Bio-based geopolymer concrete, particularly corncob ash concrete, represents a transformative advancement in sustainable construction due to its renewable feedstock utilization and carbon sequestration potential. Accurately predicting the compressive strength of corncob ash concrete is crucial for enhancing design efficiency and reducing costs. This study introduces a data-driven approach to estimating the compressive strength of corncob ash concrete across various component ratios. A dataset of 256 samples was created, and three hybrid random forest (RF) models were developed using optimization methods: termite life cycle optimizer (TLCO), catch fish optimization algorithm (CFOA), and Arctic puffin optimization (APO). Eight input parameters, including corncob ash and fine aggregates, were selected, with compressive strength as the output. Comparative analyses included an unoptimized RF model and a multiple linear regression model. Sensitivity analysis assessed the influence of each input variable on strength estimation. The research results indicate the CFOA-RF model demonstrating the best performance and efficiency, and it has an RMSE of 1.1124 MPa, MAE of 0.8305 MPa, R2 of 0.9917, and VAF of 99.1669 for the training set; and RMSE of 1.2427 MPa, MAE of 0.8440 MPa, R2 of 0.9888, and VAF of 98.8868 for the testing set. CG and W are the key factors influencing the compressive strength of corncob ash concrete. The hybrid CFOA-RF model establishes a robust correlation between compositional variables of corncob ash concrete and its compressive strength, offering a decision-support tool for optimizing recycled-aggregate concrete formulations in circular construction practices.
ElfadalyEOthmanAMAlyMH, et al.Assessing performance and environmental benefits of high-performance geopolymer mortar incorporating pumice and rice straw ash. Sustain Chem Pharm2025; 44: 101918.
2.
MaCKAwangAZOmarW. Structural and material performance of geopolymer concrete: a review. Constr Build Mater2018; 186: 90–102.
3.
AlmutairiALTayehBAAdesinaA, et al.Potential applications of geopolymer concrete in construction: a review. Case Stud Constr Mat2021; 15: e00733.
4.
MadandoustRRanjbarMMMoghadamHA, et al.Mechanical properties and durability assessment of rice husk ash concrete. Biosyst Eng2011; 110(2): 144–152.
5.
ShafighPMahmudHBJumaatMZ, et al.Agricultural wastes as aggregate in concrete mixtures–A review. Constr Build Mater2014; 53: 110–117.
6.
HeJKawasakiSAchalV. The utilization of agricultural waste as agro-cement in concrete: a review. Sustainability2020; 12(17): 6971.
7.
GudainiyanJKishoreK. A review on cement concrete strength incorporated with agricultural waste. Mater Today Proc2023; 78: 396–402.
8.
OyebisiSOlutogeFKathirvelP, et al.Sustainability assessment of geopolymer concrete synthesized by slag and corncob ash. Case Stud Constr Mat2022; 17: e01665.
9.
OyebisiSShammasMIOladejiSO, et al.Modelling mechanical strengths of blended cement concrete incorporating corncob ash and calcite powder: experimental and machine learning approaches. Asian J Civ Eng2024; 26: 1–18.
10.
WangJQuQKhanSA, et al.Experimenting the influence of corncob ash on the mechanical strength of slag-based geopolymer concrete. Rev Adv Mater Sci2024; 63(1): 20230187.
11.
CavaleriLAsterisPGPsyllakiPP, et al.Prediction of surface treatment effects on the tribological performance of tool steels using artificial neural networks. Appl Sci2019; 9(14): 2788.
12.
GhanizadehARGhanizadehAAsterisPG, et al.Developing bearing capacity model for geogrid-reinforced stone columns improved soft clay utilizing MARS-EBS hybrid method. Transp Geotech2023; 38: 100906.
13.
BarkhordariMSArmaghaniDJAsterisPG. Structural damage identification using ensemble deep convolutional neural network models. Comput Model Eng Sci2022; 134(2): 835–855.
14.
CavaleriLChatzarakisGEDi TrapaniF, et al.Modeling of surface roughness in electro-discharge machining using artificial neural networks. Adv Mater Res2017; 6(2): 169.
15.
AsterisPGTsavdaridisKDLemonisME, et al.AI-powered GUI for prediction of axial compression capacity in concrete-filled steel tube columns. Neural Comput Appl2024; 36(35): 22429–22459.
16.
AsterisPGKaroglouMSkentouAD, et al.Predicting uniaxial compressive strength of rocks using ANN models: incorporating porosity, compressional wave velocity, and schmidt hammer data. Ultrasonics2024; 141: 107347.
17.
NaderpourHRafieanAHFakharianP. Compressive strength prediction of environmentally friendly concrete using artificial neural networks. J Build Eng2018; 16: 213–219.
18.
AbdellatiefMWongLSDinNM, et al.Sustainable foam glass property prediction using machine learning: a comprehensive comparison of predictive methods and techniques. Results Eng2025; 25: 104089.
19.
EmadWMohammedASKurdaR, et al.Prediction of concrete materials compressive strength using surrogate models. Structures2022; 46: 1243–1267.
20.
AsterisPGSkentouADBardhanA, et al.Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models. Cem Concr Res2021; 145: 106449.
21.
JafDKIAbdulrahmanPIMohammedAS, et al.Machine learning techniques and multi-scale models to evaluate the impact of silicon dioxide (SiO2) and calcium oxide (CaO) in fly ash on the compressive strength of green concrete. Constr Build Mater2023; 400: 132604.
22.
MomshadAMIslamMHDattaSD, et al.Assessing the engineering properties and environmental impact with explainable machine learning analysis of sustainable concrete utilizing waste banana leaf ash as a partial cement replacement. Clean Eng Technol2025; 24: 100886.
23.
KashemAKarimRDasP, et al.Compressive strength prediction of sustainable concrete incorporating rice husk ash (RHA) using hybrid machine learning algorithms and parametric analyses. Case Stud Constr Mat2024; 20: e03030.
24.
KarimRIslamMHDattaSD, et al.Synergistic effects of supplementary cementitious materials and compressive strength prediction of concrete using machine learning algorithms with SHAP and PDP analyses. Case Stud Constr Mat2024; 20: e02828.
25.
MottakinMDattaSDHossainMM, et al.Evaluation of textile effluent treatment plant sludge as supplementary cementitious material in concrete using experimental and machine learning approaches. J Build Eng2024; 96: 110627.
26.
NguyenNHVoTPLeeS, et al.Heuristic algorithm-based semi-empirical formulas for estimating the compressive strength of the normal and high performance concrete. Constr Build Mater2021; 304: 124467.
27.
MahmoodWMohammedASSihagP, et al.Interpreting the experimental results of compressive strength of hand-mixed cement-grouted sands using various mathematical approaches. Arch Civ Mech Eng2021; 22(1): 19.
28.
AshrafianAPanahiESalehiS, et al.Mapping the strength of agro-ecological lightweight concrete containing oil palm by-product using artificial intelligence techniques. Structures2023; 48: 1209–1229.
29.
GolafshaniEKhodadadiNNgoT, et al.Modelling the compressive strength of geopolymer recycled aggregate concrete using ensemble machine learning. Adv Eng Softw2024; 191: 103611.
30.
NguyenHVuTVoTP, et al.Efficient machine learning models for prediction of concrete strengths. Constr Build Mater2021; 266: 120950.
31.
ElhishiSElashryAMEl-MetwallyS. Unboxing machine learning models for concrete strength prediction using XAI. Sci Rep2023; 13(1): 19892.
32.
SunZLiYLiY, et al.Investigation on compressive strength of coral aggregate concrete: hybrid machine learning models and experimental validation. J Build Eng2024; 82: 108220.
33.
ZhouJAsterisPGArmaghaniDJ, et al.Prediction of ground vibration induced by blasting operations through the use of the bayesian network and random forest models. Soil Dyn Earthq Eng2020; 139: 106390.
34.
SarirPChenJAsterisPG, et al.Developing GEP tree-based, neuro-swarm, and whale optimization models for evaluation of bearing capacity of concrete-filled steel tube columns. Eng Comput2021; 37: 1–19.
35.
ZhouSZhangZXLuoX, et al.Predicting dynamic compressive strength of frozen-thawed rocks by characteristic impedance and data-driven methods. J Rock Mech Geotech2024; 16(7): 2591–2606.
36.
GómezDRojasA. An empirical overview of the no free lunch theorem and its effect on real-world machine learning classification. Neural Comput2016; 28(1): 216–228.
37.
JoyceTHerrmannJM. A review of no free lunch theorems, and their implications for metaheuristic optimisation. In: Nature-inspired algorithms and applied optimization. Springer, 2018, Vol. 2018, pp. 27–51.
38.
BinFHosseiniSChenJ, et al.Proposing optimized random forest models for predicting compressive strength of geopolymer composites. Infrastructures2024; 9(10): 181.
39.
FattahiHGhaediHArmaghaniDJ. Optimizing fracture toughness estimation for rock structures: a soft computing approach with GWO and IWO algorithms. Measurement2024; 238: 115306.
40.
QiuYZhouJHeB, et al.Evaluation and interpretation of blasting-induced tunnel overbreak: using heuristic-based ensemble learning and gene expression programming techniques. Rock Mech Rock Eng2024; 57: 1–29.
41.
BardhanASumanSKKumarS, et al.An efficient framework of optimized ensemble paradigm for estimating resilient modulus of subgrades. Transp Geotech2024; 48: 101315.
42.
BreimanL. Random forests. Mach Learn2001; 45: 5–32.
43.
ZhouSLeiYZhangZX, et al.Estimating dynamic compressive strength of rock subjected to freeze-thaw weathering by data-driven models and non-destructive rock properties. Nondestruct Test Eva2024; 40: 1–24.
44.
AbrahamRSamadMEBakhachAM, et al.Forecasting a stock trend using genetic algorithm and random forest. J Risk Financ Manag2022; 15(5): 188.
45.
WalshESKreakieBJCantwellMG, et al.A random forest approach to predict the spatial distribution of sediment pollution in an estuarine system. PLoS One2017; 12(7): e0179473.
46.
YangFWangHMiH, et al.Using random forest for reliable classification and cost-sensitive learning for medical diagnosis. BMC Bioinf2009; 10: 1–14.
47.
LiXWenZSuH. An approach using random forest intelligent algorithm to construct a monitoring model for dam safety. Eng Comput2021; 37(1): 39–56.
48.
MinhHLSang-ToTTheraulazG, et al.Termite life cycle optimizer. Expert Syst Appl2023; 213: 119211.
49.
JiaHWenQWangY, et al.Catch fish optimization algorithm: a new human behavior algorithm for solving clustering problems. Clust Comput2024; 2024: 1–38.
50.
WangWTianWXuD, et al.Arctic puffin optimization: a bio-inspired metaheuristic algorithm for solving engineering design optimization. Adv Eng Softw2024; 195: 103694.
51.
OyebisiSAlomayriT. Artificial intelligence-based prediction of strengths of slag-ash-based geopolymer concrete using deep neural networks. Constr Build Mater2023; 400: 132606.
52.
KovačevićŽGurbeta PokvićLSpahićL, et al.Prediction of medical device performance using machine learning techniques: infant incubator case study. Health Technol2020; 10(1): 151–155.
53.
ZhouJLiEYangS, et al.Slope stability prediction for circular mode failure using gradient boosting machine approach based on an updated database of case histories. Saf Sci2019; 118: 505–518.
54.
ZhouJQiuYZhuS, et al.Estimation of the TBM advance rate under hard rock conditions using XGBoost and Bayesian optimization. Undergr Space2021; 6(5): 506–515.
55.
YagizSGokceogluC. Application of fuzzy inference system and nonlinear regression models for predicting rock brittleness. Expert Syst Appl2010; 37(3): 2265–2272.
56.
KişiÖ. A combined generalized regression neural network wavelet model for monthly streamflow prediction. KSCE J Civ Eng2011; 15: 1469–1479.
57.
ArmaghaniDJAminMFMYagizS, et al.Prediction of the uniaxial compressive strength of sandstone using various modeling techniques. Int J Rock Mech Min2016; 85: 174–186.
58.
ZorluKGokceogluCOcakogluF, et al.Prediction of uniaxial compressive strength of sandstones using petrography-based models. Eng Geol2008; 96(3-4): 141–158.
59.
KayabasiAGokceogluCErcanogluM. Estimating the deformation modulus of rock masses: a comparative study. Int J Rock Mech Min2003; 40(1): 55–63.
60.
EstévezPATesmerMPerezCA, et al.Normalized mutual information feature selection. IEEE T Neural Networ2009; 20(2): 189–201.
61.
GhorbaniAHasanzadehshooiiliHGhamariE, et al.Comprehensive three dimensional finite element analysis, parametric study and sensitivity analysis on the seismic performance of soil–micropile-superstructure interaction. Soil Dyn Earthq Eng2014; 58: 21–36.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
