Evaluation of Synthetic Data Generation Methods for ANN-Based Bamboo Property Prediction
Downloads
Data-driven modeling in bamboo research is hindered by the limited availability of openly accessible experimental datasets, as most studies report only summary statistics. This study evaluates whether synthetic data can reliably support data-driven modeling of bamboo mechanical properties. Three synthetic data generation methods – parametric Monte Carlo simulation (PMCS), parametric bootstrapping (PB), and Gaussian copula (GC)–were used to generate datasets based on published statistical descriptors of Bambusa blumeana for multiple sample sizes (N =1,000; 10,000; 100,000). Artificial neural network (ANN) models were developed using each dataset, and both statistical fidelity and predictive performance were assessed. Results indicate that PMCS provides the highest statistical consistency with target distributions, while GC generally yields lower prediction errors. PB demonstrates intermediate performance. Both PMCS and GC exhibit the lowest relative errors, indicating that the means and standard deviations of the generated datasets closely match the target values reported in the literature. Feature importance analysis identifies density and cross-sectional area as the most influential predictors across all methods. Despite differences in statistical fidelity, ANN predictive performance remains comparable. These findings demonstrate that synthetic data can serve as a reliable alternative for experimental datasets and highlight the feasibility of developing ANN-based predictive models using published statistical descriptors.
Downloads
[1] Aniñon, M. J. C., & Garciano, L. E. O. (2024). Advances in Connection Techniques for Raw Bamboo Structures—A Review. Buildings, 14(4), 1126. doi:10.3390/buildings14041126.
[2] Muhammad, N. A. G., Orejudos, J. N., & Aniñon, M. J. C. (2024). A Compendium of Research, Tools, Structural Analysis, and Design for Bamboo Structures. Buildings, 14(8), 2419. doi:10.3390/buildings14082419.
[3] Cacanando, C. J. D., López, L. F., Atienza, E., & Pradhan, N. P. N. (2025). Experimental characterization of mechanical properties of Bambusa blumeana bamboo poles and determination of design values. Construction and Building Materials, 490, 142498. doi:10.1016/j.conbuildmat.2025.142498.
[4] Panti, C. A. T., Cañete, C. S., Navarra, A. R., Rubinas, K. D., Garciano, L. E. O., & López, L. F. (2024). Establishing the Characteristic Compressive Strength Parallel to Fiber of Four Local Philippine Bamboo Species. Sustainability (Switzerland), 16(9), 3845. doi:10.3390/su16093845.
[5] Correal, J. F., Calvo, A. F., Trujillo, D. J. A., & Echeverry, J. S. (2022). Inference of mechanical properties and structural grades of bamboo by machine learning methods. Construction and Building Materials, 354, 129116. doi:10.1016/j.conbuildmat.2022.129116.
[6] Buachart, C., Hansapinyo, C., Sukontasukkul, P., Zhang, H., Sae-Long, W., Chetchotisak, P., & O’Brien, T. E. (2024). Characteristic and allowable compressive strengths of Dendrocalamus Sericeus bamboo culms with/without node using artificial neural networks. Case Studies in Construction Materials, 20, 2794. doi:10.1016/j.cscm.2023.e02794.
[7] Mallik, M., Dubey, S., & Gupta, D. (2024). Machine learning approach to forecast the tensile strength of bamboo. Journal of Electrical Systems, 20, 1526-1538. doi:10.52783/jes.1456.
[8] Pilapil, R. A. E., Ongpeng, J. M., & Valerio, D. N. (2025). Prediction of Mechanical Properties of Bambusa blumeana Bamboo Culms Using Non-Destructive Indicating Properties. Proceedings of International Exchange and Innovation Conference on Engineering & Sciences (IEICES), 11, 1367–1372. doi:10.5109/7395688.
[9] Ramful, R., & Casseem, M. S. (2023). Prediction of the Mechanical Characteristic of Bamboo Using Deep Neural Network. 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 1–5. doi:10.1109/ICECCME57830.2023.10253219.
[10] Su, Z., Jiang, Z., Liang, Y., Wang, B., & Sun, J. (2022). An artificial neural network model for predicting mechanical strength of bamboo-wood composite based on layups configuration. BioResources, 17(2), 3265–3277. doi:10.15376/biores.17.2.3265-3277.
[11] You, G., Wang, B., Li, J., Chen, A., & Sun, J. (2022). The prediction of MOE of bamboo-wood composites by ANN models based on the non-destructive vibration testing. Journal of Building Engineering, 59, 105078. doi:10.1016/j.jobe.2022.105078.
[12] Goyal, M., & Mahmoud, Q. H. (2024). A Systematic Review of Synthetic Data Generation Techniques Using Generative AI. Electronics (Switzerland), 13(17), 3509. doi:10.3390/electronics13173509.
[13] Endres, M., Mannarapotta Venugopal, A., & Tran, T. S. (2022). Synthetic Data Generation: A Comparative Study. Proceedings of the 26th International Database Engineered Applications Symposium, 94–102. doi:10.1145/3548785.3548793.
[14] Pathare, A., Mangrulkar, R., Suvarna, K., Parekh, A., Thakur, G., & Gawade, A. (2023). Comparison of tabular synthetic data generation techniques using propensity and cluster log metric. International Journal of Information Management Data Insights, 3(2), 100177. doi:10.1016/j.jjimei.2023.100177.
[15] White, M., & Rozovskaya, A. (2020). A Comparative Study of Synthetic Data Generation Methods for Grammatical Error Correction. Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications. doi:10.18653/v1/2020.bea-1.21.
[16] Thielen, N., Rachinger, B., Schröder, F., Preitschaft, A., Meier, S., Seidel, R., Reinhardt, A., & Franke, J. (2024). Comparative Study on Different Methods to Generate Synthetic Data for the Classification of THT Solder Joints. 2024 1st International Conference on Production Technologies and Systems for E-Mobility (EPTS), 1–6. doi:10.1109/EPTS61482.2024.10586740.
[17] Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning. MIT press, Cambridge, United States.
[18] Aniñon, M. J. C., & Albiento, E. E. M. (2022). Prediction of 28-day Compressive Strength of Concrete at the Job Site using Artificial Neural Network. Mindanao Journal of Science and Technology, 20(1), 177–205. doi:10.61310/mndjsteect.1121.22.
[19] Rubinstein, R. Y., & Kroese, D. P. (2016). Simulation and the Monte Carlo Method. Wiley Series in Probability and Statistics., Hoboken, United States. doi:10.1002/9781118631980.
[20] Efron, B., & Tibshirani, R. J. (1994). An Introduction to the Bootstrap. Chapman and Hall/CRC, New York, United States. doi:10.1201/9780429246593.
[21] Nelsen, R. B. (2006). An introduction to copulas. Springer New York, United States.
[22] Zhou, Q., Tian, J., Liu, P., & Zhang, H. (2021). Test and prediction of mechanical properties of Moso bamboo. Journal of Engineered Fibers and Fabrics, 16, 15589250211066802. doi:10.1177/15589250211066802.
[23] Liu, P., Zhou, Q., Fu, F., & Li, W. (2021). Effect of bamboo nodes on the mechanical properties of p. Edulis (phyllostachys edulis) bamboo. Forests, 12(10), 1309. doi:10.3390/f12101309.
[24] Kissell, R. L. (2021). Algorithmic Trading. Algorithmic Trading Methods, 23–56, Academic Press, New York, United States. doi:10.1016/b978-0-12-815630-8.00002-8.
[25] Kostanek, J., Karolczak, K., Kuliczkowski, W., & Watala, C. (2024). Bootstrap Method as a Tool for Analyzing Data with Atypical Distributions Deviating from Parametric Assumptions: Critique and Effectiveness Evaluation. Data, 9(8), 95. doi:10.3390/data9080095.
[26] Sklar, M. (1959). N-dimensional distribution functions and their margins. Annales de l'ISUP, 8(3), 229-231. (In French).
[27] Kim, J. M. (2025). Integrating Copula-Based Random Forest and Deep Learning Approaches for Analyzing Heterogeneous Treatment Effects in Survival Analysis. Mathematics, 13(10), 1659. doi:10.3390/math13101659.
[28] The MathWorks Inc. (2025). MATLAB R2025b. The MathWorks Inc, Natick, United States.
[29] Muhammad, N. A., & Orejudos, J. (2025). Machine Learning-Based Prediction of Mechanical Properties of Bambusa Blumeana. Proceedings of the 5th International Symposium on Concrete Structures for the Next Generation (CSN2025), 3-4 March, 2025, Manila, Philippines.
[30] Bahtiar, E. T., Imanullah, A. P., Hermawan, D., Nugroho, N., & Abdurachman. (2019). Structural grading of three sympodial bamboo culms (Hitam, Andong, and Tali) subjected to axial compressive load. Engineering Structures, 181, 233–245. doi:10.1016/j.engstruct.2018.12.026.
[31] Liu, P., Zhou, Q., & Tian, J. (2022). A Two-variable Model for Predicting the Effects of Moisture Content and Density on the Mechanical Properties of Phyllostachys edulis Bamboo. BioResources, 17(1), 400–410. doi:10.15376/biores.17.1.400-410.
[32] Bautista, B. E., Garciano, L. E. O., & Lopez, L. F. (2021). Comparative analysis of shear strength parallel to fiber of different local bamboo species in the philippines. Sustainability (Switzerland), 13(15), 8164. doi:10.3390/su13158164.
[33] Javadian, A., Smith, I. F. C., Saeidi, N., & Hebel, D. E. (2019). Mechanical properties of bamboo through measurement of culm physical properties for composite fabrication of structural concrete reinforcement. Frontiers in Materials, 6, 15. doi:10.3389/fmats.2019.00015.
[34] Mahzuz, H. M. A., Ahmed, M., Dutta, J., & Rose, R. H. (n.d.). Determination of Several Properties of a Bamboo of Bangladesh. Journal of Civil Engineering Research, 3(1), 16. doi:10.5923/j.jce.20130301.02.
[35] Tangphadungrat, P., Hansapinyo, C., Buachart, C., Suwan, T., & Limkatanyu, S. (2023). Analysis of Non-Destructive Indicating Properties for Predicting Compressive Strengths of Dendrocalamus sericeus Munro Bamboo Culms. Materials, 16(4). doi:10.3390/ma16041352.
- Authors retain all copyrights. It is noticeable that authors will not be forced to sign any copyright transfer agreements.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
