Optimizing Sustainable Self-Compacting Mortar Properties Using Natural Pozzolan and Glass Powder as Cementitious Materials: An Artificial Neural Network Approach

Optimizing Sustainable Self-Compacting Mortar Properties Using Natural Pozzolan and Glass Powder as Cementitious Materials: An Artificial Neural Network Approach | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Optimizing Sustainable Self-Compacting Mortar Properties Using Natural Pozzolan and Glass Powder as Cementitious Materials: An Artificial Neural Network Approach Younes Ouldkhaoua, Mohamed Sahraoui, Zin-El Abiddine Laidani, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6331374/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract This study aimed to investigate the use of natural pozzolana (PZ) and glass powder (GP) as binary and ternary cementitious materials to improve the sustainability of self-compacting mortar (SCM) for construction purposes. The research assessed PZ and GP's impact on SCM's flowability, mechanical strength, and durability. To do this, artificial neural networks (ANNs) were utilised to model and forecast the behaviour of the materials, offering a comprehensive understanding of how these novel composite materials affect the properties of the mortars. The findings indicated that the inclusion of GP boosted the workability and filling capacity of the mortars. In contrast, PZ improved compressive strength, with both materials exhibiting a synergistic impact when combined in a ternary blend. This combination also resulted in decreased water absorption and porosity; hence, it improved the durability of the SCM. The ANN models accurately forecasted the behaviour of the mortars and their influence on the parameters of the mixtures. The study found that using sustainable cementitious additives instead of PZ and GP improves the quality and performance of mortars while also helping the environment by lowering energy use and CO 2 emissions. Self-Compacting Mortar Pozzolan Glass Powder Artificial Neural Networks Sustainability in Construction Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 1. Introduction In recent years, the construction industry has prioritized the utilisation of industrial by-products, recycled materials, and waste to promote sustainable development [ 1 ]. Integrating these options mitigates the exhaustion of natural resources and fosters a circular economy. [ 2 ]. Even a partial substitution of conventional raw materials with recycled components can enhance environmental conservation efforts [ 3 ]. However, it is essential to ensure that construction materials are designed and manufactured in accordance with relevant standards and environmental regulations to maintain their performance and durability [ 4 ]. Self-compacting concrete (SCC) has emerged as a transformative material in modern construction due to its exceptional workability, superior surface finish, and enhanced durability [ 5 ]. Unlike conventional concrete, SCC flows and consolidates under its weight, eliminating the need for mechanical vibration, which significantly reduces labor costs and noise pollution on construction sites [ 6 ]. The incorporation of mineral additives is essential for optimizing rheological behavior, ensuring adequate flowability and resistance to segregation while also enhancing early strength development [ 7 ]. Furthermore, the use of supplementary cementitious materials, such as silica fume, fly ash, glass powder, and ground granulated blast furnace slag, helps reduce the cement content in SCC mixtures [ 8 ]. This not only reduce production costs but also minimise the carbon footprint of cement manufacturing, making SCC a more sustainable choice for the construction industry. [ 9 ]. Additionally, incorporating industrial by-products such as steel slag and calcined clay enhances both fresh and hardened properties, ensuring high mechanical performance while increasing resistance to environmental degradation. [ 9 ]. The ability of SCC to incorporate recycled materials without compromising its structural integrity highlights its significant contribution to sustainable and eco-friendly construction practices [ 10 ]. SCC is increasingly recognised as a preferable material for many applications, including high-rise buildings, bridges, and precast parts, due to its combination of excellent performance and environmental advantages. Its versatility, resilience, and diminished resource utilisation render it an essential element in the progression of sustainable building technologies. [ 11 ]. Conversely, advanced computational approaches, such as artificial neural networks (ANNs), have become indispensable for predicting and optimising the features of SCC. These machine learning algorithms can analyse complicated information and discern subtle interactions among different mix components, enabling precise predictions of essential features of SCC. [ 12 ]. Artificial Neural Networks (ANNs) allow researchers to assess the influence of extra materials on the performance of Self-Consolidating Concrete (SCC). Through the examination of intricate correlations between material characteristics and concrete performance, artificial neural networks (ANNs) enhance the formulation of more economical and sustainable mix designs, optimising workability, strength, and durability while diminishing dependence on traditional raw materials. [ 12 ]. A principal benefit of artificial neural networks in self-compacting concrete research is their capacity to evaluate the non-linear interactions among factors such as cement content, silica fume dose, water-to-binder ratio, and curing conditions. This comprehensive knowledge allows the optimisation of mixed proportions to improve both fresh and hardened characteristics while reducing resource use. Moreover, ANN-based prediction models provide dependable strength assessments at various curing ages, minimising the need for lengthy experimental testing and accelerating the material selection process. This study aims to optimize and validate the fresh and hardened properties of self-compacting concrete (SCC) incorporating binary and ternary blends of ordinary Portland cement (OPC), glass powder (GP), and natural pozzolana (PZ) using an artificial neural network (ANN) approach. The work seeks to forecast fresh features, including slump flow and V-funnel time, for SCC compositions including OPC, GP, and PZ by using ANN models trained on an extensive library of diverse mixes. Furthermore, it aims to predict hardened qualities such as compressive strength, flexural strength, water absorption, porosity, and ultrasonic pulse velocity (UPV), while also assessing the CO₂ emissions linked to these mixes. This study utilises the predictive capabilities of artificial neural networks (ANNs) to optimise the ratios of additional elements in self-compacting concrete (SCC), enhancing its flowability, segregation resistance, and overall workability. The research seeks to optimise the design process for structural applications by discovering high-performance mix designs, therefore minimising material waste and decreasing dependence on laborious experimental testing. This method improves the efficiency and sustainability of SCC manufacturing, fostering eco-friendly building practices. 2. Methodology 2.1 Experimental Design and Data Collection This study used 10 self-compacting mortar (SCM) mixes produced via laboratory trials to train and evaluate artificial neural network (ANN) models.. The goal was to anticipate and optimise the rheological, mechanical, and durability characteristics of SCM using Ordinary Portland Cement (OPC), Glass Powder (GP), and Natural Pozzolana (PZ) as cementitious materials. The experimental dataset served as a foundation for training the ANN model, resulting in a reliable and data-driven study of the effects of various mineral admixtures. The SCM mixes were designed to examine both fresh-state and hardened-state characteristics, allowing for a full understanding of material behaviour. The qualities in the fresh condition were examined using slump flow and V-funnel flow tests, which provide information about workability and viscosity. The hardened-state measurements comprised compressive strength (CS28), flexural strength (FS28), ultrasonic pulse velocity (UPV), water absorption, and porosity. Table 1 shows the experimental findings from these studies, including the quantities of OPC, GP, and PZ and their influence on SCM properties. It should also be mentioned that the sand content and superplasticizer dose were maintained consistently throughout all mixes to guarantee uniformity in the assessment of cementitious material properties. Table 1 Experimental mix proportions and their effects on studied parameters OPC (%) GP (%) PZ (%) Sand (Kg/m 3 ) SP (%) Slump (cm) V-funnel (s) CS28 (MPa) FS28 (MPa) UPV (m/s) Absorption (%) Porosity (%) 100 0 0 1830.1 0.67 32 3.2 40 4 4080 17 19 95 5 0 32.4 3 47 5.7 4100 15 17 90 10 0 32.7 2.5 50 5.5 4150 16 15 85 15 0 33 2 40 5 3850 20 20 95 0 5 31 3.75 47 4.3 4130 18 17.5 90 0 10 28 4.75 49 5.91 4200 15 16 85 0 15 27 5.5 44 4.5 3950 22 19 90 5 5 31.5 3.1 45 5.4 4100 14 17 85 10 5 32.5 2.8 43 5.15 4300 13 20 80 15 5 33 2.5 41 5 4000 16 21 2.2 Artificial Neural Network (ANN) Model Development Figure 1 illustrates the architecture of the ANN model employed in this study, comprising three input layers (denoting the proportions of cement, glass powder, and natural pozzolana), 5 hidden layers, and 7 output layers that forecast the fresh and hardened properties of self-compacting mortar (SCM). The hyperbolic tangent (tanH) function is the activation function adopted in this work. It was applied to the hidden layers to increase non-linearity and improve the ANN model's predictive accuracy. ANN models were constructed and trained using the k-fold cross-validation technique to assess the reliability and performance of a predictive model. It involves dividing the dataset into k equal subsets, where the model is trained on k-1 subsets and tested on the remaining one. This process is repeated k times, ensuring that each subset serves as the validation set once. By systematically rotating the validation set, this method provides a thorough evaluation of the model’s ability to generalize and aids in detecting potential overfitting (Mellios et al., 2023). 2.3 Mixture Design Approach This study explores the effects of ordinary Portland cement (OPC), glass powder (GP), and natural pozzolana (PZ), both individually and in combination, on the rheological and mechanical properties of self-compacting mortar (SCM). A simplex-lattice mixture design, based on a triangular grid with three components, was employed to evaluate their interactions, as shown in Fig. 2 . The total number of experimental combinations is determined using the following equation. $$\:C=\frac{(m+q-1)!}{m!(q-1)!}$$ 1 Where, m and q represent the number of levels and factors, respectively. With 10 levels and 3 factors, the number of combinations to be treated is 66. To evaluate the effects of different proportions and combinations of OPC, GP, and PZ on the targeted properties of SCM, a second-degree model was applied. As expressed in Eq. 2 , this model facilitates the prediction and analysis of how variations in OPC, GP, and PZ content influence both the fresh and hardened properties of SCM. $$\:Y={b}_{1}\times\:OPC+\:{b}_{2}\times\:\text{G}\text{P}+\:{b}_{3}\times\:PZ+{b}_{4}\times\:\left(OPC\bullet\:GP\right)+{b}_{5}\times\:\left(OPC\bullet\:PZ\right)+{b}_{6}\times\:\left(GP\bullet\:PZ\right)$$ 2 Where Y represents the output obtained from ANN models used to predict the fresh and hardened properties of SCM. The coefficients b i , determined through a standard least-square fitting process, serve as model parameters that contribute to these predictions. The values of these coefficients are provided in Table 2 The ternary plot visually represents a mixture composed of three components: OPC, GP, and PZ, with each vertex corresponding to one of these pure components. The proportion of each component within the mixture is determined by referencing the axis labeled with the color associated with that specific component. To determine the proportion of a given component, a line is drawn through the point representing the desired composition, running parallel to the base opposite the vertex of the selected pure component, as illustrated in Fig. 2 . 3. Results and discussion Table 2 shows the findings of the Artificial Neural Network (ANN) model used for self-compacting mortar (SCM) and parameter estimation, which show high predictive skills for the majority of parameters. The model demonstrates high accuracy in fresh-state properties, exhibiting R² values of 0.95 for slump flow and 0.97 for V-funnel time, which indicates a strong correlation with experimental data. Porosity (R² = 0.90) and absorption (R² = 0.79) demonstrate significant correlations, affirming the effectiveness of the ANN in describing the impact of glass powder (GP) and pozzolana (PZ) on microstructural improvement. The model demonstrates limited predictive capability for ultrasonic pulse velocity (UPV) (R² = 0.47), indicating intricate relationships between microstructural densification and wave propagation. The root mean square error (RMSE) values confirm the model's accuracy, especially in slump flow (0.4607) and V-funnel time (0.1407), thereby confirming its capacity to predict workability trends in SCM. The regression coefficients explain the contributions of GP and PZ to SCM properties. GP significantly improves fluidity and decreases viscosity, as confirmed by its positive effect on slump flow (b2 = 33.75 cm) and its adverse effect on V-funnel time (b5 = -1.18, b6 = -3.56). PZ enhances mechanical properties by increasing compressive strength (b3 = 44.20 MPa) and flexural strength (b3 = 6.22 MPa) through its pozzolanic reactivity, leading to long-term strength development. Excessive replacement levels negatively affect mechanical performance, as indicated by the negative b6 coefficient for compressive strength (-14.97 MPa). Microstructural analysis indicates that PZ is more influential in reducing porosity compared to GP, leading to a denser material matrix and enhanced durability. The ANN model demonstrates effective prediction of most SCM properties; however, its reduced accuracy for UPV indicates the need for further improvement, potentially through the incorporation of additional training data or the utilization of advanced AI techniques. Table 2 ANN model performance and regression coefficients Slump (cm) V-funnel (s) CS28 (Mpa) FS28 (Mpa) UPV (m/s) Absorption (%) Porosity (%) R² 0.95 0.97 0.81 0.60 0.47 0.79 0.90 RMSE 0.4607 0.1407 1.1686 0.4444 98.157 0.9536 0.4547 P-value < 0.0001 < 0.0001 < 0.0001 < 0.0001 < 0.0001 < 0.0001 < 0.0001 b1 32.5668 3.2207 39.3714 3.8046 3984.9785 18.6865 20.3953 b2 33.7460 2.2758 43.7045 4.2205 3943.5407 19.9426 19.3255 b3 25.6255 5.5338 44.1970 6.2258 3993.5302 19.6498 18.0670 b4 -1.2291 -0.1157 27.1078 5.4263 336.6598 -13.6533 -17.1337 b5 2.1736 -1.1826 23.0376 -0.0330 136.9164 -10.0467 -10.7314 b6 4.5854 -3.5571 -14.9710 1.9429 1329.4223 -29.1227 6.3590 3.1 Rheological Properties The ternary diagrams presented in Fig. 3 illustrate how the combination of cement, glass powder (GP), and natural pozzolan influences the slump flow of a self-compacting mortar mixture, specifically measured by the mini-cone slump test. As the proportion of glass powder increases in the mixture, the slump flow also increases. This improvement is mainly due to the fine nature of glass powder particles, which are smooth and have low porosity [ 13 ]. These characteristics help optimize the packing density of the mixture, reducing internal friction between the particles. Furthermore, glass powder has relatively low pozzolanic reactivity at early hydration stages, allowing the mixture to retain a portion of free water. This retained water enhances the flowability of the concrete, making it more workable. Kumarappan N [ 14 ], confirms that incorporating more glass powder into the mix leads to increased slump values, which reflects improved fluidity. However, when pozzolan is introduced into the mix, a reduction in fluidity is observed. Pozzolan, which is a volcanic ash or similar material, has a tendency to absorb water and form bonds with calcium hydroxide in the mixture. This interaction decreases the amount of available water in the mix, reducing its fluidity. To maintain the desired fluidity, more superplasticizer is required. Since pozzolan particles are less easily dispersed compared to mortar with 100% cement and glass powder, they require more superplasticizer to maintain the same level of fluidity. Several studies, [ 15 , 16 ], have shown that the presence of natural pozzolan in self-compacting concrete leads to a decrease in fluidity. This is consistent with the current findings, where the introduction of pozzolan necessitates higher SP dosages to achieve similar workability. Despite this, when glass powder is combined with pozzolan, a synergistic effect occurs. The presence of glass powder helps to counteract the negative effect of pozzolan on fluidity. For example, the slump flow of the mixture increases from 31 cm with 5% pozzolan to 32.5 cm when 10% glass powder is added. This combination is particularly beneficial when higher pozzolan contents are used, such as 15%, where the deformability of the mix could otherwise be compromised. Sharifi et al. [ 17 ] examined the effectiveness of recycled glass in the form of fine aggregates in self-compacting concrete mixtures. The results indicate that fluidity characteristics were enhanced as glass waste was incorporated into the mix. The synergistic effect of these two materials ensures that the mix remains fluid, homogeneous, and stable, even when the pozzolan content is relatively high. This approach could offer ease of placement in concrete mix design. The ternary contour plot in Fig. 4 demonstrates the effect of varying proportions of glass powder and natural pozzolan on the flow time of self-compacting mortar. As the PZ content increases, there is a corresponding rise in flow time, approaching the upper limit specified by EFNARC guidelines. Mortars with 15% PZ require higher dosages of superplasticizer (SP) to maintain flowability, particularly in confined spaces, to avoid potential blockages. This can be attributed to stronger interparticle interactions, which lead to increased internal friction and resistance to deformation [ 18 ]. Similar findings were reported by Belaidi et al [ 19 ]., who observed an increase in viscosity with higher amounts of natural pozzolan. Conversely, the inclusion of GP is shown to reduce the flow time compared to mortars containing only PZ. The presence of GP also decreases the amount of SP needed to maintain the self-compacting properties of the mortar. Mortars with 15% GP exhibit a more fluid consistency and require less SP than those with only cement and PZ. This can be explained by the role of fine glass powder particles in enhancing the compactness of the cementitious matrix, which reduces internal friction and improves the mixture's flowability [ 20 ]. Additionally, the smooth, non-porous surface of glass powder minimizes water absorption, ensuring that more free water is available to optimize fluidity. The combination of GP and PZ results in reduced flow times and lower overall viscosity in the mixtures. Mortars with higher GP content display flow times ranging from 3 to 4 seconds. These findings align with previous research, which suggested that incorporating GP into PZ mixtures, especially in larger proportions, mitigates the negative impact of PZ on flow time and viscosity, ultimately enhancing the ease of handling of the mixture. 3.2 Hardened-State Performance Ternary contour plots shown in Fig. 5 illustrate the evolution of flexural strength of the different mortar models at 28 days. According to the figure, the mortar mix without PZ and GP exhibits low flexural strength. However, when PZ and GP are incorporated as cementitious additions, the tensile strength increases. The improvement in the flexural strength of self-compacting mortar (SCM) in the presence of glass powder (GP) and natural pozzolan (PZ) results from several synergistic mechanisms. On the one hand, both materials exhibit pozzolanic activity, allowing them to interact with the portlandite (Ca(OH)₂) released during cement hydration, leading to the additional formation of calcium silicate hydrates (C-S-H) [ 21 ]. These phases contribute to the densification of the cementitious matrix and the enhancement of mechanical performance. On the other hand, the mortar's microstructure becomes more compact due to reduced porosity, limiting crack propagation and strengthening the material’s overall cohesion. The incorporation of GP and PZ also improves the adhesion between the cement paste and aggregates, delaying crack initiation under stress. Furthermore, the presence of glass powder plays a filler role, enhancing the mixture’s compactness and reducing water demand, which improves cohesion and mortar strength [ 20 , 22 ]. Finally, the combination of the pozzolanic effects of PZ with the reactive and filler properties of GP optimizes the mortar’s characteristics, resulting in a more homogeneous and durable structure. This pattern of flexural strength enhancement has been observed in several previous studies [ 23 – 25 ]. Figure 6 illustrates the variation in compressive strength of different models of SCM mixtures at 28 days. The results indicate a relative increase in compressive strength with the incorporation of both natural pozzolan and glass powder, with an optimum content of 15% for both binary and ternary cementitious systems. At 28 days, the compressive strength of the reference MAP mixture is 40 MPa, which improves to 48 MPa and 45 MPa with the introduction of 10% GP and 5% PZ as a binary cementitious addition. This enhancement in compressive strength at 28 days with binary and ternary cementitious additions can be attributed to the pozzolanic reaction with Ca(OH)2 over the long-term [ 26 , 27 ]. Belaidi et al [ 28 ]. observed a similar effect of pozzolan on the development of compressive strength in six self-compacting mortar mixtures containing pozzolan at different replacement levels of 0%, 5%, 10%, 15%, 20%, and 25%. They reported an increase in strength at 90 days with a higher pozzolan content during the advanced hydration stages, with an optimum of 20%. The increase in compressive strength observed in the mixtures incorporating GP can be explained, on the one hand, by the enhanced pozzolanic reaction between SiO2 and CaO from the glass powder present in the pore solution and CH grains, as reported by Elaqra et al. [ 29 ]. Additionally, the filler effect contributes to a denser microstructure by reducing total porosity. However, the pozzolanic reaction of PZ led to a more significant strength improvement compared to GP due to its combined pozzolanic and pore-filling effects. Furthermore, as observed in Fig. 5 , the addition of PZ in the mixtures containing GP as a cementitious additive resulted in higher compressive strength compared to mixtures incorporating GP alone as a binary cementitious addition. The reference SCM mixture achieved a compressive strength of 40 MPa. This enhancement can be attributed to the pozzolanic reaction of PZ, which compensates for the long-term strength development. This improvement in compressive strength may also be due to the presence of pozzolanic compounds (PZC), which penetrate and fill the pores, thus contributing to an improved interfacial transition zone (ITZ) between pozzolanic aggregates and the cement paste [ 30 ]. Ghrici et al. [ 31 ] also demonstrated that incorporating 10% limestone fillers with a low amount of natural pozzolan positively influences early-age compressive strength. However, beyond 28 days, a beneficial effect was observed with a high pozzolan content and a low amount of limestone fillers. 3.3 Microstructural integrity and durability assessment Figure 7 illustrates the evolution of water absorption in different formulations over time. The results indicate a general trend of decreasing absorption rates over time for all the studied mixtures. This progressive reduction can be attributed to the continued hydration of cementitious components and the densification of the material’s microstructure. However, a comparative analysis of the different formulations reveals that mixtures incorporating binary cements, whether containing PZ or GP, exhibit higher absorption coefficients compared to ternary cements. This difference can be explained by the nature and reactivity of the cementitious additions used. In binary cement, although the partial replacement of OPC with PZ or GP contributes to improving properties of SCM, it can also lead to increased porosity in the short term due to a slower hydration rate and less pronounced densification [ 32 ]. Conversely, formulations based on ternary cement show lower water absorption, suggesting better matrix compactness. This improved performance is likely due to the synergistic effect between PZ and GP, which promotes a more effective pozzolanic reaction and reduces capillary porosity [ 33 , 34 ]. Indeed, the combined incorporation of these two mineral additions helps fill residual pores and optimize the material’s microstructure, thereby limiting water penetration and enhancing the durability of self-compacting mortar [ 34 ]. Hossain et al [ 35 ] examined the influence of an alkali-activated ternary blended binder on water absorption. The results indicate that water transport properties can be improved with ternary cement. These observations confirm that the combined use of PZ and GP in ternary cement is an effective strategy to improve resistance to liquid penetration and, consequently, the durability of self-compacting mortars. The results presented in Fig. 8 clearly show that as the incorporation of PZ and GP increases in the self-compacting mortar, the velocity of sound waves increases. This improvement reaches an optimum when the proportion of these materials is 10%. This trend suggests that the addition of binary and ternary cement in the mortar composition optimizes the acoustic properties of the material, particularly by increasing the UGP values, which can be interpreted as a sign of better homogeneity and densification of the mortar. It was also observed that the UGP values of the mixtures with PZ and GP are higher than those of the OPC. These results indicate that the addition of these materials increases the efficiency of the hardening process of the mortar while optimizing its mechanical and acoustic performances. This phenomenon is particularly noticeable with the incorporation of PZ and GP, which play a key role in densifying the cement microstructure. Moreover, the study highlights the effect of GP and PZ in refining the pores within the cement matrix and in the interfacial transition zone (ITZ). PZ, in particular, proves to be a beneficial material for improving cement density, especially when compared to GP. This can be explained by PZ’s ability to participate in the pozzolanic reaction, which generates additional calcium silicate hydrate (C–S–H) in the micro-cracks within the structure [ 36 ]. This process not only fills the pores but also reduces the porosity of the material. The combination of these effects, namely the pore-filling capacity of PZ and GP and the additional generation of C–S–H, contributes to a reduction in the material’s porosity. Ultimately, this improves the mechanical and acoustic properties of the mortar by increasing the UGP values, reflecting better structural integrity and greater resistance to sound wave propagation. These results confirm the importance of using binary and ternary cements, not only to improve the mechanical characteristics of the mortar but also to optimize its overall physical properties. Figure 9 demonstrates the influence of PZ (Pozzolana) and GP on the porosity of self-compacting mortar mixtures. The data indicates that the inclusion of both GP and PZ results in a noticeable decrease in the void volume of the mortar. This reduction in porosity is mainly driven by two factors. Firstly, the fine particle size of GP and PZ plays a significant role in filling the existing voids within the mortar matrix. These finer particles act as a filler, occupying spaces that would otherwise remain unfilled, thereby contributing to a more compact and dense structure[ 37 ]. Secondly, the pozzolanic reaction between the PZ and GP with the available calcium hydroxide (CH) in the mortar further contributes to this densification process [ 38 ]. As the pozzolanic materials react with CH, they form additional hydration products, most notably calcium silicate hydrate (C–S–H), which plays a critical role in refining the microstructure of the mortar. These additional products help to bond the particles more effectively, filling micro-cracks and voids within the matrix. The formation of C–S–H not only improves the density of the material but also enhances its durability and overall structural integrity [ 39 ]. By reducing the porosity, the mortar’s resistance to water penetration and other environmental factors is improved, which ultimately leads to better long-term performance. Moreover, the reduced void volume also implies enhanced mechanical properties, such as increased strength and stiffness, due to the more densely packed structure. Therefore, the combination of fine particles filling voids and the formation of additional C–S–H provides a highly effective mechanism for optimizing the physical properties of self-compacting mortar. 3.4 Environmental sustainability The environmental impact assessment of a project means the quantitative estimation of the various positive and negative changes affecting the environment as a result of its creation. This evaluation considers all the environmental effects and impacts related to the activities of the studied project, based on the estimation of certain evaluation indicators, which are mentioned in the final reports. Thus, the evaluation indicators of impacts are presented separately in this study [ 40 ]. The study of carbon dioxide (CO 2 ) emissions into the atmosphere and energy consumption was calculated using the following equation: $$\:\frac{\text{C}\text{i}-\text{C}\text{o}\:}{\text{C}\text{o}}x100$$ Where: Ci: CO 2 emissions for mixtures of SCM mixed with PZ and GP (i = PZ5, PZ10, PZ15, GP5, GP10, GP15, PZ5 + GP5, PZ5 + GP10, and PZ5 + 15GP); C0: CO 2 emissions for the mixture with 100% OPC. Table 3 CO 2 emissions for all SCM elaborated. Mix Control 5GP 10GP 15GP 5PZ 10PZ 15PZ 5GP + 5PZ 10GP + 5PZ 15GP + 5PZ CO 2 emissions (%) 100 -4.2 -8.3 -12.4 -5 -8.7 -13 -8.5 -12.6 -14.2 As illustrated in Fig. 10 , which presents the CO 2 emissions and energy consumption for each cubic meter of self-compacting mortar (SCM), substituting a portion of cement with PZ and glass powder results in a significant reduction in both CO 2 emissions and energy consumption. The data reveals that CO 2 emissions decreased by an impressive range of − 5% to − 13. %, depending on the level of binary substitution of GP and PZ. Similarly, the Co2 emission is reduced by -8.5–14% as the amount of cement replaced by the ternary substitution with PZ and GP increases. This reduction can be attributed to the beneficial properties of PZ and glass powder, which, through their pozzolanic and filling effects, contribute to enhancing overall material performance while requiring less energy during production. When comparing the two mixtures—one with cement alone and the other with cement partially substituted by PZ and GP it is evident that the latter composition results in the greatest environmental benefit. The substitution of traditional cement with these supplementary materials not only reduces the carbon footprint but also contributes to energy savings, making this approach much more sustainable from an environmental perspective. The integration of PZ and glass powder aligns with the principles of sustainability by reducing the environmental impact associated with cement production. By lowering both CO 2 emissions and energy consumption, this substitution process contributes to a more eco-friendly and sustainable approach to construction materials. Such innovations are crucial for advancing sustainable construction practices and reducing the carbon footprint of the construction industry, which is one of the major contributors to global emissions. The integration of PZ and glass powder in cementitious composites offers a viable approach for developing more sustainable and ecologically conscientious construction materials. This substitute technique alleviates the environmental effects of cement manufacture and coincides with overarching sustainability goals, representing a crucial advancement in eco-friendly building practices. 4. Conclusion This study illustrates the efficient use of PZ and GP as binary and ternary cementitious additives in self-compacting mortar (SCM), providing a novel method for enhancing material performance and sustainability. Artificial Neural Networks (ANN) were used as an effective instrument for modelling and analysing the behaviour of mixes, facilitating a thorough comprehension of the influence of these additions on the characteristics of mortar. The main findings of this research are as follows: The application of ANN in this study enabled the identification of optimal parameters for the formulation of reference SCM, including the water-to-cement ratio (W/C) and sand-to-material ratio (S/M). This provided a more efficient way to design SCM mixtures that meet the desired mechanical and flow properties, using locally sourced materials. Adding GP to the SCM mix significantly improved flowability, passing ability, and filling capacity. ANN models projected that these enhancements would minimise the requirement for superplasticizers, resulting in a more efficient use of resources while preserving the workability required for large-scale applications. A significant finding of the study is that replacing part of regular Portland cement with PZ and GP reduces the environmental impact of the mortar. This substitution lowers CO2 emissions from cement production, fostering greener and more sustainable construction practices. Although the introduction of PZ and GP resulted in a slight decrease in tensile and compressive strength compared to the reference SCM, the benefits in workability and environmental performance make these modified mixtures viable for specific construction uses. Furthermore, the addition of PZ to ternary cementitious mixes increased compressive strength in some formulations. A reduction in water absorption was observed with higher dosages of PZ and GP, suggesting that these additives contribute to better long-term durability. Moreover, ANN analysis revealed that an increase in the amount of PZ and GP also led to a reduction in porosity, which improved the material’s density and resistance to external influences, such as moisture. UGP testing indicated that the inclusion of PZ and GP positively influenced the integrity and uniformity of the SCM. The ANN model was able to predict these improvements accurately, reflecting an enhanced structural cohesion and greater durability of the mortar. These findings highlight the potential of these additives to contribute to high-performance construction materials. The integration of PZ and GP as ternary cementitious additives, bolstered by ANN modelling, presents a sustainable and efficient alternative to conventional mortar formulations. This method reduces the environmental impact of cement-based products while simultaneously improving their durability and performance, so making a substantial contribution to sustainable building methods. Declarations Author Contribution Younes Ouldkhaoua: Conceptualization, Methodology and Writing Mohamed Sahraoui: Formal Analysis and MethodologyZine El-Abiddine Laidani: Methodology and Validation Benchaa Benabed: Conceptualization and SupervisorRajab abousnina: Review and EditingMohamed El-ghazali Balgacem : Review and Editing, References M. Bergonzoni, R. Melloni, L. Botti, Analysis of sustainable concrete obtained from the by-products of an industrial process and recycled aggregates from construction and demolition waste, Procedia Computer Science 217 (2023) 41-51. L. Becchetti, D.M. Bova, L. Raffaele, Win together or lose alone: Circular economy and hybrid governance for natural resource commons, Journal of Cleaner Production 486 (2025) 144520. H.S. Hassan, C. Shi, F.S. Hashem, S.A. El-Magd, A. Maged, H.A. Abdel-Gawwad, H. Pfeiffer, Industrial waste recycling approach: An ecofriendly geopolymer binder for clean and sustainable environments (A 24-h green recycling process), Journal of Environmental Management 377 (2025) 124568. M. Ulewicz, Recycled Materials in Civil Engineering Application, MDPI, 2023, p. 7075. A. Alshahrani, Towards sustainable construction: experimental approach and multi-scale simulation in high-strength self-compacting concrete design, Cardiff University, 2024. M. Hosseinpoor, Numerical Simulation of Fresh SCC Flow in Wall and Beam Elements Using Flow Dynamics Models, University of Sherbrooke, 2017. J. Ahmad, Z. Zhou, A.F. Deifalla, Steel fiber reinforced self-compacting concrete: a comprehensive review, International Journal of concrete structures and materials 17(1) (2023) 51. K. Sobolev, M. Kozhukhova, K. Sideris, E. Menéndez, M. Santhanam, Alternative supplementary cementitious materials, Properties of Fresh and Hardened Concrete Containing Supplementary Cementitious Materials: State-of-the-Art Report of the RILEM Technical Committee 238-SCM, Working Group 4 (2018) 233-282. K.C. Onyelowe, D.-P.N. Kontoni, The net-zero and sustainability potential of SCC development, production and flowability in concrete structures, International Journal of Low-Carbon Technologies 18 (2023) 530-541. M. Perera, P. Ranjith, Eco-friendly cementitious composites for enhanced strength: Emerging trends and innovations, Journal of Cleaner Production 468 (2024) 142962. A. Alhamad, S. Yehia, É. Lublóy, M. Elchalakani, Performance of different concrete types exposed to elevated temperatures: a review, Materials 15(14) (2022) 5032. M.A. Hossain, G.S. Islam, A. Mallick, Compressive strength prediction for industrial waste-based scc using artificial neural network, Journal of the Civil Engineering Forum, 2022, pp. 11-26. L. Li, C. Deng, Y. Zhou, Q. Tan, W. Yan, D. Zhou, Y. Zhou, Stability and Rheological Properties of Grouts with Waste Glass Powder as Cement Replacement: Influences of Content and Alkali Activator, Materials 18(2) (2025) 353. N. Kumarappan, Partial replacement cement in concrete using waste glass, International Journal of Engineering Research and Technology 2(10) (2013) 1880-1883. K. Celik, C. Meral, M. Mancio, P.K. Mehta, P.J. Monteiro, A comparative study of self-consolidating concretes incorporating high-volume natural pozzolan or high-volume fly ash, Construction and Building materials 67 (2014) 14-19. S. Kenai, B. Menadi, A. Debbih, E.H. Kadri, Effect of recycled concrete aggregates and natural pozzolana on rheology of self-compacting concrete, Key Engineering Materials 600 (2014) 256-263. Y. Sharifi, M. Houshiar, B. Aghebati, Recycled glass replacement as fine aggregate in self-compacting concrete, Frontiers of Structural and Civil Engineering 7(4) (2013) 419-428. B. Cheng, L. Mei, W.-J. Long, S. Kou, L. Li, S. Geng, Ai-guided proportioning and evaluating of self-compacting concrete based on rheological approach, Construction and Building Materials 399 (2023) 132522. A. Belaidi, L. Azzouz, E. Kadri, S. Kenai, Effect of natural pozzolana and marble powder on the properties of self-compacting concrete, Construction and Building Materials 31 (2012) 251-257. W. Chen, D. Liu, Y. Liang, Influence of Ultra Fine Glass Powder on the Properties and Microstructure of Mortars, Fluid Dynamics & Materials Processing 20(5) (2024). E. Haustein, S. Kalisz, Early-Age Hydration Reaction of Cement Mortars with the Participation of Aluminosilicate Microsphere Fractions, Journal of Materials in Civil Engineering 37(4) (2025) 04025044. Z. Lai, Y. Chen, Enhancing the mechanical and environmental performance of solidified soil using construction waste and glass micro-powder, Heliyon 10(22) (2024). G. Lee, T.-C. Ling, Y.-L. Wong, C.-S. Poon, Effects of crushed glass cullet sizes, casting methods and pozzolanic materials on ASR of concrete blocks, Construction and Building Materials 25(5) (2011) 2611-2618. T.-C. Ling, C.-S. Poon, Properties of architectural mortar prepared with recycled glass with different particle sizes, Materials & Design 32(5) (2011) 2675-2684. T.-C. Ling, C.-S. Poon, Utilization of recycled glass derived from cathode ray tube glass as fine aggregate in cement mortar, Journal of Hazardous Materials 192(2) (2011) 451-456. A. Mohammed, A. Salih, H. Raof, Vipulanandan constitutive models to predict the rheological properties and stress–strain behavior of cement grouts modified with metakaolin, Journal of Testing and Evaluation 48(5) (2020). M.I.C. Sousa, J.H. da Silva Rêgo, Mechanical Strength Analysis of Ternary Cement Pastes Containing Nanosilica and Metakaolin, Proceedings of the International Conference of Sustainable Production and Use of Cement and Concrete, Springer, 2020, pp. 59-67. A.S.E. Belaidi, S. Kenai, E.-H. Kadri, H. Soualhi, B. Benchaâ, Effects of experimental ternary cements on fresh and hardened properties of self-compacting concretes, Journal of adhesion science and Technology 30(3) (2016) 247-261. H. Elaqra, R. Rustom, Effect of using glass powder as cement replacement on rheological and mechanical properties of cement paste, Construction and Building Materials 179 (2018) 326-335. R. Muduli, B.B. Mukharjee, Characteristics of Concrete Prepared with Metakaolin and Recycled Coarse Aggregates, Advances in Sustainable Construction Materials and Geotechnical Engineering, Springer2020, pp. 73-85. M. Ghrici, S. Kenai, M. Said-Mansour, Mechanical properties and durability of mortar and concrete containing natural pozzolana and limestone blended cements, Cement and Concrete Composites 29(7) (2007) 542-549. O. Semmana, M.A.M. Rihan, Z.M. Barrie, C. Daniel, T.A. Abdalla, A Systematic Review of the Strength, Durability, and Microstructure Properties of Concrete Incorporating Glass Powder, Engineering Reports 7(1) (2025) e70002. A. Adesina, S. Das, Influence of glass powder on the durability properties of engineered cementitious composites, Construction and Building Materials 242 (2020) 118199. J. Esmaeili, A.O. AL-Mwanes, A review: Properties of eco-friendly ultra-high-performance concrete incorporated with waste glass as a partial replacement for cement, Materials Today: Proceedings 42 (2021) 1958-1965. M.M. Hossain, M.R. Karim, M.M.A. Elahi, M.F.M. Zain, Water absorption and sorptivity of alkali-activated ternary blended composite binder, Journal of Building Engineering 31 (2020) 101370. Y. Li, H. Zhang, M. Huang, H. Yin, K. Jiang, K. Xiao, S. Tang, Influence of different alkali sulfates on the shrinkage, hydration, pore structure, fractal dimension and microstructure of low-heat Portland cement, medium-heat Portland cement and ordinary Portland cement, Fractal and Fractional 5(03) (2021) 79. N. Sathiparan, P. Jeyananthan, D.N. Subramaniam, Influence of metakaolin on pervious concrete strength: a machine learning approach with shapley additive explanations, Multiscale and Multidisciplinary Modeling, Experiments and Design 7(4) (2024) 3919-3946. R.A. Medeiros-Junior, M. Thiesen, A.M. Betioli, J.M. Casali, L.F.Z. Trentin, A. Frare, A.G. Borçato, Influence of Precursor Particle Size and Calcium Hydroxide Content on the Development of Clay Brick Waste-Based Geopolymers, Minerals 14(11) (2024) 1169. F.Y. Al-Saffar, L.S. Wong, S.C. Paul, An elucidative review of the nanomaterial effect on the durability and calcium-silicate-hydrate (CSH) gel development of concrete, Gels 9(8) (2023) 613. M. Medine, Experimental study of lightweight concretes incorporating aggregates from the crushing of used tires, PhD thesis, University Djillali Liabès, Sidi Bel-Abas -Algeria, (2018). (In French). Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 13 Apr, 2025 Reviews received at journal 12 Apr, 2025 Reviews received at journal 05 Apr, 2025 Reviewers agreed at journal 31 Mar, 2025 Reviewers agreed at journal 29 Mar, 2025 Reviewers agreed at journal 29 Mar, 2025 Reviewers invited by journal 29 Mar, 2025 Editor assigned by journal 29 Mar, 2025 Submission checks completed at journal 28 Mar, 2025 First submitted to journal 28 Mar, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6331374","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":442222722,"identity":"edf03579-adf3-4ce6-abfc-fc3b15801181","order_by":0,"name":"Younes Ouldkhaoua","email":"data:image/png;base64,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","orcid":"","institution":"University of Sciences and Technology Houari Boumediene","correspondingAuthor":true,"prefix":"","firstName":"Younes","middleName":"","lastName":"Ouldkhaoua","suffix":""},{"id":442222726,"identity":"4ac39728-7b3b-432a-baca-fbb68b125cc1","order_by":1,"name":"Mohamed Sahraoui","email":"","orcid":"","institution":"Blida 1 University","correspondingAuthor":false,"prefix":"","firstName":"Mohamed","middleName":"","lastName":"Sahraoui","suffix":""},{"id":442222727,"identity":"ad3b5db9-484c-4bf3-a076-2873bf662500","order_by":2,"name":"Zin-El Abiddine Laidani","email":"","orcid":"","institution":"Blida 1 University","correspondingAuthor":false,"prefix":"","firstName":"Zin-El","middleName":"Abiddine","lastName":"Laidani","suffix":""},{"id":442222729,"identity":"e855d034-1387-4174-9765-5f0b94ca7c68","order_by":3,"name":"Benchaa Benabed","email":"","orcid":"","institution":"University of Laghouat","correspondingAuthor":false,"prefix":"","firstName":"Benchaa","middleName":"","lastName":"Benabed","suffix":""},{"id":442222730,"identity":"a8f25ea0-8622-4436-825a-c5ef7fd42798","order_by":4,"name":"Rajab Abousnina","email":"","orcid":"","institution":"Curtin University","correspondingAuthor":false,"prefix":"","firstName":"Rajab","middleName":"","lastName":"Abousnina","suffix":""},{"id":442222731,"identity":"b7e30f27-e540-4e7b-ae34-791b28b6a2b3","order_by":5,"name":"Mohamed El-Ghazali Belgacem","email":"","orcid":"","institution":"University of Sciences and Technology Houari Boumediene","correspondingAuthor":false,"prefix":"","firstName":"Mohamed","middleName":"El-Ghazali","lastName":"Belgacem","suffix":""}],"badges":[],"createdAt":"2025-03-29 02:08:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6331374/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6331374/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":80890980,"identity":"dfc89c1d-2056-409e-bced-8205b2ce38df","added_by":"auto","created_at":"2025-04-18 10:08:51","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":158073,"visible":true,"origin":"","legend":"\u003cp\u003eThe architecture of ANN models used in this study.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/7c687becc2629609fca129a1.png"},{"id":80891311,"identity":"fba76a87-6652-4274-ada6-f80d4955af6d","added_by":"auto","created_at":"2025-04-18 10:16:48","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":80349,"visible":true,"origin":"","legend":"\u003cp\u003eSimplex-lattice design with 3 factors and 5 levels.\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/1cee1a968a7beee228ba08d0.png"},{"id":80890975,"identity":"6b6674e7-927b-4797-bdf5-da3c67f2ee1a","added_by":"auto","created_at":"2025-04-18 10:08:51","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":130899,"visible":true,"origin":"","legend":"\u003cp\u003eTernary plot of slump flow as a function of OPC, GP, and PZ proportions.\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/532c4841f6988003dc3a85c5.png"},{"id":80891313,"identity":"105a5f34-a775-4023-a720-17438da49572","added_by":"auto","created_at":"2025-04-18 10:16:49","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":106178,"visible":true,"origin":"","legend":"\u003cp\u003eTernary plot of V-funnel flow time as a function of OPC, GP, and PZ proportions.\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/1e2db0eb625e78073227f905.png"},{"id":80890981,"identity":"70baa1f1-7b35-44d9-a6bf-268dc44074a5","added_by":"auto","created_at":"2025-04-18 10:08:52","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":106306,"visible":true,"origin":"","legend":"\u003cp\u003eTernary plot of flexural strength as a function of OPC, GP, and PZ proportions.\u003c/p\u003e","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/1bc785d639dc36d546379f89.png"},{"id":80890958,"identity":"0dbe2d30-b504-42e3-9684-6d006912d5fe","added_by":"auto","created_at":"2025-04-18 10:08:48","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":115801,"visible":true,"origin":"","legend":"\u003cp\u003eTernary plot of compressive strength as a function of OPC, GP, and PZ proportions.\u003c/p\u003e","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/a466f1ec888f61019c1ff3d9.png"},{"id":80890976,"identity":"e75a5450-cdb0-45fa-91b4-3b96e53a39bc","added_by":"auto","created_at":"2025-04-18 10:08:51","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":111661,"visible":true,"origin":"","legend":"\u003cp\u003eTernary plot of water absorption as a function of OPC, GP, and PZ proportions.\u003c/p\u003e","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/2cbfe4f976116087dbf8b745.png"},{"id":80890979,"identity":"4927c17d-cd8c-429e-9047-9ad155a63adf","added_by":"auto","created_at":"2025-04-18 10:08:51","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":137332,"visible":true,"origin":"","legend":"\u003cp\u003eTernary plot of UPV as function of OPC, GP and PZ proportions.\u003c/p\u003e","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/8f3f380421d10558791edb34.png"},{"id":80890957,"identity":"9844aa2f-e0b9-4667-97bb-99bbf235dc2a","added_by":"auto","created_at":"2025-04-18 10:08:48","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":113974,"visible":true,"origin":"","legend":"\u003cp\u003eTernary plot of porosity as function of OPC, GP and PZ proportions.\u003c/p\u003e","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/e10df8ed476484b0bb5822bc.png"},{"id":80890968,"identity":"942e386f-d86d-479b-932d-854fd53f39bc","added_by":"auto","created_at":"2025-04-18 10:08:50","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":483601,"visible":true,"origin":"","legend":"\u003cp\u003eThe environmental impact of SCM mixtures on CO\u003csub\u003e2\u003c/sub\u003e emissions.\u003c/p\u003e","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/e028511a7799e6c63dc3dc27.png"},{"id":80891315,"identity":"4d34e165-5737-4667-a6f4-d5ba0bc49bfc","added_by":"auto","created_at":"2025-04-18 10:16:56","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2365035,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6331374/v1/62f74b2f-57ce-4447-883b-9c82ef07f0ac.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Optimizing Sustainable Self-Compacting Mortar Properties Using Natural Pozzolan and Glass Powder as Cementitious Materials: An Artificial Neural Network Approach","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eIn recent years, the construction industry has prioritized the utilisation of industrial by-products, recycled materials, and waste to promote sustainable development [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Integrating these options mitigates\u003c/p\u003e \u003cp\u003ethe exhaustion of natural resources and fosters a circular economy. [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Even a partial substitution of conventional raw materials with recycled components can enhance environmental conservation efforts [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. However, it is essential to ensure that construction materials are designed and manufactured in accordance with relevant standards and environmental regulations to maintain their performance and durability [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eSelf-compacting concrete (SCC) has emerged as a transformative material in modern construction due to its exceptional workability, superior surface finish, and enhanced durability [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Unlike conventional concrete, SCC flows and consolidates under its weight, eliminating the need for mechanical vibration, which significantly reduces labor costs and noise pollution on construction sites [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. The incorporation of mineral additives is essential for optimizing rheological behavior, ensuring adequate flowability and resistance to segregation while also enhancing early strength development [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Furthermore, the use of supplementary cementitious materials, such as silica fume, fly ash, glass powder, and ground granulated blast furnace slag, helps reduce the cement content in SCC mixtures [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. This not only reduce production costs but also minimise the carbon footprint of cement manufacturing, making SCC a more sustainable choice for the construction industry. [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Additionally, incorporating industrial by-products such as steel slag and calcined clay enhances both fresh and hardened properties, ensuring high mechanical performance while increasing resistance to environmental degradation. [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. The ability of SCC to incorporate recycled materials without compromising its structural integrity highlights its significant contribution to sustainable and eco-friendly construction practices [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. SCC is increasingly recognised as a preferable material for many applications, including high-rise buildings, bridges, and precast parts, due to its combination of excellent performance and environmental advantages. Its versatility, resilience, and diminished resource utilisation render it an essential element in the progression of sustainable building technologies. [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eConversely, advanced computational approaches, such as artificial neural networks (ANNs), have become indispensable for predicting and optimising the features of SCC. These machine learning algorithms can analyse complicated information and discern subtle interactions among different mix components, enabling precise predictions of essential features of SCC.\u003c/p\u003e \u003cp\u003e[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eArtificial Neural Networks (ANNs) allow researchers to assess the influence of extra materials on the performance of Self-Consolidating Concrete (SCC). Through the examination of intricate correlations between material characteristics and concrete performance, artificial neural networks (ANNs) enhance the formulation of more economical and sustainable mix designs, optimising workability, strength, and durability while diminishing dependence on traditional raw materials.\u003c/p\u003e \u003cp\u003e[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. A principal benefit of artificial neural networks in self-compacting concrete research is their capacity to evaluate the non-linear interactions among factors such as cement content, silica fume dose, water-to-binder ratio, and curing conditions. This comprehensive knowledge allows the optimisation of mixed proportions to improve both fresh and hardened characteristics while reducing resource use. Moreover, ANN-based prediction models provide dependable strength assessments at various curing ages, minimising the need for lengthy experimental testing and accelerating the material selection process.\u003c/p\u003e \u003cp\u003eThis study aims to optimize and validate the fresh and hardened properties of self-compacting concrete (SCC) incorporating binary and ternary blends of ordinary Portland cement (OPC), glass powder (GP), and natural pozzolana (PZ) using an artificial neural network (ANN) approach. The work seeks to forecast fresh features, including slump flow and V-funnel time, for SCC compositions including OPC, GP, and PZ by using ANN models trained on an extensive library of diverse mixes. Furthermore, it aims to predict hardened qualities such as compressive strength, flexural strength, water absorption, porosity, and ultrasonic pulse velocity (UPV), while also assessing the CO₂ emissions linked to these mixes.\u003c/p\u003e \u003cp\u003eThis study utilises the predictive capabilities of artificial neural networks (ANNs) to optimise the ratios of additional elements in self-compacting concrete (SCC), enhancing its flowability, segregation resistance, and overall workability. The research seeks to optimise the design process for structural applications by discovering high-performance mix designs, therefore minimising material waste and decreasing dependence on laborious experimental testing. This method improves the efficiency and sustainability of SCC manufacturing, fostering eco-friendly building practices.\u003c/p\u003e"},{"header":"2. Methodology","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Experimental Design and Data Collection\u003c/h2\u003e \u003cp\u003eThis study used 10 self-compacting mortar (SCM) mixes produced via laboratory trials to train and evaluate artificial neural network (ANN) models.. The goal was to anticipate and optimise the rheological, mechanical, and durability characteristics of SCM using Ordinary Portland Cement (OPC), Glass Powder (GP), and Natural Pozzolana (PZ) as cementitious materials. The experimental dataset served as a foundation for training the ANN model, resulting in a reliable and data-driven study of the effects of various mineral admixtures. The SCM mixes were designed to examine both fresh-state and hardened-state characteristics, allowing for a full understanding of material behaviour. The qualities in the fresh condition were examined using slump flow and V-funnel flow tests, which provide information about workability and viscosity. The hardened-state measurements comprised compressive strength (CS28), flexural strength (FS28), ultrasonic pulse velocity (UPV), water absorption, and porosity.\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e shows the experimental findings from these studies, including the quantities of OPC, GP, and PZ and their influence on SCM properties. It should also be mentioned that the sand content and superplasticizer dose were maintained consistently throughout all mixes to guarantee uniformity in the assessment of cementitious material properties.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eExperimental mix proportions and their effects on studied parameters\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"12\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c12\" colnum=\"12\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOPC\u003c/p\u003e \u003cp\u003e(%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGP\u003c/p\u003e \u003cp\u003e(%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePZ\u003c/p\u003e \u003cp\u003e(%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSand\u003c/p\u003e \u003cp\u003e(Kg/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSP\u003c/p\u003e \u003cp\u003e(%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSlump (cm)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eV-funnel (s)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eCS28 (MPa)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eFS28 (MPa)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c10\"\u003e \u003cp\u003eUPV\u003c/p\u003e \u003cp\u003e(m/s)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c11\"\u003e \u003cp\u003eAbsorption (%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c12\"\u003e \u003cp\u003ePorosity (%)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\" morerows=\"9\" rowspan=\"10\"\u003e \u003cp\u003e1830.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"9\" rowspan=\"10\"\u003e \u003cp\u003e0.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e3.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e4080\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e32.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e47\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e4100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e32.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e2.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e4150\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e3850\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e31\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e3.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e47\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e4.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e4130\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e17.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e4.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e4200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e5.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e4.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e3950\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e31.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e3.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e4100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e32.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e2.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5.15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e4300\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e2.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e4000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Artificial Neural Network (ANN) Model Development\u003c/h2\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e illustrates the architecture of the ANN model employed in this study, comprising three input layers (denoting the proportions of cement, glass powder, and natural pozzolana), 5 hidden layers, and 7 output layers that forecast the fresh and hardened properties of self-compacting mortar (SCM). The hyperbolic tangent (tanH) function is the activation function adopted in this work. It was applied to the hidden layers to increase non-linearity and improve the ANN model's predictive accuracy. ANN models were constructed and trained using the k-fold cross-validation technique to assess the reliability and performance of a predictive model. It involves dividing the dataset into k equal subsets, where the model is trained on k-1 subsets and tested on the remaining one. This process is repeated k times, ensuring that each subset serves as the validation set once. By systematically rotating the validation set, this method provides a thorough evaluation of the model\u0026rsquo;s ability to generalize and aids in detecting potential overfitting (Mellios et al., 2023).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Mixture Design Approach\u003c/h2\u003e \u003cp\u003eThis study explores the effects of ordinary Portland cement (OPC), glass powder (GP), and natural pozzolana (PZ), both individually and in combination, on the rheological and mechanical properties of self-compacting mortar (SCM). A simplex-lattice mixture design, based on a triangular grid with three components, was employed to evaluate their interactions, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The total number of experimental combinations is determined using the following equation.\u003cdiv id=\"Equ1\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ1\" name=\"EquationSource\"\u003e\n$$\\:C=\\frac{(m+q-1)!}{m!(q-1)!}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e1\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eWhere, \u003cem\u003em\u003c/em\u003e and \u003cem\u003eq\u003c/em\u003e represent the number of levels and factors, respectively. With 10 levels and 3 factors, the number of combinations to be treated is 66. To evaluate the effects of different proportions and combinations of OPC, GP, and PZ on the targeted properties of SCM, a second-degree model was applied. As expressed in Eq.\u0026nbsp;\u003cspan refid=\"Equ2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, this model facilitates the prediction and analysis of how variations in OPC, GP, and PZ content influence both the fresh and hardened properties of SCM.\u003cdiv id=\"Equ2\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ2\" name=\"EquationSource\"\u003e\n$$\\:Y={b}_{1}\\times\\:OPC+\\:{b}_{2}\\times\\:\\text{G}\\text{P}+\\:{b}_{3}\\times\\:PZ+{b}_{4}\\times\\:\\left(OPC\\bullet\\:GP\\right)+{b}_{5}\\times\\:\\left(OPC\\bullet\\:PZ\\right)+{b}_{6}\\times\\:\\left(GP\\bullet\\:PZ\\right)$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e2\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eWhere \u003cem\u003eY\u003c/em\u003e represents the output obtained from ANN models used to predict the fresh and hardened properties of SCM. The coefficients \u003cem\u003eb\u003csub\u003ei\u003c/sub\u003e\u003c/em\u003e, determined through a standard least-square fitting process, serve as model parameters that contribute to these predictions. The values of these coefficients are provided in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe ternary plot visually represents a mixture composed of three components: OPC, GP, and PZ, with each vertex corresponding to one of these pure components. The proportion of each component within the mixture is determined by referencing the axis labeled with the color associated with that specific component. To determine the proportion of a given component, a line is drawn through the point representing the desired composition, running parallel to the base opposite the vertex of the selected pure component, as illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results and discussion","content":"\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e shows the findings of the Artificial Neural Network (ANN) model used for self-compacting mortar (SCM) and parameter estimation, which show high predictive skills for the majority of parameters. The model demonstrates high accuracy in fresh-state properties, exhibiting R\u0026sup2; values of 0.95 for slump flow and 0.97 for V-funnel time, which indicates a strong correlation with experimental data. Porosity (R\u0026sup2; = 0.90) and absorption (R\u0026sup2; = 0.79) demonstrate significant correlations, affirming the effectiveness of the ANN in describing the impact of glass powder (GP) and pozzolana (PZ) on microstructural improvement. The model demonstrates limited predictive capability for ultrasonic pulse velocity (UPV) (R\u0026sup2; = 0.47), indicating intricate relationships between microstructural densification and wave propagation. The root mean square error (RMSE) values confirm the model's accuracy, especially in slump flow (0.4607) and V-funnel time (0.1407), thereby confirming its capacity to predict workability trends in SCM.\u003c/p\u003e \u003cp\u003eThe regression coefficients explain the contributions of GP and PZ to SCM properties. GP significantly improves fluidity and decreases viscosity, as confirmed by its positive effect on slump flow (b2\u0026thinsp;=\u0026thinsp;33.75 cm) and its adverse effect on V-funnel time (b5 = -1.18, b6 = -3.56). PZ enhances mechanical properties by increasing compressive strength (b3\u0026thinsp;=\u0026thinsp;44.20 MPa) and flexural strength (b3\u0026thinsp;=\u0026thinsp;6.22 MPa) through its pozzolanic reactivity, leading to long-term strength development. Excessive replacement levels negatively affect mechanical performance, as indicated by the negative b6 coefficient for compressive strength (-14.97 MPa).\u003c/p\u003e \u003cp\u003eMicrostructural analysis indicates that PZ is more influential in reducing porosity compared to GP, leading to a denser material matrix and enhanced durability. The ANN model demonstrates effective prediction of most SCM properties; however, its reduced accuracy for UPV indicates the need for further improvement, potentially through the incorporation of additional training data or the utilization of advanced AI techniques.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eANN model performance and regression coefficients\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"8\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSlump (cm)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eV-funnel (s)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCS28 (Mpa)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eFS28 (Mpa)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eUPV\u003c/p\u003e \u003cp\u003e(m/s)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAbsorption (%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003ePorosity (%)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eR\u0026sup2;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.47\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.90\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRMSE\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.4607\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.1407\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.1686\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.4444\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e98.157\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.9536\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.4547\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eP-value\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eb1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e32.5668\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3.2207\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e39.3714\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.8046\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e3984.9785\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e18.6865\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e20.3953\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eb2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e33.7460\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.2758\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e43.7045\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4.2205\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e3943.5407\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e19.9426\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e19.3255\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eb3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e25.6255\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5.5338\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e44.1970\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e6.2258\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e3993.5302\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e19.6498\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e18.0670\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eb4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e-1.2291\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e-0.1157\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e27.1078\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e5.4263\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e336.6598\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e-13.6533\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e-17.1337\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eb5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.1736\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e-1.1826\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e23.0376\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-0.0330\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e136.9164\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e-10.0467\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e-10.7314\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eb6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4.5854\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e-3.5571\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e-14.9710\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.9429\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1329.4223\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e-29.1227\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e6.3590\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Rheological Properties\u003c/h2\u003e \u003cp\u003eThe ternary diagrams presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e illustrate how the combination of cement, glass powder (GP), and natural pozzolan influences the slump flow of a self-compacting mortar mixture, specifically measured by the mini-cone slump test. As the proportion of glass powder increases in the mixture, the slump flow also increases. This improvement is mainly due to the fine nature of glass powder particles, which are smooth and have low porosity [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. These characteristics help optimize the packing density of the mixture, reducing internal friction between the particles. Furthermore, glass powder has relatively low pozzolanic reactivity at early hydration stages, allowing the mixture to retain a portion of free water. This retained water enhances the flowability of the concrete, making it more workable. Kumarappan N [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e], confirms that incorporating more glass powder into the mix leads to increased slump values, which reflects improved fluidity. However, when pozzolan is introduced into the mix, a reduction in fluidity is observed. Pozzolan, which is a volcanic ash or similar material, has a tendency to absorb water and form bonds with calcium hydroxide in the mixture. This interaction decreases the amount of available water in the mix, reducing its fluidity. To maintain the desired fluidity, more superplasticizer is required. Since pozzolan particles are less easily dispersed compared to mortar with 100% cement and glass powder, they require more superplasticizer to maintain the same level of fluidity.\u003c/p\u003e \u003cp\u003eSeveral studies, [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e], have shown that the presence of natural pozzolan in self-compacting concrete leads to a decrease in fluidity. This is consistent with the current findings, where the introduction of pozzolan necessitates higher SP dosages to achieve similar workability. Despite this, when glass powder is combined with pozzolan, a synergistic effect occurs. The presence of glass powder helps to counteract the negative effect of pozzolan on fluidity. For example, the slump flow of the mixture increases from 31 cm with 5% pozzolan to 32.5 cm when 10% glass powder is added. This combination is particularly beneficial when higher pozzolan contents are used, such as 15%, where the deformability of the mix could otherwise be compromised. Sharifi et al. [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e] examined the effectiveness of recycled glass in the form of fine aggregates in self-compacting concrete mixtures. The results indicate that fluidity characteristics were enhanced as glass waste was incorporated into the mix.\u003c/p\u003e \u003cp\u003eThe synergistic effect of these two materials ensures that the mix remains fluid, homogeneous, and stable, even when the pozzolan content is relatively high. This approach could offer ease of placement in concrete mix design.\u003c/p\u003e \u003cp\u003eThe ternary contour plot in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e demonstrates the effect of varying proportions of glass powder and natural pozzolan on the flow time of self-compacting mortar. As the PZ content increases, there is a corresponding rise in flow time, approaching the upper limit specified by EFNARC guidelines. Mortars with 15% PZ require higher dosages of superplasticizer (SP) to maintain flowability, particularly in confined spaces, to avoid potential blockages. This can be attributed to stronger interparticle interactions, which lead to increased internal friction and resistance to deformation [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. Similar findings were reported by Belaidi et al [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]., who observed an increase in viscosity with higher amounts of natural pozzolan.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eConversely, the inclusion of GP is shown to reduce the flow time compared to mortars containing only PZ. The presence of GP also decreases the amount of SP needed to maintain the self-compacting properties of the mortar. Mortars with 15% GP exhibit a more fluid consistency and require less SP than those with only cement and PZ. This can be explained by the role of fine glass powder particles in enhancing the compactness of the cementitious matrix, which reduces internal friction and improves the mixture's flowability [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. Additionally, the smooth, non-porous surface of glass powder minimizes water absorption, ensuring that more free water is available to optimize fluidity.\u003c/p\u003e \u003cp\u003eThe combination of GP and PZ results in reduced flow times and lower overall viscosity in the mixtures. Mortars with higher GP content display flow times ranging from 3 to 4 seconds. These findings align with previous research, which suggested that incorporating GP into PZ mixtures, especially in larger proportions, mitigates the negative impact of PZ on flow time and viscosity, ultimately enhancing the ease of handling of the mixture.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Hardened-State Performance\u003c/h2\u003e \u003cp\u003eTernary contour plots shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e illustrate the evolution of flexural strength of the different mortar models at 28 days. According to the figure, the mortar mix without PZ and GP exhibits low flexural strength. However, when PZ and GP are incorporated as cementitious additions, the tensile strength increases. The improvement in the flexural strength of self-compacting mortar (SCM) in the presence of glass powder (GP) and natural pozzolan (PZ) results from several synergistic mechanisms. On the one hand, both materials exhibit pozzolanic activity, allowing them to interact with the portlandite (Ca(OH)₂) released during cement hydration, leading to the additional formation of calcium silicate hydrates (C-S-H) [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. These phases contribute to the densification of the cementitious matrix and the enhancement of mechanical performance. On the other hand, the mortar's microstructure becomes more compact due to reduced porosity, limiting crack propagation and strengthening the material\u0026rsquo;s overall cohesion.\u003c/p\u003e \u003cp\u003eThe incorporation of GP and PZ also improves the adhesion between the cement paste and aggregates, delaying crack initiation under stress. Furthermore, the presence of glass powder plays a filler role, enhancing the mixture\u0026rsquo;s compactness and reducing water demand, which improves cohesion and mortar strength [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFinally, the combination of the pozzolanic effects of PZ with the reactive and filler properties of GP optimizes the mortar\u0026rsquo;s characteristics, resulting in a more homogeneous and durable structure. This pattern of flexural strength enhancement has been observed in several previous studies [\u003cspan additionalcitationids=\"CR24\" citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e].\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e illustrates the variation in compressive strength of different models of SCM mixtures at 28 days. The results indicate a relative increase in compressive strength with the incorporation of both natural pozzolan and glass powder, with an optimum content of 15% for both binary and ternary cementitious systems. At 28 days, the compressive strength of the reference MAP mixture is 40 MPa, which improves to 48 MPa and 45 MPa with the introduction of 10% GP and 5% PZ as a binary cementitious addition. This enhancement in compressive strength at 28 days with binary and ternary cementitious additions can be attributed to the pozzolanic reaction with Ca(OH)2 over the long-term [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e, \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eBelaidi et al [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]. observed a similar effect of pozzolan on the development of compressive strength in six self-compacting mortar mixtures containing pozzolan at different replacement levels of 0%, 5%, 10%, 15%, 20%, and 25%. They reported an increase in strength at 90 days with a higher pozzolan content during the advanced hydration stages, with an optimum of 20%.\u003c/p\u003e \u003cp\u003eThe increase in compressive strength observed in the mixtures incorporating GP can be explained, on the one hand, by the enhanced pozzolanic reaction between SiO2 and CaO from the glass powder present in the pore solution and CH grains, as reported by Elaqra et al. [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Additionally, the filler effect contributes to a denser microstructure by reducing total porosity. However, the pozzolanic reaction of PZ led to a more significant strength improvement compared to GP due to its combined pozzolanic and pore-filling effects. Furthermore, as observed in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e, the addition of PZ in the mixtures containing GP as a cementitious additive resulted in higher compressive strength compared to mixtures incorporating GP alone as a binary cementitious addition. The reference SCM mixture achieved a compressive strength of 40 MPa. This enhancement can be attributed to the pozzolanic reaction of PZ, which compensates for the long-term strength development. This improvement in compressive strength may also be due to the presence of pozzolanic compounds (PZC), which penetrate and fill the pores, thus contributing to an improved interfacial transition zone (ITZ) between pozzolanic aggregates and the cement paste [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eGhrici et al. [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e] also demonstrated that incorporating 10% limestone fillers with a low amount of natural pozzolan positively influences early-age compressive strength. However, beyond 28 days, a beneficial effect was observed with a high pozzolan content and a low amount of limestone fillers.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e3.3 Microstructural integrity and durability assessment\u003c/h2\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003e illustrates the evolution of water absorption in different formulations over time. The results indicate a general trend of decreasing absorption rates over time for all the studied mixtures. This progressive reduction can be attributed to the continued hydration of cementitious components and the densification of the material\u0026rsquo;s microstructure.\u003c/p\u003e \u003cp\u003eHowever, a comparative analysis of the different formulations reveals that mixtures incorporating binary cements, whether containing PZ or GP, exhibit higher absorption coefficients compared to ternary cements. This difference can be explained by the nature and reactivity of the cementitious additions used. In binary cement, although the partial replacement of OPC with PZ or GP contributes to improving properties of SCM, it can also lead to increased porosity in the short term due to a slower hydration rate and less pronounced densification [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]. Conversely, formulations based on ternary cement show lower water absorption, suggesting better matrix compactness. This improved performance is likely due to the synergistic effect between PZ and GP, which promotes a more effective pozzolanic reaction and reduces capillary porosity [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e, \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]. Indeed, the combined incorporation of these two mineral additions helps fill residual pores and optimize the material\u0026rsquo;s microstructure, thereby limiting water penetration and enhancing the durability of self-compacting mortar [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]. Hossain et al [\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e] examined the influence of an alkali-activated ternary blended binder on water absorption. The results indicate that water transport properties can be improved with ternary cement. These observations confirm that the combined use of PZ and GP in ternary cement is an effective strategy to improve resistance to liquid penetration and, consequently, the durability of self-compacting mortars.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe results presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e8\u003c/span\u003e clearly show that as the incorporation of PZ and GP increases in the self-compacting mortar, the velocity of sound waves increases. This improvement reaches an optimum when the proportion of these materials is 10%. This trend suggests that the addition of binary and ternary cement in the mortar composition optimizes the acoustic properties of the material, particularly by increasing the UGP values, which can be interpreted as a sign of better homogeneity and densification of the mortar.\u003c/p\u003e \u003cp\u003eIt was also observed that the UGP values of the mixtures with PZ and GP are higher than those of the OPC. These results indicate that the addition of these materials increases the efficiency of the hardening process of the mortar while optimizing its mechanical and acoustic performances. This phenomenon is particularly noticeable with the incorporation of PZ and GP, which play a key role in densifying the cement microstructure.\u003c/p\u003e \u003cp\u003eMoreover, the study highlights the effect of GP and PZ in refining the pores within the cement matrix and in the interfacial transition zone (ITZ). PZ, in particular, proves to be a beneficial material for improving cement density, especially when compared to GP. This can be explained by PZ\u0026rsquo;s ability to participate in the pozzolanic reaction, which generates additional calcium silicate hydrate (C\u0026ndash;S\u0026ndash;H) in the micro-cracks within the structure [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e]. This process not only fills the pores but also reduces the porosity of the material.\u003c/p\u003e \u003cp\u003eThe combination of these effects, namely the pore-filling capacity of PZ and GP and the additional generation of C\u0026ndash;S\u0026ndash;H, contributes to a reduction in the material\u0026rsquo;s porosity. Ultimately, this improves the mechanical and acoustic properties of the mortar by increasing the UGP values, reflecting better structural integrity and greater resistance to sound wave propagation. These results confirm the importance of using binary and ternary cements, not only to improve the mechanical characteristics of the mortar but also to optimize its overall physical properties.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e9\u003c/span\u003e demonstrates the influence of PZ (Pozzolana) and GP on the porosity of self-compacting mortar mixtures. The data indicates that the inclusion of both GP and PZ results in a noticeable decrease in the void volume of the mortar. This reduction in porosity is mainly driven by two factors. Firstly, the fine particle size of GP and PZ plays a significant role in filling the existing voids within the mortar matrix. These finer particles act as a filler, occupying spaces that would otherwise remain unfilled, thereby contributing to a more compact and dense structure[\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]. Secondly, the pozzolanic reaction between the PZ and GP with the available calcium hydroxide (CH) in the mortar further contributes to this densification process [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]. As the pozzolanic materials react with CH, they form additional hydration products, most notably calcium silicate hydrate (C\u0026ndash;S\u0026ndash;H), which plays a critical role in refining the microstructure of the mortar. These additional products help to bond the particles more effectively, filling micro-cracks and voids within the matrix. The formation of C\u0026ndash;S\u0026ndash;H not only improves the density of the material but also enhances its durability and overall structural integrity [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eBy reducing the porosity, the mortar\u0026rsquo;s resistance to water penetration and other environmental factors is improved, which ultimately leads to better long-term performance. Moreover, the reduced void volume also implies enhanced mechanical properties, such as increased strength and stiffness, due to the more densely packed structure. Therefore, the combination of fine particles filling voids and the formation of additional C\u0026ndash;S\u0026ndash;H provides a highly effective mechanism for optimizing the physical properties of self-compacting mortar.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003e3.4 Environmental sustainability\u003c/h2\u003e \u003cp\u003eThe environmental impact assessment of a project means the quantitative estimation of the various positive and negative changes affecting the environment as a result of its creation. This evaluation considers all the environmental effects and impacts related to the activities of the studied project, based on the estimation of certain evaluation indicators, which are mentioned in the final reports. Thus, the evaluation indicators of impacts are presented separately in this study [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe study of carbon dioxide (CO\u003csub\u003e2\u003c/sub\u003e) emissions into the atmosphere and energy consumption was calculated using the following equation:\u003cdiv id=\"Equa\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equa\" name=\"EquationSource\"\u003e\n$$\\:\\frac{\\text{C}\\text{i}-\\text{C}\\text{o}\\:}{\\text{C}\\text{o}}x100$$\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eWhere:\u003c/p\u003e \u003cp\u003eCi: CO\u003csub\u003e2\u003c/sub\u003e emissions for mixtures of SCM mixed with PZ and GP (i\u0026thinsp;=\u0026thinsp;PZ5, PZ10, PZ15, GP5, GP10, GP15, PZ5\u0026thinsp;+\u0026thinsp;GP5, PZ5\u0026thinsp;+\u0026thinsp;GP10, and PZ5\u0026thinsp;+\u0026thinsp;15GP);\u003c/p\u003e \u003cp\u003eC0: CO\u003csub\u003e2\u003c/sub\u003e emissions for the mixture with 100% OPC.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eCO\u003csub\u003e2\u003c/sub\u003e emissions for all SCM elaborated.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"11\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMix\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eControl\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5GP\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e10GP\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e15GP\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003e5PZ\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003e10PZ\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003e15PZ\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5GP\u0026thinsp;+\u0026thinsp;5PZ\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c10\"\u003e \u003cp\u003e10GP\u0026thinsp;+\u0026thinsp;5PZ\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c11\"\u003e \u003cp\u003e15GP\u0026thinsp;+\u0026thinsp;5PZ\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCO\u003csub\u003e2\u003c/sub\u003e emissions (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e-4.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e-8.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-12.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e-5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e-8.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e-13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e-8.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e-12.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e-14.2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eAs illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e, which presents the CO\u003csub\u003e2\u003c/sub\u003e emissions and energy consumption for each cubic meter of self-compacting mortar (SCM), substituting a portion of cement with PZ and glass powder results in a significant reduction in both CO\u003csub\u003e2\u003c/sub\u003e emissions and energy consumption. The data reveals that CO\u003csub\u003e2\u003c/sub\u003e emissions decreased by an impressive range of \u0026minus;\u0026thinsp;5% to \u0026minus;\u0026thinsp;13. %, depending on the level of binary substitution of GP and PZ. Similarly, the Co2 emission is reduced by -8.5\u0026ndash;14% as the amount of cement replaced by the ternary substitution with PZ and GP increases. This reduction can be attributed to the beneficial properties of PZ and glass powder, which, through their pozzolanic and filling effects, contribute to enhancing overall material performance while requiring less energy during production. When comparing the two mixtures\u0026mdash;one with cement alone and the other with cement partially substituted by PZ and GP it is evident that the latter composition results in the greatest environmental benefit. The substitution of traditional cement with these supplementary materials not only reduces the carbon footprint but also contributes to energy savings, making this approach much more sustainable from an environmental perspective.\u003c/p\u003e \u003cp\u003eThe integration of PZ and glass powder aligns with the principles of sustainability by reducing the environmental impact associated with cement production. By lowering both CO\u003csub\u003e2\u003c/sub\u003e emissions and energy consumption, this substitution process contributes to a more eco-friendly and sustainable approach to construction materials. Such innovations are crucial for advancing sustainable construction practices and reducing the carbon footprint of the construction industry, which is one of the major contributors to global emissions. The integration of PZ and glass powder in cementitious composites offers a viable approach for developing more sustainable and ecologically conscientious construction materials. This substitute technique alleviates the environmental effects of cement manufacture and coincides with overarching sustainability goals, representing a crucial advancement in eco-friendly building practices.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"4. Conclusion","content":"\u003cp\u003eThis study illustrates the efficient use of PZ and GP as binary and ternary cementitious additives in self-compacting mortar (SCM), providing a novel method for enhancing material performance and sustainability. Artificial Neural Networks (ANN) were used as an effective instrument for modelling and analysing the behaviour of mixes, facilitating a thorough comprehension of the influence of these additions on the characteristics of mortar. The main findings of this research are as follows:\u003c/p\u003e \u003cp\u003e \u003col\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eThe application of ANN in this study enabled the identification of optimal parameters for the formulation of reference SCM, including the water-to-cement ratio (W/C) and sand-to-material ratio (S/M). This provided a more efficient way to design SCM mixtures that meet the desired mechanical and flow properties, using locally sourced materials.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eAdding GP to the SCM mix significantly improved flowability, passing ability, and filling capacity. ANN models projected that these enhancements would minimise the requirement for superplasticizers, resulting in a more efficient use of resources while preserving the workability required for large-scale applications.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eA significant finding of the study is that replacing part of regular Portland cement with PZ and GP reduces the environmental impact of the mortar. This substitution lowers CO2 emissions from cement production, fostering greener and more sustainable construction practices. Although the introduction of PZ and GP resulted in a slight decrease in tensile and compressive strength compared to the reference SCM, the benefits in workability and environmental performance make these modified mixtures viable for specific construction uses. Furthermore, the addition of PZ to ternary cementitious mixes increased compressive strength in some formulations.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eA reduction in water absorption was observed with higher dosages of PZ and GP, suggesting that these additives contribute to better long-term durability. Moreover, ANN analysis revealed that an increase in the amount of PZ and GP also led to a reduction in porosity, which improved the material\u0026rsquo;s density and resistance to external influences, such as moisture.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eUGP testing indicated that the inclusion of PZ and GP positively influenced the integrity and uniformity of the SCM. The ANN model was able to predict these improvements accurately, reflecting an enhanced structural cohesion and greater durability of the mortar. These findings highlight the potential of these additives to contribute to high-performance construction materials.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003c/ol\u003e \u003c/p\u003e \u003cp\u003eThe integration of PZ and GP as ternary cementitious additives, bolstered by ANN modelling, presents a sustainable and efficient alternative to conventional mortar formulations. This method reduces the environmental impact of cement-based products while simultaneously improving their durability and performance, so making a substantial contribution to sustainable building methods.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eYounes Ouldkhaoua: Conceptualization, Methodology and Writing Mohamed Sahraoui: Formal Analysis and MethodologyZine El-Abiddine Laidani: Methodology and Validation Benchaa Benabed: Conceptualization and SupervisorRajab abousnina: Review and EditingMohamed El-ghazali Balgacem : Review and Editing,\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eM. Bergonzoni, R. Melloni, L. Botti, Analysis of sustainable concrete obtained from the by-products of an industrial process and recycled aggregates from construction and demolition waste, Procedia Computer Science 217 (2023) 41-51.\u003c/li\u003e\n\u003cli\u003eL. Becchetti, D.M. Bova, L. Raffaele, Win together or lose alone: Circular economy and hybrid governance for natural resource commons, Journal of Cleaner Production 486 (2025) 144520.\u003c/li\u003e\n\u003cli\u003eH.S. Hassan, C. Shi, F.S. Hashem, S.A. El-Magd, A. Maged, H.A. Abdel-Gawwad, H. Pfeiffer, Industrial waste recycling approach: An ecofriendly geopolymer binder for clean and sustainable environments (A 24-h green recycling process), Journal of Environmental Management 377 (2025) 124568.\u003c/li\u003e\n\u003cli\u003eM. Ulewicz, Recycled Materials in Civil Engineering Application, MDPI, 2023, p. 7075.\u003c/li\u003e\n\u003cli\u003eA. Alshahrani, Towards sustainable construction: experimental approach and multi-scale simulation in high-strength self-compacting concrete design, Cardiff University, 2024.\u003c/li\u003e\n\u003cli\u003eM. Hosseinpoor, Numerical Simulation of Fresh SCC Flow in Wall and Beam Elements Using Flow Dynamics Models, University of Sherbrooke, 2017.\u003c/li\u003e\n\u003cli\u003eJ. Ahmad, Z. Zhou, A.F. Deifalla, Steel fiber reinforced self-compacting concrete: a comprehensive review, International Journal of concrete structures and materials 17(1) (2023) 51.\u003c/li\u003e\n\u003cli\u003eK. Sobolev, M. Kozhukhova, K. Sideris, E. Men\u0026eacute;ndez, M. Santhanam, Alternative supplementary cementitious materials, Properties of Fresh and Hardened Concrete Containing Supplementary Cementitious Materials: State-of-the-Art Report of the RILEM Technical Committee 238-SCM, Working Group 4 (2018) 233-282.\u003c/li\u003e\n\u003cli\u003eK.C. Onyelowe, D.-P.N. Kontoni, The net-zero and sustainability potential of SCC development, production and flowability in concrete structures, International Journal of Low-Carbon Technologies 18 (2023) 530-541.\u003c/li\u003e\n\u003cli\u003eM. Perera, P. Ranjith, Eco-friendly cementitious composites for enhanced strength: Emerging trends and innovations, Journal of Cleaner Production 468 (2024) 142962.\u003c/li\u003e\n\u003cli\u003eA. Alhamad, S. Yehia, \u0026Eacute;. Lubl\u0026oacute;y, M. Elchalakani, Performance of different concrete types exposed to elevated temperatures: a review, Materials 15(14) (2022) 5032.\u003c/li\u003e\n\u003cli\u003eM.A. Hossain, G.S. Islam, A. Mallick, Compressive strength prediction for industrial waste-based scc using artificial neural network, Journal of the Civil Engineering Forum, 2022, pp. 11-26.\u003c/li\u003e\n\u003cli\u003eL. Li, C. Deng, Y. Zhou, Q. Tan, W. Yan, D. Zhou, Y. Zhou, Stability and Rheological Properties of Grouts with Waste Glass Powder as Cement Replacement: Influences of Content and Alkali Activator, Materials 18(2) (2025) 353.\u003c/li\u003e\n\u003cli\u003eN. Kumarappan, Partial replacement cement in concrete using waste glass, International Journal of Engineering Research and Technology 2(10) (2013) 1880-1883.\u003c/li\u003e\n\u003cli\u003eK. Celik, C. Meral, M. Mancio, P.K. Mehta, P.J. Monteiro, A comparative study of self-consolidating concretes incorporating high-volume natural pozzolan or high-volume fly ash, Construction and Building materials 67 (2014) 14-19.\u003c/li\u003e\n\u003cli\u003eS. Kenai, B. Menadi, A. Debbih, E.H. Kadri, Effect of recycled concrete aggregates and natural pozzolana on rheology of self-compacting concrete, Key Engineering Materials 600 (2014) 256-263.\u003c/li\u003e\n\u003cli\u003eY. Sharifi, M. Houshiar, B. Aghebati, Recycled glass replacement as fine aggregate in self-compacting concrete, Frontiers of Structural and Civil Engineering 7(4) (2013) 419-428.\u003c/li\u003e\n\u003cli\u003eB. Cheng, L. Mei, W.-J. Long, S. Kou, L. Li, S. Geng, Ai-guided proportioning and evaluating of self-compacting concrete based on rheological approach, Construction and Building Materials 399 (2023) 132522.\u003c/li\u003e\n\u003cli\u003eA. Belaidi, L. Azzouz, E. Kadri, S. Kenai, Effect of natural pozzolana and marble powder on the properties of self-compacting concrete, Construction and Building Materials 31 (2012) 251-257.\u003c/li\u003e\n\u003cli\u003eW. Chen, D. Liu, Y. Liang, Influence of Ultra Fine Glass Powder on the Properties and Microstructure of Mortars, Fluid Dynamics \u0026amp; Materials Processing 20(5) (2024).\u003c/li\u003e\n\u003cli\u003eE. Haustein, S. Kalisz, Early-Age Hydration Reaction of Cement Mortars with the Participation of Aluminosilicate Microsphere Fractions, Journal of Materials in Civil Engineering 37(4) (2025) 04025044.\u003c/li\u003e\n\u003cli\u003eZ. Lai, Y. Chen, Enhancing the mechanical and environmental performance of solidified soil using construction waste and glass micro-powder, Heliyon 10(22) (2024).\u003c/li\u003e\n\u003cli\u003eG. Lee, T.-C. Ling, Y.-L. Wong, C.-S. Poon, Effects of crushed glass cullet sizes, casting methods and pozzolanic materials on ASR of concrete blocks, Construction and Building Materials 25(5) (2011) 2611-2618.\u003c/li\u003e\n\u003cli\u003eT.-C. Ling, C.-S. Poon, Properties of architectural mortar prepared with recycled glass with different particle sizes, Materials \u0026amp; Design 32(5) (2011) 2675-2684.\u003c/li\u003e\n\u003cli\u003eT.-C. Ling, C.-S. Poon, Utilization of recycled glass derived from cathode ray tube glass as fine aggregate in cement mortar, Journal of Hazardous Materials 192(2) (2011) 451-456.\u003c/li\u003e\n\u003cli\u003eA. Mohammed, A. Salih, H. Raof, Vipulanandan constitutive models to predict the rheological properties and stress\u0026ndash;strain behavior of cement grouts modified with metakaolin, Journal of Testing and Evaluation 48(5) (2020).\u003c/li\u003e\n\u003cli\u003eM.I.C. Sousa, J.H. da Silva R\u0026ecirc;go, Mechanical Strength Analysis of Ternary Cement Pastes Containing Nanosilica and Metakaolin, Proceedings of the International Conference of Sustainable Production and Use of Cement and Concrete, Springer, 2020, pp. 59-67.\u003c/li\u003e\n\u003cli\u003eA.S.E. Belaidi, S. Kenai, E.-H. Kadri, H. Soualhi, B. Bencha\u0026acirc;, Effects of experimental ternary cements on fresh and hardened properties of self-compacting concretes, Journal of adhesion science and Technology 30(3) (2016) 247-261.\u003c/li\u003e\n\u003cli\u003eH. Elaqra, R. Rustom, Effect of using glass powder as cement replacement on rheological and mechanical properties of cement paste, Construction and Building Materials 179 (2018) 326-335.\u003c/li\u003e\n\u003cli\u003eR. Muduli, B.B. Mukharjee, Characteristics of Concrete Prepared with Metakaolin and Recycled Coarse Aggregates, Advances in Sustainable Construction Materials and Geotechnical Engineering, Springer2020, pp. 73-85.\u003c/li\u003e\n\u003cli\u003eM. Ghrici, S. Kenai, M. Said-Mansour, Mechanical properties and durability of mortar and concrete containing natural pozzolana and limestone blended cements, Cement and Concrete Composites 29(7) (2007) 542-549.\u003c/li\u003e\n\u003cli\u003eO. Semmana, M.A.M. Rihan, Z.M. Barrie, C. Daniel, T.A. Abdalla, A Systematic Review of the Strength, Durability, and Microstructure Properties of Concrete Incorporating Glass Powder, Engineering Reports 7(1) (2025) e70002.\u003c/li\u003e\n\u003cli\u003eA. Adesina, S. Das, Influence of glass powder on the durability properties of engineered cementitious composites, Construction and Building Materials 242 (2020) 118199.\u003c/li\u003e\n\u003cli\u003eJ. Esmaeili, A.O. AL-Mwanes, A review: Properties of eco-friendly ultra-high-performance concrete incorporated with waste glass as a partial replacement for cement, Materials Today: Proceedings 42 (2021) 1958-1965.\u003c/li\u003e\n\u003cli\u003eM.M. Hossain, M.R. Karim, M.M.A. Elahi, M.F.M. Zain, Water absorption and sorptivity of alkali-activated ternary blended composite binder, Journal of Building Engineering 31 (2020) 101370.\u003c/li\u003e\n\u003cli\u003eY. Li, H. Zhang, M. Huang, H. Yin, K. Jiang, K. Xiao, S. Tang, Influence of different alkali sulfates on the shrinkage, hydration, pore structure, fractal dimension and microstructure of low-heat Portland cement, medium-heat Portland cement and ordinary Portland cement, Fractal and Fractional 5(03) (2021) 79.\u003c/li\u003e\n\u003cli\u003eN. Sathiparan, P. Jeyananthan, D.N. Subramaniam, Influence of metakaolin on pervious concrete strength: a machine learning approach with shapley additive explanations, Multiscale and Multidisciplinary Modeling, Experiments and Design 7(4) (2024) 3919-3946.\u003c/li\u003e\n\u003cli\u003eR.A. Medeiros-Junior, M. Thiesen, A.M. Betioli, J.M. Casali, L.F.Z. Trentin, A. Frare, A.G. Bor\u0026ccedil;ato, Influence of Precursor Particle Size and Calcium Hydroxide Content on the Development of Clay Brick Waste-Based Geopolymers, Minerals 14(11) (2024) 1169.\u003c/li\u003e\n\u003cli\u003eF.Y. Al-Saffar, L.S. Wong, S.C. Paul, An elucidative review of the nanomaterial effect on the durability and calcium-silicate-hydrate (CSH) gel development of concrete, Gels 9(8) (2023) 613.\u003c/li\u003e\n\u003cli\u003eM. Medine, Experimental study of lightweight concretes incorporating aggregates from the crushing of used tires, PhD thesis, University Djillali Liab\u0026egrave;s, Sidi Bel-Abas -Algeria, (2018). (In French).\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"asian-journal-of-civil-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Asian Journal of Civil Engineering](https://www.springer.com/journal/42107)","snPcode":"42107","submissionUrl":"https://submission.nature.com/new-submission/42107/3","title":"Asian Journal of Civil Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Self-Compacting Mortar, Pozzolan, Glass Powder, Artificial Neural Networks, Sustainability in Construction","lastPublishedDoi":"10.21203/rs.3.rs-6331374/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6331374/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study aimed to investigate the use of natural pozzolana (PZ) and glass powder (GP) as binary and ternary cementitious materials to improve the sustainability of self-compacting mortar (SCM) for construction purposes. The research assessed PZ and GP's impact on SCM's flowability, mechanical strength, and durability. To do this, artificial neural networks (ANNs) were utilised to model and forecast the behaviour of the materials, offering a comprehensive understanding of how these novel composite materials affect the properties of the mortars. The findings indicated that the inclusion of GP boosted the workability and filling capacity of the mortars. In contrast, PZ improved compressive strength, with both materials exhibiting a synergistic impact when combined in a ternary blend. This combination also resulted in decreased water absorption and porosity; hence, it improved the durability of the SCM. The ANN models accurately forecasted the behaviour of the mortars and their influence on the parameters of the mixtures. The study found that using sustainable cementitious additives instead of PZ and GP improves the quality and performance of mortars while also helping the environment by lowering energy use and CO\u003csub\u003e2\u003c/sub\u003e emissions.\u003c/p\u003e","manuscriptTitle":"Optimizing Sustainable Self-Compacting Mortar Properties Using Natural Pozzolan and Glass Powder as Cementitious Materials: An Artificial Neural Network Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-18 10:08:15","doi":"10.21203/rs.3.rs-6331374/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-13T09:06:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-12T17:11:01+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-05T18:02:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"61522991488332169752042214981558656295","date":"2025-03-31T09:24:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"309554957307657494098654808349800549931","date":"2025-03-29T11:01:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"220008102341306609863604846088654341375","date":"2025-03-29T10:56:55+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-29T10:49:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-29T07:03:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-29T03:09:38+00:00","index":"","fulltext":""},{"type":"submitted","content":"Asian Journal of Civil Engineering","date":"2025-03-29T02:02:52+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"asian-journal-of-civil-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Asian Journal of Civil Engineering](https://www.springer.com/journal/42107)","snPcode":"42107","submissionUrl":"https://submission.nature.com/new-submission/42107/3","title":"Asian Journal of Civil Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"9122c53f-34c2-4659-9bca-37c0f7b9402b","owner":[],"postedDate":"April 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-05-04T12:08:07+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-18 10:08:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6331374","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6331374","identity":"rs-6331374","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}