.019 ‒0.003 0.011 ‒0.113 ‒0.067 ‒0.026 ‒0.073 ‒0.026 0.068 0.049
4 n = R 2 ‒ R O ′ 2 R 2 n < 0.1 0.010 ‒0.017 ‒0.035 ‒0.034 ‒0.035 0.041 ‒0.071 0.041 ‒0.047 ‒0.101
5 R O 2 = 1 ‒ ( ∑ i = 1 n ( yp i ‒ ye i o ) 2 ∑ i = 1 n ( yp i ‒ yp i o ) 2 ) , ye i o = K × ye i R O 2 ≈ 1 0.996 0.986 0.951 0.999 0.996 0.955 0.996 0.955 0.880 0.854
6 R O ′ 2 = 1 ‒ ∑ i = 1 n ( ye i ‒ yp i o ) 2 ∑ i = 1 n ( ye i ‒ ye i o ) 2 , yp i o = K ′ × ye i R O ′ 2 ≈ 1 0.966 0.999 0.996 0.929 0.966 0.892 0.995 0.892 0.990 0.990
7 R m = R 2 ( 1 ‒ √ | R 2 ‒ R O 2 | ) R m > 0.5 0.840 0.922 0.862 0.611 0.699 0.783 0.686 0.783 0.704 0.708

Therefore, the external evaluation results of the models not only meet the needed standards but also demonstrate an outstanding capacity to predict the SPT and FS. These models provide acceptable prediction insights by transcending more connections between independent and dependent variables.

5 Conclusion

This study developed a stacking ensemble learning-based RHAC SPT and FS prediction model to improve the prediction model’s capabilities. Additionally, generalized expressions based on the GEP model were developed for RHAC’s SPT and FS. The models were trained on a comprehensive dataset from the literature comprising 110 and 67 data points for SPT and TS, respectively. Experimental research was conducted to determine the superiority of the stacking ensemble approach and the rationalism of the chosen base learners in the stacking model. Eventually, the importance of the variables in the input was assessed using the SHAP analysis for the RF model and parametric analysis for the GEP models. The conclusions drawn from this study are as follows:

  1. For SPT and FS, the LR model was employed as the second-layer meta-learner, while the RF, SVR, and RF, GBR models were utilized as the first-layer base learners, respectively.

  2. The established stacking model for SPT’s performance evaluation indications for testing and training are as follows: RMSE = 0.21, 0.30, MAE = 0.16, 0.23, and R = 0.99, 0.988, respectively. Similarly, the values for FS are as follows: RMSE = 0.48, 0.72; MAE = 0.34, 0.50; and R = 0.988, 0.964. The stacking model effectively integrates the base learners’ prediction results to enhance the model’s predictive capability.

  3. The GEP model has been trained effectively, showing a substantial correlation between the actual and predicted outcomes with low error values. For the model training, the RMSE, MAE, and R values of the SPT model were 0.65, 0.47, and 0.92, respectively, and the values calculated for the testing were 0.47, 0.32, and 0.97. Similarly, for the FS model, the RMSE, MAE, and R values for the model training were 0.99, 0.0.74, and 0.95, respectively, while for the model testing, values were 0.80, 0.68, and 0.95. The GEP expression effectively incorporated the influence of input variables for predicting RHAC’s SPT and FS. The parametric analysis validates the robustness of the model.

  4. The SHAP analysis investigation for the RF reveals that W, C, W, SP, and age are the most influential variables that impact the SPT and FS of RHAC, respectively. Moreover, the parametric analysis of GEP models identified that C, RHA, SP, and age have a positive correlation, and W has a negative correlation for each respective strength attribute.

The developed ensemble-based learners, staking model, and GEP expressions apply specifically to the given range of datasets. The generalizations of the stacking and GEP models can be further enhanced by using a vast range of datasets and considering the age of RHAC. In addition, different expression techniques such as multi-GEP, hybrid genetic and simulated annealing, and neural network models could be developed to compare the results of stacking and the GEP models.

Acknowledgments

The authors acknowledge the facility’s support with numerical calculations using the supercomputer located in the National Supercomputing Center in JiNan, Big Data Computing Center of Southeast University. This project was financially supported by the Natural Science Foundation of China (grant no. 51378104), the National Science Fund for Distinguished Young Scholars (grant no. 52125802), the “One belt, one road” innovation cooperation project under the policy guidance plan of Jiangsu Province (grant no. BZ2021011), and the Fundamental Research Funds for the Central Universities (2242022k30030, 2242022k30031). The authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through Large Research Project under grant number RGP2/176/45.

  1. Funding information: This project was financially supported by the Natural Science Foundation of China (grant no. 51378104), the National Science Fund for Distinguished Young Scholars (grant no. 52125802), the “One belt, one road” innovation cooperation project under the policy guidance plan of Jiangsu Province (grant no. BZ2021011) and the Fundamental Research Funds for the Central Universities (2242022k30030, 2242022k30031).

  2. Author contributions: Muhammad Waqas Ashraf: conceptualization, methodology, software, data curation, writing – original draft, visualization, investigation, software, validation, writing – review and editing. Adnan Khan: conceptualization, methodology, software, data curation, visualization, investigation, validation, writing – review and editing. Tu Yongming: methodology, visualization, investigation, supervision, validation, writing – review and editing. Wang Chao: visualization, investigation, supervision, validation, writing – review and editing. Nabil Ben Kahla: validation, writing – review and editing. Safi Ullah: software, data curation, Visualization. Jawad Tariq: software, data curation, visualization. All authors have accepted responsibility for the entire content of this manuscript and approved its submission.

  3. Conflict of interest: The authors state no conflict of interest.

  4. Data availability statement: The article contains citations to the dataset from where it is collected. In addition, the Excel macro files of the GEP models are available in the supplementary materials.

References

[1] Jaturapitakkul, C. and B. Roongreung. Cementing material from calcium carbide residue-rice husk ash. Journal of Materials in Civil Engineering, Vol. 15, 2003, pp. 470–475.Search in Google Scholar

[2] Rodríguez de Sensale, G. Strength development of concrete with rice-husk ash. Cement and Concrete Composites, Vol. 28, 2006, pp. 158–160.Search in Google Scholar

[3] Singh, B. Rice husk ash. Waste and Supplementary Cementitious Materials in Concrete, Woodhead Publishing, Elsevier, 2018, pp. 417–460.Search in Google Scholar

[4] Chopra, D. and R. Siddique. Strength, permeability and microstructure of self-compacting concrete containing rice husk ash. Biosystems Engineering, Vol. 130, 2015, pp. 72–80.Search in Google Scholar

[5] Kizhakkumodom Venkatanarayanan, H. and P. R. Rangaraju. Effect of grinding of low-carbon rice husk ash on the microstructure and performance properties of blended cement concrete. Cement and Concrete Composites, Vol. 55, 2015, pp. 348–363.Search in Google Scholar

[6] Zain, M. F. M., M. N. Islam, F. Mahmud, and M. Jamil. Production of rice husk ash for use in concrete as a supplementary cementitious material. Construction and Building Materials, Vol. 25, 2011, pp. 798–805.Search in Google Scholar

[7] Khan, M. N. N., M. Jamil, M. R. Karim, M. F. M. Zain, and A. B. M. A. Kaish. Filler effect of pozzolanic materials on the strength and microstructure development of mortar. KSCE Journal of Civil Engineering, Vol. 21, 2017, pp. 274–284.Search in Google Scholar

[8] Rukzon, S. and P. Chindaprasirt. Mathematical model of strength and porosity of ternary blend Portland rice husk ash and fly ash cement mortar. Computers and Concrete, Vol. 5, 2008, pp. 75–88.Search in Google Scholar

[9] Karthik, S., P. R. M. Rao, and P. O. Awoyera. Strength properties of bamboo and steel reinforced concrete containing manufactured sand and mineral admixtures. Journal of King Saud University - Engineering Sciences, Vol. 29, 2017, pp. 400–406.Search in Google Scholar

[10] Singh, P. To study strength characteristics of concrete with rice husk ash. Indian Journal of Science and Technology, Vol. 9, 2016, pp. 1–5.Search in Google Scholar

[11] Bixapathi, G. and M. Saravanan. Strength and durability of concrete using Rice Husk ash as a partial replacement of cement. Materials Today: Proceedings, Vol. 52, 2022, pp. 1606–1610.Search in Google Scholar

[12] Paris, J. M., J. G. Roessler, C. C. Ferraro, H. D. DeFord, and T. G. Townsend. A review of waste products utilized as supplements to Portland cement in concrete. Journal of Cleaner Production, Vol. 121, 2016, pp. 1–18.Search in Google Scholar

[13] Hariharan, A. R. and A. S. Santhi. G. Mohan Ganesh, Statistical model to predict the mechanical properties of binary and ternary blended concrete using regression analysis. International Journal of Civil Engineering, Vol. 13, 2015, pp. 331–340.Search in Google Scholar

[14] Farooq, F., W. Ahmed, A. Akbar, F. Aslam, and R. Alyousef. Predictive modeling for sustainable high-performance concrete from industrial wastes: A comparison and optimization of models using ensemble learners. Journal of Cleaner Production, Vol. 292, 2021, id. 126032.Search in Google Scholar

[15] Datta, S. D., M. Islam, M.dH. Rahman Sobuz, S. Ahmed, and M. Kar. Artificial intelligence and machine learning applications in the project lifecycle of the construction industry: A comprehensive review. Heliyon, Vol. 10, 2024, id. e26888.Search in Google Scholar

[16] Jalal, F. E., M. Iqbal, W. A. Khan, A. Jamal, and K. Onyelowe. ANN-based swarm intelligence for predicting expansive soil swell pressure and compression strength. Scientific Reports, Vol. 14, 2024, id. 14597.Search in Google Scholar

[17] Awoyera, P. O., M. S. Kirgiz, A. Viloria, and D. Ovallos-Gazabon. Estimating strength properties of geopolymer self-compacting concrete using machine learning techniques. Journal of Materials Research and Technology, Vol. 9, 2020, pp. 9016–9028.Search in Google Scholar

[18] Bui, D.-K., T. Nguyen, J.-S. Chou, H. Nguyen-Xuan, and T. D. Ngo. A modified firefly algorithm-artificial neural network expert system for predicting compressive and tensile strength of high-performance concrete. Construction and Building Materials, Vol. 180, 2018, pp. 320–333.Search in Google Scholar

[19] Yan, K. and C. Shi. Prediction of elastic modulus of normal and high strength concrete by support vector machine. Construction and Building Materials, Vol. 24, 2010, pp. 1479–1485.Search in Google Scholar

[20] Nazari, A. and J. G. Sanjayan. Modelling of compressive strength of geopolymer paste, mortar and concrete by optimized support vector machine. Ceramics International, Vol. 41, 2015, pp. 12164–12177.Search in Google Scholar

[21] Altun, F., Ö. Kişi, and K. Aydin. Predicting the compressive strength of steel fiber added lightweight concrete using neural network. Computational Materials Science, Vol. 42, 2008, pp. 259–265.Search in Google Scholar

[22] Mohammed, A., L. Burhan, K. Ghafor, W. Sarwar, and W. Mahmood. Artificial neural network (ANN), M5P-tree, and regression analyses to predict the early age compression strength of concrete modified with DBC-21 and VK-98 polymers. Neural Computing & Applications, Vol. 33, 2021, pp. 7851–7873.Search in Google Scholar

[23] Ahmed, H. U., A. S. Mohammed, and A. A. Mohammed. Proposing several model techniques including ANN and M5P-tree to predict the compressive strength of geopolymer concretes incorporated with nano-silica. Environmental Science and Pollution Research, Vol. 29, 2022, pp. 71232–71256.Search in Google Scholar

[24] Emad, W., A. Salih Mohammed, R. Kurda, K. Ghafor, L. Cavaleri, S. M. A., Qaidi, et al. Prediction of concrete materials compressive strength using surrogate models. Structures, Vol. 46, 2022, pp. 1243–1267.Search in Google Scholar

[25] Shakr Piro, N., A. Mohammed, S. M. Hamad, and R. Kurda. Electrical resistivity-Compressive strength predictions for normal strength concrete with waste steel slag as a coarse aggregate replacement using various analytical models. Construction and Building Materials, Vol. 327, 2022, id. 127008.Search in Google Scholar

[26] Alves Ribeiro, V. H. and G. Reynoso-Meza. Ensemble learning by means of a multi-objective optimization design approach for dealing with imbalanced data sets. Expert Systems With Applications, Vol. 147, 2020, id. 113232.Search in Google Scholar

[27] Oyeyi, A. G., A. Khan, J. Huyan, W. Zhang, F. M. W. Ni, and S. L. Tighe. Ensemble and evolutionary prediction of layers temperature in conventional and lightweight cellular concrete subbase pavements. International Journal of Pavement Engineering, Vol. 25, 2024, id. 2322525.Search in Google Scholar

[28] Khan, A., J. Huyan, R. Zhang, Y. Zhu, W. Zhang, G. Ying, et al. An ensemble tree-based prediction of Marshall mix design parameters and resilient modulus in stabilized base materials. Construction and Building Materials, Vol. 401, 2023, id. 132833.Search in Google Scholar

[29] Lyngdoh, G. A., M. Zaki, N. M. A. Krishnan, and S. Das. Prediction of concrete strengths enabled by missing data imputation and interpretable machine learning. Cement and Concrete Composites, Vol. 128, 2022, id. 104414.Search in Google Scholar

[30] Pranav, S., M. Lahoti, and M. Gopalarathnam. Concrete compress strength prediction using boosting algorithms, Springer, Singapore, 2023, pp. 307–315.Search in Google Scholar

[31] Karim, R., M. H. Islam, S. D. Datta, and A. Kashem. Synergistic effects of supplementary cementitious materials and compressive strength prediction of concrete using machine learning algorithms with SHAP and PDP analyses. Case Studies in Construction Materials, Vol. 20, 2024, id. e02828.Search in Google Scholar

[32] Kashem, A., R. Karim, S. C. Malo, P. Das, S. D. Datta, and M. Alharthai. Hybrid data-driven approaches to predicting the compressive strength of ultra-high-performance concrete using SHAP and PDP analyses. Case Studies in Construction Materials, Vol. 20, 2024, id. e02991.Search in Google Scholar

[33] Shahmansouri, A. A., H. Akbarzadeh Bengar, and S. Ghanbari. Compressive strength prediction of eco-efficient GGBS-based geopolymer concrete using GEP method. Journal of Building Engineering, Vol. 31, 2020, id. 101326.Search in Google Scholar

[34] Chu, H.-H., M. A. Khan, M. Javed, A. Zafar, M. Ijaz Khan, H. Alabduljabbar, et al. Sustainable use of fly-ash: Use of gene-expression programming (GEP) and multi-expression programming (MEP) for forecasting the compressive strength geopolymer concrete. Ain Shams Engineering Journal, Vol. 12, 2021, pp. 3603–3617.Search in Google Scholar

[35] Kioumarsi, M., H. Dabiri, A. Kandiri, and V. Farhangi. Compressive strength of concrete containing furnace blast slag; optimized machine learning-based models. Cleaner Engineering and Technology, Vol. 13, 2023, id. 100604.Search in Google Scholar

[36] Ray, S., M. M. Rahman, M. Haque, M. W. Hasan, and M. M. Alam. Performance evaluation of SVM and GBM in predicting compressive and splitting tensile strength of concrete prepared with ceramic waste and nylon fiber. Journal of King Saud University, Vol. 35, 2023, pp. 92–100.Search in Google Scholar

[37] Saha, P., P. Debnath, and P. Thomas. Prediction of fresh and hardened properties of self-compacting concrete using support vector regression approach. Neural Computing & Applications, Vol. 32, 2020, pp. 7995–8010.Search in Google Scholar

[38] Naser, A. H., A. H. Badr, S. N. Henedy, K. A. Ostrowski, and H. Imran. Application of Multivariate Adaptive Regression Splines (MARS) approach in prediction of compressive strength of eco-friendly concrete. Case Studies in Construction Materials, Vol. 17, 2022, id. e01262.Search in Google Scholar

[39] Amin, M. N., A. A. A. Al-Naghi, R.-U.-D. Nassar, O. Algassem, S. A. Khan, and A. F. Deifalla. Investigating the rheological characteristics of alkali-activated concrete using contemporary artificial intelligence approaches. Reviews on Advanced Materials Science, Vol. 63, 2024, id. 20240006.Search in Google Scholar

[40] Amin, M. N., S. A. Khan, A. A. Alawi Al-Naghi, E. R. Latifee, N. Alnawmasi, and A. F. Deifalla. Low-carbon embodied alkali-activated materials for sustainable construction: A comparative study of single and ensemble learners. Reviews on Advanced Materials Science, Vol. 63, 2024, id. 20230162.Search in Google Scholar

[41] Ashrafian, A., E. Panahi, S. Salehi, M. Karoglou, and P. G. Asteris. Mapping the strength of agro-ecological lightweight concrete containing oil palm by-product using artificial intelligence techniques. Structures, Vol. 48, 2023, pp. 1209–1229.Search in Google Scholar

[42] Yang, J., P. Jiang, R.-U.-D. Nassar, S. A. Suhail, M. Sufian, and A. F. Deifalla. Experimental investigation and AI prediction modelling of ceramic waste powder concrete – An approach towards sustainable construction. Journal of Materials Research and Technology, Vol. 23, 2023, pp. 3676–3696.Search in Google Scholar

[43] Bušić, R., M. Benšić, I. Miličević, and K. Strukar. Prediction models for the mechanical properties of self-compacting concrete with recycled rubber and silica fume. Materials, Vol. 13, 2020, id. 1821.Search in Google Scholar

[44] Mehta, V. Machine learning approach for predicting concrete compressive, splitting tensile, and flexural strength with waste foundry sand. Journal of Building Engineering, Vol. 70, 2023, id. 106363.Search in Google Scholar

[45] Golafshani, E. M. and A. Behnood. Predicting the mechanical properties of sustainable concrete containing waste foundry sand using multi-objective ANN approach. Construction and Building Materials, Vol. 291, 2021, id. 123314.Search in Google Scholar

[46] Ali, R., M. Muayad, A. S. Mohammed, and P. G. Asteris. Analysis and prediction of the effect of Nanosilica on the compressive strength of concrete with different mix proportions and specimen sizes using various numerical approaches. Structural Concrete, Vol. 24, 2023, pp. 4161–4184.Search in Google Scholar

[47] Kashem, A., R. Karim, P. Das, S. D. Datta, and M. Alharthai. Compressive strength prediction of sustainable concrete incorporating rice husk ash (RHA) using hybrid machine learning algorithms and parametric analyses. Case Studies in Construction Materials, Vol. 20, 2024, id. e03030.Search in Google Scholar

[48] Kakasor Ismael Jaf, D., P. Ismael Abdulrahman, A. Salih Mohammed, R. Kurda, S. M. A. Qaidi, and P. G. Asteris. Machine learning techniques and multi-scale models to evaluate the impact of silicon dioxide (SiO2) and calcium oxide (CaO) in fly ash on the compressive strength of green concrete. Construction and Building Materials, Vol. 400, 2023, id. 132604.Search in Google Scholar

[49] Mohammed, A., R. Kurda, D. J. Armaghani, and M. Hasanipanah. Prediction of compressive strength of concrete modified with fly ash: applications of neuro-swarm and neuro-imperialism models. Computers and Concrete, Vol. 27, 2021, pp. 489–512.Search in Google Scholar

[50] Noaman, M. A., M. R. Karim, and M. N. Islam. Comparative study of pozzolanic and filler effect of rice husk ash on the mechanical properties and microstructure of brick aggregate concrete. Heliyon, Vol. 5, 2019, id. e01926.Search in Google Scholar

[51] Ameri, F., P. Shoaei, N. Bahrami, M. Vaezi, and T. Ozbakkaloglu. Optimum rice husk ash content and bacterial concentration in self-compacting concrete. Construction and Building Materials, Vol. 222, 2019, pp. 796–813.Search in Google Scholar

[52] Rajashekhar Reddy, K., M. Harihanandh, and K. Murali. Strength performance of high-grade concrete using rice husk ash (RHA) as cement replacement material. Materials Today: Proceedings, Vol. 46, 2021, pp. 8822–8825.Search in Google Scholar

[53] Zareei, S. A., F. Ameri, F. Dorostkar, and M. Ahmadi. Rice husk ash as a partial replacement of cement in high strength concrete containing micro silica: Evaluating durability and mechanical properties. Case Studies in Construction Materials, Vol. 7, 2017, pp. 73–81.Search in Google Scholar

[54] Olutoge, F. A. and P. A. Adesina. Effects of rice husk ash prepared from charcoal-powered incinerator on the strength and durability properties of concrete. Construction and Building Materials, Vol. 196, 2019, pp. 386–394.Search in Google Scholar

[55] Krishna, N. K., S. Sandeep, and K. M. Mini. Study on concrete with partial replacement of cement by rice husk ash. IOP Conference Series: Materials Science and Engineering, Vol. 149, 2016, id. 012109.Search in Google Scholar

[56] Amin, M. and B. A. Abdelsalam. Efficiency of rice husk ash and fly ash as reactivity materials in sustainable concrete. Sustainable Environment Research, Vol. 29, 2019, id. 30.Search in Google Scholar

[57] Ganesan, K., K. Rajagopal, and K. Thangavel. Rice husk ash blended cement: Assessment of optimal level of replacement for strength and permeability properties of concrete. Construction and Building Materials, Vol. 22, 2008, pp. 1675–1683.Search in Google Scholar

[58] Gautam, A., R. Batra, and N. Singh. A study on use of rice husk ash in concrete. Engineering Heritage Journal, Vol. 3, 2019, pp. 01–04.Search in Google Scholar

[59] Ahmed, S. O. Rice husk ash as a partial replacement of cement in high strength concrete containing fly ash. International Journal of Current Engineering and Technology, Vol. 11, 2021, pp. 195–200.Search in Google Scholar

[60] Breiman, L. Random forests. Machine Learning, Vol. 45, 2001, pp. 5–32.Search in Google Scholar

[61] Milad, A., S. H. Hussein, A. R. Khekan, M. Rashid, H. Al-Msari, and T. H. Tran. Development of ensemble machine learning approaches for designing fiber-reinforced polymer composite strain prediction model. Engineering Computation, Vol. 38, 2022, pp. 3625–3637.Search in Google Scholar

[62] Vapnik, V. N. The nature of statistical learning theory, Springer, New York, 2000.Search in Google Scholar

[63] Cortes, C. and V. Vapnik. Support-vector networks. Machine Learning, Vol. 20, 1995, pp. 273–297.Search in Google Scholar

[64] Zhang, W., A. Khan, J. Huyan, J. Zhong, T. Peng, and H. Cheng. Predicting marshall parameters of flexible pavement using support vector machine and genetic programming. Construction and Building Materials, Vol. 306, 2021, id. 124924.Search in Google Scholar

[65] Kaloop, M. R., D. Kumar, P. Samui, J. W. Hu, and D. Kim. Compressive strength prediction of high-performance concrete using gradient tree boosting machine. Construction and Building Materials, Vol. 264, 2020, id. 120198.Search in Google Scholar

[66] Gong, M., Y. Bai, J. Qin, J. Wang, P. Yang, and S. Wang. Gradient boosting machine for predicting return temperature of district heating system: A case study for residential buildings in Tianjin. Journal of Building Engineering, Vol. 27, 2020, id. 100950.Search in Google Scholar

[67] Ferreira, C. Gene Expression Programming: a New Adaptive Algorithm for Solving Problems, Complex Systems, Vol. 13, No. 2, 2001, pp. 87–129.Search in Google Scholar

[68] Hossein Alavi, A. and A. Hossein Gandomi. A robust data mining approach for formulation of geotechnical engineering systems. Engineering Computations, Vol. 28, 2011, pp. 242–274.Search in Google Scholar

[69] Shah, H. A., S. K. U. Rehman, M. F. Javed, and Y. Iftikhar. Prediction of compressive and splitting tensile strength of concrete with fly ash by using gene expression programming. Structural Concrete, Vol. 23, 2022, pp. 2435–2449.Search in Google Scholar

[70] Iqbal, M. F., Q. Liu, I. Azim, X. Zhu, J. Yang, M. F. Javed, et al. Prediction of mechanical properties of green concrete incorporating waste foundry sand based on gene expression programming. Journal of Hazardous Materials, Vol. 384, 2020, id. 121322.Search in Google Scholar

[71] Wu, W., Y. Xia, and W. Jin. Predicting bus passenger flow and prioritizing influential factors using multi-source data: scaled stacking gradient boosting decision trees. IEEE Transactions on Intelligent Transportation Systems, Vol. 22, 2021, pp. 2510–2523.Search in Google Scholar

[72] Zhou, Z.-H. Ensemble Methods, Chapman and Hall/CRC, Boca Raton, Florida, USA, 2012.Search in Google Scholar

[73] Ekanayake, I. U., D. P. P. Meddage, and U. Rathnayake. A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP). Case Studies in Construction Materials, Vol. 16, 2022, id. e01059.Search in Google Scholar

[74] Lundberg, S. M., S.-I. Lee. A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17). Curran Associates Inc., Red Hook, NY, USA, 2017, pp. 4768–4777.Search in Google Scholar

[75] Gandomi, A. H. and D. A. Roke. Assessment of artificial neural network and genetic programming as predictive tools. Advances in Engineering Software, Vol. 88, 2015, pp. 63–72.Search in Google Scholar

[76] Al-Alwan, A. A. K., M. Al-Bazoon, F. I. Mussa, H. A. Alalwan, M. Hatem Shadhar, M. M. Mohammed, et al. The impact of using rice husk ash as a replacement material in concrete: An experimental study. Journal of King Saud University – Engineering Sciences, 2022.Search in Google Scholar

[77] Golbraikh, A. and A. Tropsha. Beware of q2! Journal of Molecular Graphics & Modelling, Vol. 20, 2002, pp. 269–276.Search in Google Scholar

[78] Roy, P. P. and K. Roy. On some aspects of variable selection for partial least squares regression models. QSAR & Combinatorial Science, Vol. 27, 2008, pp. 302–313.Search in Google Scholar

[79] Iftikhar, B., S. C. Alih, M. Vafaei, M. A. Elkotb, M. Shutaywi, M. F. Javed, et al. Predictive modeling of compressive strength of sustainable rice husk ash concrete: Ensemble learner optimization and comparison. Journal of Cleaner Production, Vol. 348, 2022, id. 131285.Search in Google Scholar
Received: 2024-05-15
Revised: 2024-07-02
Accepted: 2024-07-14
Published Online: 2024-08-26

© 2024 the author(s), published by De Gruyter

This work is licensed under the Creative Commons Attribution 4.0 International License.

Articles in the same Issue

  1. Review Articles
  2. Effect of superplasticizer in geopolymer and alkali-activated cement mortar/concrete: A review
  3. Experimenting the influence of corncob ash on the mechanical strength of slag-based geopolymer concrete
  4. Powder metallurgy processing of high entropy alloys: Bibliometric analysis and systematic review
  5. Exploring the potential of agricultural waste as an additive in ultra-high-performance concrete for sustainable construction: A comprehensive review
  6. A review on partial substitution of nanosilica in concrete
  7. Foam concrete for lightweight construction applications: A comprehensive review of the research development and material characteristics
  8. Modification of PEEK for implants: Strategies to improve mechanical, antibacterial, and osteogenic properties
  9. Interfacing the IoT in composite manufacturing: An overview
  10. Advances in processing and ablation properties of carbon fiber reinforced ultra-high temperature ceramic composites
  11. Advancing auxetic materials: Emerging development and innovative applications
  12. Revolutionizing energy harvesting: A comprehensive review of thermoelectric devices
  13. Exploring polyetheretherketone in dental implants and abutments: A focus on biomechanics and finite element methods
  14. Smart technologies and textiles and their potential use and application in the care and support of elderly individuals: A systematic review
  15. Reinforcement mechanisms and current research status of silicon carbide whisker-reinforced composites: A comprehensive review
  16. Innovative eco-friendly bio-composites: A comprehensive review of the fabrication, characterization, and applications
  17. Review on geopolymer concrete incorporating Alccofine-1203
  18. Advancements in surface treatments for aluminum alloys in sports equipment
  19. Ionic liquid-modified carbon-based fillers and their polymer composites – A Raman spectroscopy analysis
  20. Emerging boron nitride nanosheets: A review on synthesis, corrosion resistance coatings, and their impacts on the environment and health
  21. Mechanism, models, and influence of heterogeneous factors of the microarc oxidation process: A comprehensive review
  22. Synthesizing sustainable construction paradigms: A comprehensive review and bibliometric analysis of granite waste powder utilization and moisture correction in concrete
  23. 10.1515/rams-2025-0086
  24. Research Articles
  25. Coverage and reliability improvement of copper metallization layer in through hole at BGA area during load board manufacture
  26. Study on dynamic response of cushion layer-reinforced concrete slab under rockfall impact based on smoothed particle hydrodynamics and finite-element method coupling
  27. Study on the mechanical properties and microstructure of recycled brick aggregate concrete with waste fiber
  28. Multiscale characterization of the UV aging resistance and mechanism of light stabilizer-modified asphalt
  29. Characterization of sandwich materials – Nomex-Aramid carbon fiber performances under mechanical loadings: Nonlinear FE and convergence studies
  30. Effect of grain boundary segregation and oxygen vacancy annihilation on aging resistance of cobalt oxide-doped 3Y-TZP ceramics for biomedical applications
  31. Mechanical damage mechanism investigation on CFRP strengthened recycled red brick concrete
  32. Finite element analysis of deterioration of axial compression behavior of corroded steel-reinforced concrete middle-length columns
  33. Grinding force model for ultrasonic assisted grinding of γ-TiAl intermetallic compounds and experimental validation
  34. Enhancement of hardness and wear strength of pure Cu and Cu–TiO2 composites via a friction stir process while maintaining electrical resistivity
  35. Effect of sand–precursor ratio on mechanical properties and durability of geopolymer mortar with manufactured sand
  36. Research on the strength prediction for pervious concrete based on design porosity and water-to-cement ratio
  37. Development of a new damping ratio prediction model for recycled aggregate concrete: Incorporating modified admixtures and carbonation effects
  38. Exploring the viability of AI-aided genetic algorithms in estimating the crack repair rate of self-healing concrete
  39. Modification of methacrylate bone cement with eugenol – A new material with antibacterial properties
  40. Numerical investigations on constitutive model parameters of HRB400 and HTRB600 steel bars based on tensile and fatigue tests
  41. Research progress on Fe3+-activated near-infrared phosphor
  42. Discrete element simulation study on effects of grain preferred orientation on micro-cracking and macro-mechanical behavior of crystalline rocks
  43. Ultrasonic resonance evaluation method for deep interfacial debonding defects of multilayer adhesive bonded materials
  44. Effect of impurity components in titanium gypsum on the setting time and mechanical properties of gypsum-slag cementitious materials
  45. Bending energy absorption performance of composite fender piles with different winding angles
  46. Theoretical study of the effect of orientations and fibre volume on the thermal insulation capability of reinforced polymer composites
  47. Synthesis and characterization of a novel ternary magnetic composite for the enhanced adsorption capacity to remove organic dyes
  48. Couple effects of multi-impact damage and CAI capability on NCF composites
  49. Mechanical testing and engineering applicability analysis of SAP concrete used in buffer layer design for tunnels in active fault zones
  50. Investigating the rheological characteristics of alkali-activated concrete using contemporary artificial intelligence approaches
  51. Integrating micro- and nanowaste glass with waste foundry sand in ultra-high-performance concrete to enhance material performance and sustainability
  52. Effect of water immersion on shear strength of epoxy adhesive filled with graphene nanoplatelets
  53. Impact of carbon content on the phase structure and mechanical properties of TiBCN coatings via direct current magnetron sputtering
  54. Investigating the anti-aging properties of asphalt modified with polyphosphoric acid and tire pyrolysis oil
  55. Biomedical and therapeutic potential of marine-derived Pseudomonas sp. strain AHG22 exopolysaccharide: A novel bioactive microbial metabolite
  56. Effect of basalt fiber length on the behavior of natural hydraulic lime-based mortars
  57. Optimizing the performance of TPCB/SCA composite-modified asphalt using improved response surface methodology
  58. Compressive strength of waste-derived cementitious composites using machine learning
  59. Melting phenomenon of thermally stratified MHD Powell–Eyring nanofluid with variable porosity past a stretching Riga plate
  60. Development and characterization of a coaxial strain-sensing cable integrated steel strand for wide-range stress monitoring
  61. Compressive and tensile strength estimation of sustainable geopolymer concrete using contemporary boosting ensemble techniques
  62. Customized 3D printed porous titanium scaffolds with nanotubes loading antibacterial drugs for bone tissue engineering
  63. Facile design of PTFE-kaolin-based ternary nanocomposite as a hydrophobic and high corrosion-barrier coating
  64. Effects of C and heat treatment on microstructure, mechanical, and tribo-corrosion properties of VAlTiMoSi high-entropy alloy coating
  65. Study on the damage mechanism and evolution model of preloaded sandstone subjected to freezing–thawing action based on the NMR technology
  66. Promoting low carbon construction using alkali-activated materials: A modeling study for strength prediction and feature interaction
  67. Entropy generation analysis of MHD convection flow of hybrid nanofluid in a wavy enclosure with heat generation and thermal radiation
  68. Friction stir welding of dissimilar Al–Mg alloys for aerospace applications: Prospects and future potential
  69. Fe nanoparticle-functionalized ordered mesoporous carbon with tailored mesostructures and their applications in magnetic removal of Ag(i)
  70. Study on physical and mechanical properties of complex-phase conductive fiber cementitious materials
  71. Evaluating the strength loss and the effectiveness of glass and eggshell powder for cement mortar under acidic conditions
  72. Effect of fly ash on properties and hydration of calcium sulphoaluminate cement-based materials with high water content
  73. Analyzing the efficacy of waste marble and glass powder for the compressive strength of self-compacting concrete using machine learning strategies
  74. Experimental study on municipal solid waste incineration ash micro-powder as concrete admixture
  75. Parameter optimization for ultrasonic-assisted grinding of γ-TiAl intermetallics: A gray relational analysis approach with surface integrity evaluation
  76. Producing sustainable binding materials using marble waste blended with fly ash and rice husk ash for building materials
  77. Effect of steam curing system on compressive strength of recycled aggregate concrete
  78. A sawtooth constitutive model describing strain hardening and multiple cracking of ECC under uniaxial tension
  79. Predicting mechanical properties of sustainable green concrete using novel machine learning: Stacking and gene expression programming
  80. Toward sustainability: Integrating experimental study and data-driven modeling for eco-friendly paver blocks containing plastic waste
  81. A numerical analysis of the rotational flow of a hybrid nanofluid past a unidirectional extending surface with velocity and thermal slip conditions
  82. A magnetohydrodynamic flow of a water-based hybrid nanofluid past a convectively heated rotating disk surface: A passive control of nanoparticles
  83. Prediction of flexural strength of concrete with eggshell and glass powders: Advanced cutting-edge approach for sustainable materials
  84. Efficacy of sustainable cementitious materials on concrete porosity for enhancing the durability of building materials
  85. Phase and microstructural characterization of swat soapstone (Mg3Si4O10(OH)2)
  86. Effect of waste crab shell powder on matrix asphalt
  87. Improving effect and mechanism on service performance of asphalt binder modified by PW polymer
  88. Influence of pH on the synthesis of carbon spheres and the application of carbon sphere-based solid catalysts in esterification
  89. Experimenting the compressive performance of low-carbon alkali-activated materials using advanced modeling techniques
  90. Thermogravimetric (TG/DTG) characterization of cold-pressed oil blends and Saccharomyces cerevisiae-based microcapsules obtained with them
  91. Investigation of temperature effect on thermo-mechanical property of carbon fiber/PEEK composites
  92. Computational approaches for structural analysis of wood specimens
  93. Integrated structure–function design of 3D-printed porous polydimethylsiloxane for superhydrophobic engineering
  94. Exploring the impact of seashell powder and nano-silica on ultra-high-performance self-curing concrete: Insights into mechanical strength, durability, and high-temperature resilience
  95. Axial compression damage constitutive model and damage characteristics of fly ash/silica fume modified magnesium phosphate cement after being treated at different temperatures
  96. Integrating testing and modeling methods to examine the feasibility of blended waste materials for the compressive strength of rubberized mortar
  97. Special Issue on 3D and 4D Printing of Advanced Functional Materials - Part II
  98. Energy absorption of gradient triply periodic minimal surface structure manufactured by stereolithography
  99. Marine polymers in tissue bioprinting: Current achievements and challenges
  100. Quick insight into the dynamic dimensions of 4D printing in polymeric composite mechanics
  101. Recent advances in 4D printing of hydrogels
  102. Mechanically sustainable and primary recycled thermo-responsive ABS–PLA polymer composites for 4D printing applications: Fabrication and studies
  103. Special Issue on Materials and Technologies for Low-carbon Biomass Processing and Upgrading
  104. Low-carbon embodied alkali-activated materials for sustainable construction: A comparative study of single and ensemble learners
  105. Study on bending performance of prefabricated glulam-cross laminated timber composite floor
  106. Special Issue on Recent Advancement in Low-carbon Cement-based Materials - Part I
  107. Supplementary cementitious materials-based concrete porosity estimation using modeling approaches: A comparative study of GEP and MEP
  108. Modeling the strength parameters of agro waste-derived geopolymer concrete using advanced machine intelligence techniques
  109. Promoting the sustainable construction: A scientometric review on the utilization of waste glass in concrete
  110. Incorporating geranium plant waste into ultra-high performance concrete prepared with crumb rubber as fine aggregate in the presence of polypropylene fibers
  111. Investigation of nano-basic oxygen furnace slag and nano-banded iron formation on properties of high-performance geopolymer concrete
  112. Effect of incorporating ultrafine palm oil fuel ash on the resistance to corrosion of steel bars embedded in high-strength green concrete
  113. Influence of nanomaterials on properties and durability of ultra-high-performance geopolymer concrete
  114. Influence of palm oil ash and palm oil clinker on the properties of lightweight concrete
https://doi.org/10.1515/rams-2024-0050
Keywords for this article
rice husk ash; stacking; gene expression programming; tensile and flexural strength; parametric analysis; SHAP analysis
Creative Commons
BY 4.0

Articles in the same Issue

  1. Review Articles
  2. Effect of superplasticizer in geopolymer and alkali-activated cement mortar/concrete: A review
  3. Experimenting the influence of corncob ash on the mechanical strength of slag-based geopolymer concrete
  4. Powder metallurgy processing of high entropy alloys: Bibliometric analysis and systematic review
  5. Exploring the potential of agricultural waste as an additive in ultra-high-performance concrete for sustainable construction: A comprehensive review
  6. A review on partial substitution of nanosilica in concrete
  7. Foam concrete for lightweight construction applications: A comprehensive review of the research development and material characteristics
  8. Modification of PEEK for implants: Strategies to improve mechanical, antibacterial, and osteogenic properties
  9. Interfacing the IoT in composite manufacturing: An overview
  10. Advances in processing and ablation properties of carbon fiber reinforced ultra-high temperature ceramic composites
  11. Advancing auxetic materials: Emerging development and innovative applications
  12. Revolutionizing energy harvesting: A comprehensive review of thermoelectric devices
  13. Exploring polyetheretherketone in dental implants and abutments: A focus on biomechanics and finite element methods
  14. Smart technologies and textiles and their potential use and application in the care and support of elderly individuals: A systematic review
  15. Reinforcement mechanisms and current research status of silicon carbide whisker-reinforced composites: A comprehensive review
  16. Innovative eco-friendly bio-composites: A comprehensive review of the fabrication, characterization, and applications
  17. Review on geopolymer concrete incorporating Alccofine-1203
  18. Advancements in surface treatments for aluminum alloys in sports equipment
  19. Ionic liquid-modified carbon-based fillers and their polymer composites – A Raman spectroscopy analysis
  20. Emerging boron nitride nanosheets: A review on synthesis, corrosion resistance coatings, and their impacts on the environment and health
  21. Mechanism, models, and influence of heterogeneous factors of the microarc oxidation process: A comprehensive review
  22. Synthesizing sustainable construction paradigms: A comprehensive review and bibliometric analysis of granite waste powder utilization and moisture correction in concrete
  23. 10.1515/rams-2025-0086
  24. Research Articles
  25. Coverage and reliability improvement of copper metallization layer in through hole at BGA area during load board manufacture
  26. Study on dynamic response of cushion layer-reinforced concrete slab under rockfall impact based on smoothed particle hydrodynamics and finite-element method coupling
  27. Study on the mechanical properties and microstructure of recycled brick aggregate concrete with waste fiber
  28. Multiscale characterization of the UV aging resistance and mechanism of light stabilizer-modified asphalt
  29. Characterization of sandwich materials – Nomex-Aramid carbon fiber performances under mechanical loadings: Nonlinear FE and convergence studies
  30. Effect of grain boundary segregation and oxygen vacancy annihilation on aging resistance of cobalt oxide-doped 3Y-TZP ceramics for biomedical applications
  31. Mechanical damage mechanism investigation on CFRP strengthened recycled red brick concrete
  32. Finite element analysis of deterioration of axial compression behavior of corroded steel-reinforced concrete middle-length columns
  33. Grinding force model for ultrasonic assisted grinding of γ-TiAl intermetallic compounds and experimental validation
  34. Enhancement of hardness and wear strength of pure Cu and Cu–TiO2 composites via a friction stir process while maintaining electrical resistivity
  35. Effect of sand–precursor ratio on mechanical properties and durability of geopolymer mortar with manufactured sand
  36. Research on the strength prediction for pervious concrete based on design porosity and water-to-cement ratio
  37. Development of a new damping ratio prediction model for recycled aggregate concrete: Incorporating modified admixtures and carbonation effects
  38. Exploring the viability of AI-aided genetic algorithms in estimating the crack repair rate of self-healing concrete
  39. Modification of methacrylate bone cement with eugenol – A new material with antibacterial properties
  40. Numerical investigations on constitutive model parameters of HRB400 and HTRB600 steel bars based on tensile and fatigue tests
  41. Research progress on Fe3+-activated near-infrared phosphor
  42. Discrete element simulation study on effects of grain preferred orientation on micro-cracking and macro-mechanical behavior of crystalline rocks
  43. Ultrasonic resonance evaluation method for deep interfacial debonding defects of multilayer adhesive bonded materials
  44. Effect of impurity components in titanium gypsum on the setting time and mechanical properties of gypsum-slag cementitious materials
  45. Bending energy absorption performance of composite fender piles with different winding angles
  46. Theoretical study of the effect of orientations and fibre volume on the thermal insulation capability of reinforced polymer composites
  47. Synthesis and characterization of a novel ternary magnetic composite for the enhanced adsorption capacity to remove organic dyes
  48. Couple effects of multi-impact damage and CAI capability on NCF composites
  49. Mechanical testing and engineering applicability analysis of SAP concrete used in buffer layer design for tunnels in active fault zones
  50. Investigating the rheological characteristics of alkali-activated concrete using contemporary artificial intelligence approaches
  51. Integrating micro- and nanowaste glass with waste foundry sand in ultra-high-performance concrete to enhance material performance and sustainability
  52. Effect of water immersion on shear strength of epoxy adhesive filled with graphene nanoplatelets
  53. Impact of carbon content on the phase structure and mechanical properties of TiBCN coatings via direct current magnetron sputtering
  54. Investigating the anti-aging properties of asphalt modified with polyphosphoric acid and tire pyrolysis oil
  55. Biomedical and therapeutic potential of marine-derived Pseudomonas sp. strain AHG22 exopolysaccharide: A novel bioactive microbial metabolite
  56. Effect of basalt fiber length on the behavior of natural hydraulic lime-based mortars
  57. Optimizing the performance of TPCB/SCA composite-modified asphalt using improved response surface methodology
  58. Compressive strength of waste-derived cementitious composites using machine learning
  59. Melting phenomenon of thermally stratified MHD Powell–Eyring nanofluid with variable porosity past a stretching Riga plate
  60. Development and characterization of a coaxial strain-sensing cable integrated steel strand for wide-range stress monitoring
  61. Compressive and tensile strength estimation of sustainable geopolymer concrete using contemporary boosting ensemble techniques
  62. Customized 3D printed porous titanium scaffolds with nanotubes loading antibacterial drugs for bone tissue engineering
  63. Facile design of PTFE-kaolin-based ternary nanocomposite as a hydrophobic and high corrosion-barrier coating
  64. Effects of C and heat treatment on microstructure, mechanical, and tribo-corrosion properties of VAlTiMoSi high-entropy alloy coating
  65. Study on the damage mechanism and evolution model of preloaded sandstone subjected to freezing–thawing action based on the NMR technology
  66. Promoting low carbon construction using alkali-activated materials: A modeling study for strength prediction and feature interaction
  67. Entropy generation analysis of MHD convection flow of hybrid nanofluid in a wavy enclosure with heat generation and thermal radiation
  68. Friction stir welding of dissimilar Al–Mg alloys for aerospace applications: Prospects and future potential
  69. Fe nanoparticle-functionalized ordered mesoporous carbon with tailored mesostructures and their applications in magnetic removal of Ag(i)
  70. Study on physical and mechanical properties of complex-phase conductive fiber cementitious materials
  71. Evaluating the strength loss and the effectiveness of glass and eggshell powder for cement mortar under acidic conditions
  72. Effect of fly ash on properties and hydration of calcium sulphoaluminate cement-based materials with high water content
  73. Analyzing the efficacy of waste marble and glass powder for the compressive strength of self-compacting concrete using machine learning strategies
  74. Experimental study on municipal solid waste incineration ash micro-powder as concrete admixture
  75. Parameter optimization for ultrasonic-assisted grinding of γ-TiAl intermetallics: A gray relational analysis approach with surface integrity evaluation
  76. Producing sustainable binding materials using marble waste blended with fly ash and rice husk ash for building materials
  77. Effect of steam curing system on compressive strength of recycled aggregate concrete
  78. A sawtooth constitutive model describing strain hardening and multiple cracking of ECC under uniaxial tension
  79. Predicting mechanical properties of sustainable green concrete using novel machine learning: Stacking and gene expression programming
  80. Toward sustainability: Integrating experimental study and data-driven modeling for eco-friendly paver blocks containing plastic waste
  81. A numerical analysis of the rotational flow of a hybrid nanofluid past a unidirectional extending surface with velocity and thermal slip conditions
  82. A magnetohydrodynamic flow of a water-based hybrid nanofluid past a convectively heated rotating disk surface: A passive control of nanoparticles
  83. Prediction of flexural strength of concrete with eggshell and glass powders: Advanced cutting-edge approach for sustainable materials
  84. Efficacy of sustainable cementitious materials on concrete porosity for enhancing the durability of building materials
  85. Phase and microstructural characterization of swat soapstone (Mg3Si4O10(OH)2)
  86. Effect of waste crab shell powder on matrix asphalt
  87. Improving effect and mechanism on service performance of asphalt binder modified by PW polymer
  88. Influence of pH on the synthesis of carbon spheres and the application of carbon sphere-based solid catalysts in esterification
  89. Experimenting the compressive performance of low-carbon alkali-activated materials using advanced modeling techniques
  90. Thermogravimetric (TG/DTG) characterization of cold-pressed oil blends and Saccharomyces cerevisiae-based microcapsules obtained with them
  91. Investigation of temperature effect on thermo-mechanical property of carbon fiber/PEEK composites
  92. Computational approaches for structural analysis of wood specimens
  93. Integrated structure–function design of 3D-printed porous polydimethylsiloxane for superhydrophobic engineering
  94. Exploring the impact of seashell powder and nano-silica on ultra-high-performance self-curing concrete: Insights into mechanical strength, durability, and high-temperature resilience
  95. Axial compression damage constitutive model and damage characteristics of fly ash/silica fume modified magnesium phosphate cement after being treated at different temperatures
  96. Integrating testing and modeling methods to examine the feasibility of blended waste materials for the compressive strength of rubberized mortar
  97. Special Issue on 3D and 4D Printing of Advanced Functional Materials - Part II
  98. Energy absorption of gradient triply periodic minimal surface structure manufactured by stereolithography
  99. Marine polymers in tissue bioprinting: Current achievements and challenges
  100. Quick insight into the dynamic dimensions of 4D printing in polymeric composite mechanics
  101. Recent advances in 4D printing of hydrogels
  102. Mechanically sustainable and primary recycled thermo-responsive ABS–PLA polymer composites for 4D printing applications: Fabrication and studies
  103. Special Issue on Materials and Technologies for Low-carbon Biomass Processing and Upgrading
  104. Low-carbon embodied alkali-activated materials for sustainable construction: A comparative study of single and ensemble learners
  105. Study on bending performance of prefabricated glulam-cross laminated timber composite floor
  106. Special Issue on Recent Advancement in Low-carbon Cement-based Materials - Part I
  107. Supplementary cementitious materials-based concrete porosity estimation using modeling approaches: A comparative study of GEP and MEP
  108. Modeling the strength parameters of agro waste-derived geopolymer concrete using advanced machine intelligence techniques
  109. Promoting the sustainable construction: A scientometric review on the utilization of waste glass in concrete
  110. Incorporating geranium plant waste into ultra-high performance concrete prepared with crumb rubber as fine aggregate in the presence of polypropylene fibers
  111. Investigation of nano-basic oxygen furnace slag and nano-banded iron formation on properties of high-performance geopolymer concrete
  112. Effect of incorporating ultrafine palm oil fuel ash on the resistance to corrosion of steel bars embedded in high-strength green concrete
  113. Influence of nanomaterials on properties and durability of ultra-high-performance geopolymer concrete
  114. Influence of palm oil ash and palm oil clinker on the properties of lightweight concrete
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 10.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/rams-2024-0050/html
Scroll to top button