AI-POWERED INSIGHTS
ANN Trained by BBO for Modeling of Fly Ash Cementitious Systems with High Range Water Reducing Admixtures
Naz Mardani, Ramin Kazemi, Murteda Unverdi, Ali Mardani & Seyedali Mirjalili | Published online: 01 February 2026
This study aims to develop artificial intelligence (AI) models for predicting the compressive strength and flow value of cementitious systems containing fly ash, influenced by various high-range water-reducing admixtures (HRWRAs) that differ in molecular weight and chain length. A database comprising 180 mixes was created, encompassing cement and fly ash dosages, HRWRA characteristics (including molecular weight, main and side chain lengths) curing period, and flow time. Two AI-based modelling approaches were employed: a classical artificial neural network (ANN) and a new hybrid model that integrates ANN with biogeography-based optimisation (ANN-BBO). The modeling results showed that the hybrid model achieved a compressive strength performance with an R² of approximately 0.99 and an RMSE of around 1.37 MPa, while the single ANN model attained an R² of about 0.91 and an RMSE of 4.40 MPa. For flow value prediction, the ANN-BBO_model also demonstrated high accuracy (R² ~ 0.98; RMSE ~ 0.32 cm). Furthermore, the ANN-BBO model reduced the prediction error by approximately 60% across the evaluation criteria compared to the single ANN model, highlighting its enhanced performance. The importance of the input variables indicated that curing time and cement content have the greatest impact on compressive strength, while flow time and the molecular weight of the HRWRA significantly influence the flow value. Since AI models rely solely on virtual trials, they significantly reduce laboratory time and material usage while aiding in the design of mixes with lower water-to-binder ratios and higher fly ash content, which ultimately helps to reduce the CO2 footprint. The proposed models provide a practical route to low-clinker, FA-rich mix designs that satisfy strength/workability targets with less cement, supporting embodied-carbon reductions and straightforward integration into ready-mix/precast quality-control workflows.
Executive Impact
Leveraging advanced AI for cementitious systems offers profound operational and environmental advantages for your enterprise.
0%
CS Prediction Accuracy Boost
0%
FV Prediction Accuracy Boost
0%
Overall Prediction Error Reduction
0%
Lab Time & Material Savings
0%
Potential CO2 Footprint Reduction
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
Overview of AI-Driven Advances
This research successfully developed a hybrid Artificial Neural Network (ANN) model, optimized by Biogeography-Based Optimization (BBO), for predicting the compressive strength (CS) and flow value (FV) of fly ash cementitious systems. The ANN-BBO model significantly outperformed the classical ANN, achieving R² values of 0.99 for CS and 0.98 for FV, and reducing prediction errors by approximately 60%. This AI-driven approach promises substantial reductions in laboratory time, material usage, and CO2 footprint by enabling optimized, low-clinker concrete mix designs.
0
Peak CS Prediction Accuracy
0
Peak Flow Value Prediction Accuracy
0%
Prediction Error Reduction
| Metric | Classical ANN | Hybrid ANN-BBO |
|---|---|---|
| CS R² (Overall) | 0.91 | 0.99 |
| CS RMSE (Overall) | 4.40 MPa | 1.36 MPa |
| FV R² (Overall) | 0.92 | 0.98 |
| FV RMSE (Overall) | 0.74 cm | 0.32 cm |
| Error Reduction | Baseline | ~60% |
0%
Influence of Curing Time on CS
0%
Influence of Flow Time on FV
The analysis of input variable importance revealed that curing time (X6) and cement content (X1) have the greatest impact on compressive strength, contributing 27% and 20% respectively. For flow value, flow time (X7) and the molecular weight of the HRWRA (X3) are the most significant influencers, contributing 30% and 20% respectively. Understanding these key drivers allows for targeted optimization in concrete mix design.
Enterprise Process Flow
Database (180 records)
→
Machine Learning (ANN & ANN-BBO)
→
Evaluation (Metrics)
→
Interpretation (Feature Importance)
Optimizing Sustainable Concrete with AI
Challenge: Traditional concrete mix design is labor-intensive, time-consuming, and often leads to suboptimal material use and higher carbon footprints. The interaction of high-range water-reducing admixtures (HRWRAs) with supplementary cementitious materials like fly ash is complex, making empirical optimization difficult.
AI Solution: The ANN-BBO hybrid model leverages artificial intelligence to predict compressive strength and flow value based on various input parameters, including HRWRA molecular architecture. This enables virtual trials, drastically reducing the need for physical experimentation. The optimization via BBO fine-tunes the ANN, ensuring superior predictive accuracy and robustness.
Impact: By accurately modeling material behavior, this AI solution facilitates the design of low-clinker, high-fly ash content concrete mixes. This directly leads to significant reductions in embodied CO2 emissions and material waste, while simultaneously improving structural performance and workability. The approach supports sustainable construction practices and can be integrated into existing quality control workflows, accelerating the deployment of next-generation concrete.
Strategic Future Directions for AI in Construction
Future work includes broadening the dataset to encompass different cement types (CEM I/II, LC³), wider fly ash ranges, and additional HRWRA families, as well as incorporating data from multi-lab sources to assess domain shift. Benchmarking alternative learners like gradient-boosted trees and transformer-style models with Bayesian/evolutionary hyperparameter search and multi-objective optimization for strength-flow-CO2-cost is also planned. The research aims to quantify uncertainty, couple the surrogate with Life Cycle Assessment (LCA) and Life Cycle Cost Analysis (LCCA), and conduct field trials with active-learning-guided experiments to accelerate deployment into practice. This will allow for the development of multi-SCM surrogates with active learning for performance-carbon optimization.
Calculate Your Potential ROI
Estimate the direct impact of AI-driven optimization on your operational efficiency and cost savings.
Estimated Annual Savings
$0
Annual Hours Reclaimed
0
Your AI Implementation Roadmap
A clear path to integrate these advanced AI solutions into your enterprise operations.
Phase 1: Discovery & Strategy
Comprehensive assessment of your current material science workflows, data infrastructure, and sustainability goals. Define key performance indicators and tailor an AI strategy.
Phase 2: Data Integration & Model Training
Securely integrate existing and new material data. Customize and train the ANN-BBO models to your specific concrete formulations and HRWRA characteristics.
Phase 3: Validation & Optimization
Rigorously validate model predictions against experimental data. Fine-tune parameters for peak accuracy and integrate sustainability metrics like CO2 footprint reduction.
Phase 4: Deployment & Continuous Improvement
Seamlessly integrate the AI prediction engine into your design and quality control systems. Establish monitoring for continuous learning and adaptation to new materials or objectives.
Ready to Transform Your Operations?
Schedule a complimentary consultation with our AI specialists to explore how these insights can be tailored for your business.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat