MACHINE LEARNING-ASSISTED PREDICTION OF FIRE-RETARDANT AND PRESERVATIVE PERFORMANCE OF CHEMICALLY MODIFIED WOOD: AN ECO-FRIENDLY APPROACH
DOI:
https://doi.org/10.5281/zenodo.22209756Abstract
Wood protection currently relies on agents that are effective but environmentally problematic, while the search
for bio-based alternatives is hindered by the vast formulation design space. A critical review of eco-friendly fire-retardant
and preservative chemistries for wood is integrated with a proposed experimental design and a supervised machine-learning
framework for predicting performance outcomes. Three candidate systems are considered: phytic acid with silica
nanosol; condensed tannin fixed with hexamine and boric acid; and chitosan combined with caffeine. Performance ranges
reported in the literature are synthesised, an experimental factor structure suitable for regression modelling is specified,
and a modelling protocol based on regularised regression, tree ensembles, and a compact neural network, incorporating
nested cross-validation and SHAP-based attribution, is proposed. At this stage, no experimental data have been collected
by the author; all quantitative values presented are derived from published studies and are cited accordingly.
Keywords
wood modification; phytic acid; condensed tannin; chitosan; flame retardancy; decay resistance; machine learning; QSPR; SHAP.References
Bi Z. J., Zhou X. J., Chen J., Lei Y. F., Yan L. Effects of extracts on color, dimensional stability, and decay resistance of
thermally modified wood // European Journal of Wood and Wood Products. — 2024. — Vol. 82. — P. 387–401.
Breiman L. Random forests // Machine Learning. — 2001. — Vol. 45, No. 1. — P. 5–32. — DOI: 10.1023/A:1010933404324.
Chen S., Shiina R., Nakai K., Awano T., Yoshinaga A., Sugiyama J. Potential of machine learning approaches for
predicting mechanical properties of spruce wood in the transverse direction // Journal of Wood Science. — 2023. —
Vol. 69. — Art. 22. — DOI: 10.1186/s10086-023-02096-z.
Chen T., Guestrin C. XGBoost: A scalable tree boosting system // Proceedings of the 22nd ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining. — ACM, 2016. — P. 785–794. — DOI: 10.1145/2939672.2939785.
Chen Z., Zhang S., Ding M., Wang M., Xu X. Construction of a phytic acid–silica system in wood for highly efficient
flame retardancy and smoke suppression // Materials. — 2021. — Vol. 14, No. 15. — Art. 4164. — DOI: 10.3390/
ma14154164.
de Lima N. N., de Castro V. R., Lopes N. F., Nunes Í. L., Andrade F. A., Zanuncio A. J. V., Carneiro A. C. O., Araújo S.
O. Tannin extracts as a preservative for pine thermo-mechanically densified wood // BioResources. — 2023. — Vol.
, No. 1. — P. 641–652.
Facchi S. P., de Almeida D. A., Abrantes K. K. B., Rodrigues P. C. S., Tessmann D. J., Bonafé E. G., da Silva M. F.,
Gashti M. P., Martins A. F., Cardozo-Filho L. Ultra-pressurized deposition of hydrophobic chitosan surface coating on
wood for fungal resistance // International Journal of Molecular Sciences. — 2024. — Vol. 25, No. 20. — Art. 10899.
— DOI: 10.3390/ijms252010899.
Hill C. A. S. Wood modification: Chemical, thermal and other processes. — Chichester: John Wiley & Sons, 2006. —
DOI: 10.1002/0470021748.
Hill C., Altgen M., Rautkari L. Thermal modification of wood: A review of chemical changes and hygroscopicity //
Journal of Materials Science. — 2021. — Vol. 56, No. 11. — P. 6581–6614. — DOI: 10.1007/s10853-020-05722-z.
Jafari P., Zhang R., Huo S., Wang Q., Yong J., Hong M., Deo R., Wang H., Song P. Machine learning for expediting
next-generation of fire-retardant polymer composites // Composites Communications. — 2024. — Vol. 45. — Art.
— DOI: 10.1016/j.coco.2023.101806.
Jang E.-S., Kang C.-W. Evaluation of the utilization of Ginkgo biloba leaf (GBL) extract as an eco-friendly wood
preservative // BioResources. — 2024. — Vol. 20, No. 1. — P. 155–163.
Khademibami L., Bobadilha G. S. Recent developments studies on wood protection research in academia: A review //
Frontiers in Forests and Global Change. — 2022. — Vol. 5. — Art. 793177. — DOI: 10.3389/ffgc.2022.793177.
Li L., Chen Z., Lu J., Wei M., Huang Y., Jiang P. Combustion behavior and thermal degradation properties of wood
impregnated with intumescent biomass flame retardants: Phytic acid, hydrolyzed collagen, and glycerol // ACS Omega.
— 2021. — Vol. 6, No. 6. — P. 3921–3930. — DOI: 10.1021/acsomega.0c05778.
Liu Q., Chai Y., Ni L., Lyu W. Flame retardant properties and thermal decomposition kinetics of wood treated with boric
acid modified silica sol // Materials. — 2020. — Vol. 13, No. 20. — Art. 4478. — DOI: 10.3390/ma13204478.
Lowden L. A., Hull T. R. Flammability behaviour of wood and a review of the methods for its reduction // Fire Science
Reviews. — 2013. — Vol. 2. — Art. 4. — DOI: 10.1186/2193-0414-2-4.
Lundberg S. M., Lee S.-I. A unified approach to interpreting model predictions // Advances in Neural Information
Processing Systems 30. — 2017. — P. 4765–4774. — URL: https://arxiv.org/abs/1705.07874.
Ma J., Kuang Z., Fang Y., Huang J. A multi-input residual network for non-destructive prediction of wood mechanical
properties // Forests. — 2025. — Vol. 16, No. 2. — Art. 355. — DOI: 10.3390/f16020355.
Nguyen H. T., Nguyen K. T. Q., Le T. C., Zhang G. Review on the use of artificial intelligence to predict fire performance
of construction materials and their flame retardancy // Molecules. — 2021. — Vol. 26, No. 4. — Art. 1022. — DOI:
3390/molecules26041022.
Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R.,
Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay É. Scikit-learn: Machine
learning in Python // Journal of Machine Learning Research. — 2011. — Vol. 12. — P. 2825–2830.
Popescu C.-M., Pfriem A. Treatments and modification to improve the reaction to fire of wood and wood based products:
An overview // Fire and Materials. — 2020. — Vol. 44, No. 1. — P. 100–111. — DOI: 10.1002/fam.2779.
Rowell R. M. (Ed.). Handbook of wood chemistry and wood composites. — 2nd ed. — Boca Raton: CRC Press, 2012.
— DOI: 10.1201/b12487.
Sandberg D., Kutnar A., Karlsson O., Jones D. Wood modification technologies: Principles, sustainability, and the need
for innovation. — Boca Raton: CRC Press, 2021.
Schartel B., Hull T. R. Development of fire-retarded materials: Interpretation of cone calorimeter data // Fire and
Materials. — 2007. — Vol. 31, No. 5. — P. 327–354. — DOI: 10.1002/fam.949.
Spear M. J., Curling S. F., Dimitriou A., Ormondroyd G. A. Review of functional treatments for modified wood //
Coatings. — 2021. — Vol. 11, No. 3. — Art. 327. — DOI: 10.3390/coatings11030327.
Thomas A., Moinuddin K., Zhu H., Joseph P. Passive fire protection of wood using some bio-derived fire retardants //
Fire Safety Journal. — 2020. — Vol. 120. — Art. 103074. — DOI: 10.1016/j.firesaf.2020.103074.
Thybring E. E., Fredriksson M. Wood modification as a tool to understand moisture in wood // Forests. — 2021. — Vol.
, No. 3. — Art. 372. — DOI: 10.3390/f12030372.
Wang K., Meng D., Wang S., Sun J., Li H., Gu X., Zhang S. Impregnation of phytic acid into the delignified wood
to realize excellent flame retardant // Industrial Crops and Products. — 2022. — Vol. 176. — Art. 114364. — DOI:
1016/j.indcrop.2021.114364.
Wang R., Fu T., Yang Y.-J., Wang X.-L., Wang Y.-Z. Deeper insights into flame retardancy of polymers by interpretable,
quantifiable, yet accurate machine-learning model // Polymer Degradation and Stability. — 2024. — Vol. 230. — Art.
— DOI: 10.1016/j.polymdegradstab.2024.110981.
Zelinka S. L., Altgen M., Emmerich L., Guigo N., Keplinger T., Kymäläinen M., Thybring E. E., Thygesen L. G. Review
of wood modification and wood functionalization technologies // Forests. — 2022. — Vol. 13, No. 7. — Art. 1004. —
DOI: 10.3390/f13071004.
Zhang R., Zhu Y. Predicting the mechanical properties of heat-treated woods using optimization-algorithm-based
BPNN // Forests. — 2023. — Vol. 14, No. 5. — Art. 935.
Zhang S., Ma K., Wang L., Zhang Z., Ye X., Zhang J., Li H. Prediction of thermal protection performance and empirical
study of flame-retardant cotton based on a combined model // Frontiers in Materials. — 2024. — Vol. 11. — Art.
— DOI: 10.3389/fmats.2024.1454935.
Zhang Z., Jiao Z., Shen R., Song P., Wang Q. Accelerated design of flame retardant polymeric nanocomposites via
machine learning prediction // ACS Applied Engineering Materials. — 2022. — Vol. 1, No. 1. — P. 596–605. — DOI:
1021/acsaenm.2c00145.
Zhou H., Wen D., Hao X., Chen C., Zhao N., Ou R., Wang Q. Nanostructured multifunctional wood hybrids fabricated
via in situ mineralization of zinc borate in hierarchical wood structures // Chemical Engineering Journal. — 2022. —
Vol. 451. — Art. 138308. — DOI: 10.1016/j.cej.2022.138308.
Zhu X., Wu Y., Tian C., Qing Y., Yao C. Synergistic effect of nanosilica aerogel with phosphorus flame retardants on
improving flame retardancy and leaching resistance of wood // Journal of Nanomaterials. — 2014. — Vol. 2014. — Art.
— DOI: 10.1155/2014/867106.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 MUHANDISLIK VA IQTISODIYOT
This work is licensed under a Creative Commons Attribution 4.0 International License.
