Abstract
The environmental burden associated with conventional cement-based materials has intensified research for sustainable alternatives with lower carbon footprints. For this, gypsum-based composites reinforced with agricultural waste, such as wheat straw, offer a promising solution. However, their mechanical performance is governed by nonlinear and complex interactions among multiple mixture parameters. This study proposes a comprehensive machine learning (ML) framework to predict the compressive and flexural strength of wheat straw reinforced gypsum composites. A dataset comprising 161 experimental samples was used and five ML models: artificial neural network, Gaussian process regression (GPR), random forest, extreme gradient boosting, and support vector machine, were used. Model performance was assessed using tenfold cross-validation with multiple statistical metrics along with Taylor diagram analysis. Among the evaluated models, GPR demonstrated superior predictive capability for both compressive and flexural strength, while providing uncertainty quantification that enhances reliability for engineering applications. Feature importance and SHapley Additive exPlanations analyses were employed to improve model interpretability, revealing gypsum strength as the most influential parameter, with water-related parameters, wheat straw content, and chemical additives contributing secondary effects. The proposed ML-based framework provides acceptable and interpretable predictions, offering the optimization of sustainable gypsum composites while reducing experimental efforts and supporting environment-friendly construction.
Similar content being viewed by others
Data availability
The dataset generated during and/or analyzed during the current study are available in this article. The trained models and prediction scripts have been made publicly accessible at repository (https://doi.org/10.5281/zenodo.18877579).
References
Cement and concrete around the world. https://gccassociation.org/concretefuture/cement-concrete-around-the-world/. Accessed 03 March 2026.
Sharma, R. D. & Singh, N. Evaluation of strength and absorption behaviour of iron slag and recycled aggregates concrete and its comparative environmental estimation by life cycle assessment. Clean. Mater. 10, 100210 (2023).
Ma, J., Yuan, H., Zhang, J. & Zhang, P. Enhancing concrete performance: A comprehensive review of hybrid fiber reinforced concrete. Structures 64, 106560 (2024).
Kaptan, K., Cunha, S. & Aguiar, J. A review: Construction and demolition waste as a novel source for CO2 reduction in Portland cement production for concrete. Sustainability 16(2), 585 (2024).
Rajendran, N. et al. Economic and environmental impact analysis of cellulose nanofiber-reinforced concrete mixture production. Resour. Conserv. Recycl. 212, 107917 (2025).
Zhaurova, M., Soukka, R. & Horttanainen, M. Multi-criteria evaluation of CO2 utilization options for cement plants using the example of Finland. Int. J. Greenh. Gas Control 112, 103481 (2021).
Argalis, P. P., Sinka, M. & Bajare, D. Recycling of cement–wood board production waste into a low-strength cementitious binder. Recycling 7(5), 76 (2022).
Shah, S. A. R. et al. Optimization of fresh and mechanical properties of sustainable concrete composite containing ARGF and fly ash: An application of response surface methodology. Constr. Build. Mater. 362, 129722 (2023).
Benhelal, E., Zahedi, G., Shamsaei, E. & Bahadori, A. Global strategies and potentials to curb CO2 emissions in cement industry. J. Clean. Prod. 51, 142–161 (2013).
Jia, B., Peng, L. & Zhao, Y. Recycling waste glass powder in lightweight aggregate concrete: Towards lightweight, sustainable and durable marine engineering structures. Constr. Build. Mater. 472, 140690 (2025).
Riaz, M. R., Azhar, M. M., Ejaz, M. F., Azam, R. & Javaid, M. F. Mechanical characterization and impact resistance of concrete incorporating recycled thin-walled hollow tubular GFRP sections. Innov. Infrastruct. Solut. 10(12), 585 (2025).
Murali, G., Wong, L. S., Abdulkadir, I., Algaifi, H. A. & Abdellatief, M. Sustainable transformation of waste phosphogypsum into geopolymer concrete: Comprehensive review on strength, durability, and microstructural characteristics. J. Build. Eng. 111, 113597 (2025).
Abdullah, M., Qazi, A. U., Khan, Q. S., Kazmi, S. M. S. & Munir, M. J. Experimental and analytical investigations on shear performance of ambient-cured reinforced geopolymer concrete beams. Buildings 14(1), 204 (2024).
Aziz, W. et al. Mechanical properties, drying shrinkage and structural performance of coconut shell lightweight concrete. Structures 35, 26–35 (2022).
Ejaz, M. F. et al. Coconut shell waste as an alternative lightweight aggregate in concrete—A review. Adv. Mater. Res. 11(4), 299–330 (2022).
Domanskaya, I., Petropavlovskaya, V., Novichenkova, T., Petropavlovskii, K. & Fediuk, R. Potential of gypsum-based matrices for sustainable composite materials: A comprehensive review: Domanskaya, Petropavlovskaya, Novichenkova, Petropavlovskii, and Fediuk. JOM 77(4), 2367–2382 (2025).
del Río-Merino, M. et al. A review of the research about gypsum mortars with waste aggregates. J. Build. Eng. 45, 103338 (2022).
Sonnier, R. et al. Fire behaviour of hemp, clay and gypsum-based light biobased concretes and renders. Constr. Build. Mater. 331, 127230 (2022).
Khrissi, Y., Tilioua, A., Laaroussi, N. & Bybi, A. Recycling date palm waste in a gypsum-based composite: Experimental study of thermal, acoustic, mechanical and hydric performance. Innov. Infrastruct. Solut. 10(7), 312 (2025).
Ramzi, S. & Hajiloo, H. Evaluation of the fall-off of gypsum board in lightweight and mass timber constructions and implications in fire resistance. Fire Saf. J. https://doi.org/10.1016/j.firesaf.2025.104455 (2025).
Zhang, L. et al. Valorization of industrial by-product gypsum for sustainable lightweight brick: Performance, microstructure and environmental safety assessments. Sustain. Chem. Pharm. 48, 102179 (2025).
Zhang, F. et al. Innovative valorization of basic oxygen furnace slag in gypsum-based sustainable building blocks. J. Build. Eng. 105, 112489 (2025).
Togun, H. et al. Innovative PCM-gypsum plasterboard technologies for smart building envelopes: Recent advances and applications. Sustain. Energy Technol. Assess. 82, 104470 (2025).
Kou, Y.-f, Xu, G.-l, Ren, Q.-q, Hao, J.-p & Tian, L.-m. Experimental investigations into the cyclic performance of innovative original bamboo frame and gypsum-based mortar composite walls. Structures 80, 109890 (2025).
Javed, M. H., Riaz, M. R., Azam, R., Kashif, M. & Fatima, A. Physico-mechanical characterization of eco-friendly gypsum composites incorporating shredded surgical face masks. Innov. Infrastruct. Solut. 9(6), 186 (2024).
Doleželová, M., Krejsová, J., Scheinherrová, L., Keppert, M. & Vimmrová, A. Investigation of environmentally friendly gypsum based composites with improved water resistance. J. Clean. Prod. 370, 133278 (2022).
Sharifi Teshnizi, E., Mirzababaei, M., Karimiazar, J., Arjmandzadeh, R. & Mahmoudpardabad, K. Gypsum and rice husk ash for sustainable stabilization of forest road subgrade. Q. J. Eng. Geol. Hydrogeol. 57(1), qjegh2023-008 (2024).
Songkhla, W. N., Chaikaew, C., Chatveera, B. & Sua-iam, G. Experimental investigation of recycled HDPE waste fiber-reinforced gypsum with emphasis on durability and mechanical performance. Results Eng. https://doi.org/10.1016/j.rineng.2025.105330 (2025).
Seid, A. M. et al. Recent progress on the physical, thermal, and mechanical properties of expanded polystyrene waste-based composites. Int. J. Polym. Sci. 2025(1), 9285040 (2025).
Beldjilali, S. et al. Waste brick as partial replacement of gypsum in mortars: Mechanical performance and environmental benefits for sustainable construction. Sustainability 17(16), 7452 (2025).
Rouf, M. A., Alam, M. R., Belal, S. A., Ali, Y. & Rahman, M. Z. Mechanical and thermal performances of banana fiber–reinforced gypsum composites. Int. J. Polym. Sci. 2025(1), 8120082 (2025).
Pedreño-Rojas, M. A., Morales-Conde, M. J. & Flores-Colen, I. Incorporation of wood waste as aggregate in the production of recycled gypsum products: Mechanical and thermal analysis. J. Build. Eng. https://doi.org/10.1016/j.jobe.2025.114567 (2025).
Chen, C., Fang, L., Jiu, S., Chen, Y. & Liu, Y. Preparation of novel straw-based shape-stabilized phase change materials and their effect on the properties of gypsum-based composites. J. Energy Storage 116, 116087 (2025).
Li, S. & Chen, G. Agricultural waste-derived superabsorbent hydrogels: Preparation, performance, and socioeconomic impacts. J. Clean. Prod. 251, 119669 (2020).
Raza, W. et al. A review on the deteriorating situation of smog and its preventive measures in Pakistan. J. Clean. Prod. 279, 123676 (2021).
SAARC. Energy center report. In Possible Uses of Crop Residue for Energy Generation Instead of Open Burning (SAARC Energy Centre, Islamabad, 2019).
Habib, A., Nasim, S. & Shahab, A. Charting Pakistan’s Air Quality Policy Landscape (International Growth Centre, 2021).
Saeed, M. et al. Agricultural waste biomass energy potential in Pakistan. In Proceedings of the International Conference Held in Shanghai, PR China (Leeds, 2015).
Kazemi, F., Çiftçioğlu, A. Ӧ, Shafighfard, T., Asgarkhani, N. & Jankowski, R. RAGN-R: A multi-subject ensemble machine-learning method for estimating mechanical properties of advanced structural materials. Comput. Struct. 308, 107657 (2025).
Wang, R. et al. Application and prospect of machine learning techniques in cost estimation of building projects. Eng. Constr. Archit. Manag. 32(12), 8445–8471 (2025).
Yuan, Z., Zheng, W. & Qiao, H. Machine learning based optimization for mix design of manufactured sand concrete. Constr. Build. Mater. 467, 140256 (2025).
Shaaban, M., Amin, M., Selim, S. & Riad, I. M. Machine learning approaches for forecasting compressive strength of high-strength concrete. Sci. Rep. 15(1), 25567 (2025).
Sinkhonde, D., Bezabih, T., Mirindi, D., Mashava, D. & Mirindi, F. Ensemble machine learning algorithms for efficient prediction of compressive strength of concrete containing tyre rubber and brick powder. Clean. Waste Syst. 10, 100236 (2025).
Gharagoz, M. M., Noureldin, M. & Kim, J. Explainable machine learning (XML) framework for seismic assessment of structures using Extreme Gradient Boosting (XGBoost). Eng. Struct. 327, 119621 (2025).
Zhan, H., He, W., Xu, H., Yang, J. & Shi, C. Machine learning-enhanced prediction of traffic-induced ground vibrations with vehicle–road surface–soil coupling and experimental validation. Soil Dyn. Earthq. Eng. 202, 109995 (2026).
Aziz, M. T. et al. State-of-the-art artificial intelligence techniques in structural engineering: A review of applications and prospects. Results Eng. 28, 107882 (2025).
Ejaz, M. F. et al. Physico-mechanical characterization of gypsum-agricultural waste composites for developing eco-friendly false ceiling tiles. Sustainability 14(16), 9797 (2022).
Vavřínová, N., Stejskalová, K., Teslík, J., Kubenková, K. & Majer, J. Research of mechanical and thermal properties of composite material based on gypsum and straw. J. Renew. Mater. 10(7), 1859 (2022).
Gomes, D. A. C. et al. Analysis of the influence of wheat residues on gypsum composites. Innov. Infrastr. Solut. 8(1), 31 (2023).
El hammouti, A. et al. Application analysis and environmental impact of straw reinforced gypsum plaster for improving the energy efficiency in buildings in the six climate zones of Morocco. J. Build. Eng. 74, 106829 (2023).
Regulska, K. & Repelewicz, A. Properties of gypsum composites with straw fillers. In IOP Conference Series: Materials Science and Engineering (IOP Publishing, 2019).
Durgun, M. Y. Experimental research on gypsum-based mixtures containing recycled roofing tile powder at ambient and high temperatures. Constr. Build. Mater. 285, 122956 (2021).
Petrella, A. et al. Experimental investigation on environmentally sustainable cement composites based on wheat straw and perlite. Materials 15(2), 453 (2022).
Morales-Conde, M. J., Rodríguez-Liñán, C. & Pedreño-Rojas, M. A. Physical and mechanical properties of wood-gypsum composites from demolition material in rehabilitation works. Constr. Build. Mater. 114, 6–14 (2016).
Bishop, C. M. Neural Networks for Pattern Recognition (Oxford University Press, 1995).
Khan, A. Q., Awan, H. A., Rasul, M., Siddiqi, Z. A. & Pimanmas, A. Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete. Clean. Mater. 10, 100211 (2023).
Morsy, A. M., Abd Elmoaty, A. E. & Harraz, A. B. Predicting mechanical properties of engineering cementitious composite reinforced with PVA using artificial neural network. Case Stud. Constr. Mater. https://doi.org/10.1016/j.cscm.2022.e00998 (2022).
Congro, M. et al. Prediction of the residual flexural strength of fiber reinforced concrete using artificial neural networks. Constr. Build. Mater. 303, 124502 (2021).
Williams, C. & Rasmussen, C. Gaussian processes for regression. In Advances in Neural Information Processing Systems, vol. 8 (1995).
Haruna, S. et al. Gaussian process regression model for the prediction of the compressive strength of polyurethane-based polymer concrete for runway repair: A comparative approach. In IOP Conference Series: Earth and Environmental Science (IOP Publishing, 2022).
Al-Kahtani, M., Zhu, H., Ibrahim, Y. E., Haruna, S. & Al-Qahtani, S. Study on the mechanical properties of polyurethane-cement mortar containing nanosilica: RSM and machine learning approach. Appl. Sci. 13(24), 13348 (2023).
Breiman, L. Random forests. Mach. Learn. 45(1), 5–32 (2001).
Farooq, F. et al. A comparative study of random forest and genetic engineering programming for the prediction of compressive strength of high strength concrete (HSC). Appl. Sci. 10(20), 7330 (2020).
Qing, S. & Li, C. Data-driven prediction on critical mechanical properties of engineered cementitious composites based on machine learning. Sci. Rep. 14(1), 15322 (2024).
Chen, T. XGBoost: A Scalable Tree Boosting System (Cornell University, 2016).
Alshboul, O., Almasabha, G., Shehadeh, A. & Al-Shboul, K. A comparative study of LightGBM, XGBoost, and GEP models in shear strength management of SFRC-SBWS. Structures https://doi.org/10.1016/j.istruc.2024.106009 (2024).
Nguyen, H., Vu, T., Vo, T. P. & Thai, H.-T. Efficient machine learning models for prediction of concrete strengths. Constr. Build. Mater. 266, 120950 (2021).
Cortes, C. & Vapnik, V. Support-vector networks. Mach. Learn. 20(3), 273–297 (1995).
Jueyendah, S., Lezgy-Nazargah, M., Eskandari-Naddaf, H. & Emamian, S. Predicting the mechanical properties of cement mortar using the support vector machine approach. Constr. Build. Mater. 291, 123396 (2021).
Cemiloglu, A. et al. Support vector machine (SVM) application for uniaxial compression strength (UCS) prediction: A case study for Maragheh limestone. Appl. Sci. 13(4), 2217 (2023).
Ahmad, H. & Matsumoto, Y. An investigation of the effect of age degradation on natural frequency of single span prestressed concrete bridge under environmental variation using Gaussian process regression. In International Conference on Experimental Vibration Analysis for Civil Engineering Structures (Springer, 2025).
Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems, vol. 30 (2017).
Funding
This study did not receive any funding.
Author information
Authors and Affiliations
Contributions
H.A.: Formal analysis, investigation, software, writing—original draft, visualization. M.F.E.: Conceptualization, data curation, methodology, formal analysis, software, writing—original draft, writing—review and editing. M.R.R.: Conceptualization, supervision, visualization, validation. S.S.: Data curation, investigation, resources. S.E.K.: Resources, supervision, validation. M.G.K.: Methodology, project administration. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: Test database for gypsum wheat-straw reinforced composite specimens experiencing flexure and compression tests
Appendix: Test database for gypsum wheat-straw reinforced composite specimens experiencing flexure and compression tests
See Table 2.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Ahmad, H., Ejaz, M.F., Riaz, M.R. et al. Machine learning-based prediction of compressive and flexural strength of wheat straw reinforced sustainable gypsum composites. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45024-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45024-z
