Strength prediction of silicon–aluminum phosphate geopolymers using machine learning
Source abstract
Abstract
Silico-aluminate phosphate (SAP) geopolymers are three-dimensional amorphous polymers formed by the reaction of aluminosilicate with phosphate. They exhibit high strength, excellent thermal resistance, and corrosion resistance, making them highly promising for applications such as construction materials, fireproof/anticorrosive coatings, and hazardous waste immobilization. However, current research on SAP geopolymers is in its early stages, with limited reported studies and significant variability in optimal mix proportions for achieving high strength, which hinders further development. To clarify the factors influencing the strength of SAP geopolymers and advance their development, this study established, for the first time, a comprehensive database of seven key characteristic parameters and their corresponding strength values. Machine learning algorithms were used to developa model to predict the compressive strength of SAP geopolymers, along with a graphical user interface for strength prediction. The results showed that the random forest regression model delivered the best predictive performance (R2 > 0.8) and strong generalization capability. Increasing the curing temperature and phosphate concentration enhanced compressive strength. The molar ratios of phosphorus/aluminum, phosphorus/silicon, and silicon/aluminum molar ratio must be maintained within specific ranges to maximize strength. The optimal ranges for achieving peak strength were investigated.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Concrete and Cement Materials Research · Magnesium Oxide Properties and Applications · Innovative concrete reinforcement materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Beijing University of Technology Key Laboratory of Urban Security and Disaster Engineering of Ministry of Education, Beijing Key Laboratory of Earthquake Engineering and Structural Retrofit, , Beijing,
References (69)
Show source-provided references
1. Development of intelligent fault-tolerant control systems with machine learning, deep learning, and transfer learning algorithms: a review10.1016/j.eswa.2023.121956 ↗
2. Phosphate-based geopolymer: influence of municipal solid waste fly ash introduction on structure and compressive strength10.1016/j.ceramint.2023.04.042 ↗
3. Prediction of surface chloride concentration of marine concrete using ensemble machine learning10.1016/j.cemconres.2020.106164 ↗
4. Composition and properties of phosphoric acid-based geopolymers10.1016/j.jnoncrysol.2018.04.044 ↗
5. Mechanical and microstructural investigations on the low-reactive copper mine tailing-based geopolymer activated by phosphoric acid10.1016/j.conbuildmat.2023.132030 ↗
6. Geopolymers and geopolymeric materials10.1007/BF01904446 ↗
7. The reaction of calcium during the formation of metakaolin phosphate geopolymer binder10.1016/j.cemconres.2022.106840 ↗
8. The role of curing temperature and reactive aluminum species on characteristics of phosphate geopolymer10.1039/D2RA04562A ↗
9. Properties and characterization of a metakaolin phosphate acid-based geopolymer synthesized in a humid environment10.1007/s41779-019-00376-w ↗
10. Structural, thermal and dielectric properties of phosphoric acid-based geopolymers with different amounts of H3PO410.1016/j.matlet.2013.10.075 ↗
11. Effect of SiO2/Al2O3 molar ratio on microstructure and properties of phosphoric acid-based metakaolin geopolymerss10.12783/dtmse/msce2016/10486 ↗
12. Preparation and characterization of acid-based geopolymer using metakaolin and disused polishing liquid10.1016/j.ceramint.2016.02.073 ↗
13. Realization of high-percentage addition of fly ash in the materials for the preparation of geopolymer derived from acid-activated metakaolin10.1016/j.jclepro.2020.125430 ↗
14. Preparation of high-performance silico-aluminophosphate geopolymers using fly ash and metakaolin as raw materials10.1016/j.clay.2021.106019 ↗
15. Preparation and characterization of geopolymers based on a phosphoric-acid-activated electrolytic manganese dioxide residue10.1016/j.jclepro.2018.09.141 ↗
16. Strength, microstructure, CO2 emission and economic analyses of low concentration phosphoric acid-activated fly ash geopolymer10.1016/j.conbuildmat.2023.130920 ↗
17. A data-driven method for prediction and design of biomass ash alkali-activated materials10.1680/jgele.24.00132 ↗
18. Multi-objective prediction of alkali-activated material properties and material parameter design10.1007/s00500-025-10710-z ↗
19. Using machine learning techniques for predicting autogenous shrinkage of concrete incorporating superabsorbent polymers and supplementary cementitious materials10.1016/j.jobe.2022.104086 ↗
20. Latest concrete materials dataset and ensemble prediction model for concrete compressive strength containing RCA and GGBFS materials10.1016/j.conbuildmat.2022.126525 ↗
21. Metakaolinite phosphate cementitious matrix: Inorganic polymer obtained by acidic activation10.3390/ma12030442 ↗
22. Estimation of bond strength between UHPC and reinforcing bars using machine learning approaches10.1016/j.engstruct.2022.114311 ↗
23. The study of effect of carbon nanotubes on the compressive strength of cement-based materials based on machine learning10.1016/j.conbuildmat.2022.129435 ↗
24. The data-driven research on bond strength between fly ash-based geopolymer concrete and reinforcing bars10.1016/j.conbuildmat.2022.129384 ↗
25. Preparation and properties of geopolymer containing phosphoric acid-activated fly ash and mechanically-milled kaolinite: experiments and density function theory10.1016/j.jclepro.2024.140992 ↗
26. Ambient-temperature properties and mechanistic insights of calcium oxalate-modified low-calcium fly ash geopolymer: eliminating the need for high-temperature activation10.1016/j.cscm.2025.e04477 ↗
27. Interpretable ensemble-machine-learning models for predicting creep behavior of concrete10.1016/j.cemconcomp.2021.104295 ↗
28. Properties and reaction mechanism of phosphoric acid activated metakaolin geopolymer at varied curing temperatures10.1016/j.cemconres.2021.106425 ↗
29. Preparation of phosphoric acid-based porous geopolymers10.1016/j.clay.2010.10.004 ↗
30. The phase evolution of phosphoric acid-based geopolymers at elevated temperatures10.1016/j.matlet.2011.08.043 ↗
31. Prediction of carbonation depth for recycled aggregate concrete using ANN hybridized with swarm intelligence algorithms10.1016/j.conbuildmat.2021.124382 ↗
32. Prediction of the sulfate resistance for recycled aggregate concrete based on ensemble learning algorithms10.1016/j.conbuildmat.2021.125917 ↗
33. Innovative modeling framework of chloride resistance of recycled aggregate concrete using ensemble-machine-learning methods10.1016/j.conbuildmat.2022.127613 ↗
34. Structure and properties of new eco-material obtained by phosphoric acid attack of natural Tunisian clay10.1016/j.clay.2014.07.015 ↗
35. Acid based geopolymerization kinetics: effect of clay particle size10.1016/j.clay.2016.08.007 ↗
36. Phosphate-activated high-calcium fly ash acid-base cements10.1016/j.cemconcomp.2015.09.002 ↗
37. Particle swarm optimization (PSO). A tutorial10.1016/j.chemolab.2015.08.020 ↗
38. Control of the alumino-silico-phosphate geopolymers properties and structures by the phosphorus concentration10.1016/j.matchemphys.2020.123867 ↗
39. Water resistance and thermal behavior of metakaolin-phosphate-based geopolymer cements10.1080/21870764.2018.1507660 ↗
40. Relative strengths of phosphoric acid-reacted and alkali-reacted metakaolin materials10.1007/s10853-008-2913-6 ↗
41. A novel acidic phosphoric-based geopolymer binder for lead solidification/stabilization10.1016/j.jhazmat.2021.125659 ↗
42. Mechanical and microscopic properties of fly ash phosphoric acid-based geopolymer paste: a comprehensive study10.1016/j.conbuildmat.2021.123947 ↗
43. A eco-friendly acid fly ash geopolymer with a higher strength10.1016/j.conbuildmat.2022.127450 ↗
44. A green phosphate-based geopolymer adsorbent or binder with high specific surface area for environmental applications10.1016/j.conbuildmat.2023.133738 ↗
45. Enhancement mechanical properties of phosphoric-based geopolymer using aluminum dihydrogen phosphate10.1016/j.mtcomm.2023.107656 ↗
46. Valorization of sugar beet waste as a foaming agent for metakaolin geopolymer activated with phosphoric acid10.1016/j.conbuildmat.2022.128240 ↗
47. Prediction of compressive strength of alkali-activated construction demolition waste geopolymers using ensemble machine learning10.1016/j.conbuildmat.2022.129600 ↗
48. The influence of gibbsite in kaolin and the formation of berlinite on the properties of metakaolin-phosphate-based geopolymer cements10.1016/j.matchemphys.2017.07.020 ↗
49. Influence of the molar concentration of phosphoric acid solution on the properties of metakaolin-phosphate-based geopolymer cements10.1016/j.clay.2017.07.036 ↗
50. The effects of synthesized calcium phosphate compounds on the mechanical and microstructural properties of metakaolin-based geopolymer cements10.1016/j.conbuildmat.2017.12.162 ↗
51. Machine learning approach for investigating chloride diffusion coefficient of concrete containing supplementary cementitious materials10.1016/j.conbuildmat.2022.127103 ↗
52. Structural study of the effect of nano additives on the thermal properties of metakaolin phosphate geopolymer by MASNMR, XPS and SEM analysis10.1016/j.inoche.2023.110758 ↗
53. The role of polyethylene glycol, a water entrainer on characteristics of silico alumino phosphate geopolymer to harvest enhanced gel phase and stability10.1007/s10904-023-02715-8 ↗
54. Phosphate-based geopolymer: formation mechanism and thermal stability10.1016/j.matlet.2017.01.022 ↗
55. Influence of coal fly ash on the early performance enhancement and formation mechanisms of silico-aluminophosphate geopolymer10.1016/j.cemconres.2019.105932 ↗
56. Mechanical and thermal properties of phosphoric acid activated geopolymer materials reinforced with mullite fibers10.3390/ma15124185 ↗
57. Prediction of the frost resistance of high-performance concrete based on RF-REF: a hybrid prediction approach10.1016/j.conbuildmat.2022.127132 ↗
58. Effect of acid-activator characteristics on the early hydration behavior and properties of metakaolin-based geopolymer10.1016/j.jobe.2023.106608 ↗
59. Preparation of acid aluminum phosphate solutions for metakaolin phosphate geopolymer binder10.1039/D1RA05433C ↗
60. Comparative study on the preparation of phosphate-based geopolymers using different activators10.1016/j.conbuildmat.2024.137000 ↗
61. Novel acid-based geopolymer synthesized from nanosized tubular halloysite: the role of precalcination temperature and phosphoric acid concentration10.1016/j.cemconcomp.2020.103601 ↗
62. Undehydrated kaolinite as materials for the preparation of geopolymer through phosphoric acid-activation10.1016/j.clay.2020.105887 ↗
63. Quantitative evaluation of steel corrosion induced deterioration in rubber concrete by integrating ultrasonic testing, machine learning and mesoscale simulation10.1016/j.cemconcomp.2022.104426 ↗
64. Modulus of elasticity predictions through LSBoost for concrete of normal and high strength10.1016/j.matchemphys.2022.126007 ↗
65. The influence of composite modification of precursor and activator on the properties of the silica-aluminum phosphate geopolymer10.1016/j.ceramint.2025.01.176 ↗
66. Effect of sulfate freeze-thaw on the stress-strain relationship of recycled coarse aggregate self-compacting concrete: Experimental and machine learning algorithms10.1016/j.conbuildmat.2024.138383 ↗
67. Effect of curing temperature on the synthesis, structure and mechanical properties of phosphate-based geopolymers10.1016/j.jnoncrysol.2019.01.032 ↗
68. Mechanical, microstructural and structural investigation of phosphate-based geopolymers with respect to P/Al molar ratio10.1016/j.jssc.2019.121025 ↗
69. Investigation of dealumination in phosphate-based geopolymer formation process: Factor screening and optimization10.3390/min12091104 ↗