Abstract
Curtain grouting is widely used to control seepage in large-scale water conservancy and hydropower projects, and accurate prediction of grouting volume is essential for ensuring construction quality and cost control. This study proposes a grouting volume prediction model combining Bayesian optimization (BO) with a stacking ensemble learning framework. The model was developed using a dataset of 778 valid grouting records and incorporated seven key input features: hole sequence, hole depth, section length, hole diameter, pre-grouting permeability, initial water-cement ratio, and grouting pressure. Within this framework, XGBoost, LightGBM, and Random Forest were employed as base learners, with BO applied for global hyperparameter optimization. Ridge regression served as the meta-learner to construct the Bayesian-optimized stacking ensemble (BO-Stacking) model. SHapley Additive exPlanations (SHAP) analysis was used to quantify feature contributions and enhance model interpretability. The results show that the BO-Stacking model outperformed the benchmark models, achieving a coefficient of determination (R2) of 0.92, a mean absolute error (MAE) of 70.19 L, and a root mean square error (RMSE) of 187.07 L. Scatter analysis further indicated strong agreement between predicted and measured values. SHAP analysis quantified the relative contributions of geological conditions, construction parameters, and slurry properties to grouting volume. Overall, the proposed approach improves predictive performance of grouting volume under complex geological conditions and provides support for construction planning and quality management.
Similar content being viewed by others
Data availability
The data presented in this study are available on request to the corresponding author. The data are not publicly available due to privacy.
References
Xu, Z. H. et al. Latest research progress and future development direction of grouting numerical simulation in underground engineering. J. Basic. Sci. Eng. 33, 903–922 (2025).
Guo, P. et al. Discrete element analysis of grouting reinforcement and slurry diffusion in overburden strata. Appl. Sci. 15, 8464 (2025).
Xia, K. Grouting Technology Collection (China Water & Power Press, 2015).
Arash, M., Dolatshahi, A. & Shahriar, K. Three-dimensional simulation analysis of the impact of excavation on non-level crossing tunnels. Sci. Rep. https://doi.org/10.1038/s41598-025-33078-4 (2025).
Lan, F. et al. Research on surrounding rock deformation characteristics and support optimization measures for tunnel TBM crossing through fault fracture zones. Sci. Rep. https://doi.org/10.1038/s41598-026-35748-3 (2026).
Zhu, D. et al. Probabilistic stability analyses of two-layer undrained slopes. Comput. Geotech. 182, 107178 (2025).
Wang, L. et al. Fracture evolution of granite under cyclic thermal shocks: effects of liquid nitrogen cooling on strength, toughness, and acoustic emission characteristics. Therm. Sci. Eng. Prog. 70, 104507 (2026).
Liu, M. et al. Experimental study on the structural failure characteristics and load-bearing mechanism of anchored fractured rock mass. Sci. Rep. 16, 4537 (2026).
Zhang, H. et al. Mechanism and application of reaming anchorage of inverted wedge-shaped hole bottom in argillaceous cemented roadway. Sci. Rep. 16, 5094 (2026).
Sohrabi-Bidar, A., Rastegar-Nia, A. & Zolfaghari, A. Estimation of the grout take using empirical relationships (case study: Bakhtiari dam site). Bull. Eng. Geol. Environ. 75, 425–438 (2016).
Li, X. et al. Nonlinear flow characteristics of cement grout in fractures with varying geometries. Sci. Rep. https://doi.org/10.1038/s41598-025-30580-7 (2025).
Rastegarnia, A. et al. Assessment of relationship between grouted values and calculated values in the Bazoft Dam site. Geotech. Geol. Eng. 35, 1299–1310 (2017).
Rouhani, M. M. et al. Cerchar abrasiveness index prediction based on rock properties leveraging hybrid soft computing techniques. Sci. Rep. 15, 37499 (2025).
Thangavel, P. et al. Investigation of cold formed steel angle compression through high throughput design FEA and machine learning. Sci. Rep. 15, 19222 (2025).
Rouhani, M. M. & Dolatshahi, A. Predicting mode I fracture toughness of CCNBD quasi-brittle specimens using hybrid gradient boosting algorithms. Theor. Appl. Fract. Mech. 140, 104966 (2025).
Rouhani, M. M. et al. Intelligent prediction of flyrock hazards in surface mining using optimized gradient boosting models. Nat. Resour. Res. 35, 1–23 (2025).
Sunkpho, J. et al. Sustainable use of red mud in concrete: Assessing mechanical strength, durability, and performance through machine learning models. Green. Technol. Sustain. 4 (2), 100283 (2025).
Katuwal, T. B., Panthi, K. K. & Basnet, C. B. Machine learning approach for prediction of TBM performance and risk of jamming in Himalayan geology using a cross-project tunnelling database. Sci. Rep. https://doi.org/10.1038/s41598-025-34273-z (2026).
Zhong, D. H. et al. Advancements in intelligent dam engineering construction in the intelligence era. J. Hydraul Eng. 56, 1–19 (2025).
Li, K. et al. Grouting flow hybrid prediction model based on CEEMDAN–Transformer. J. Hydraul Eng. 54, 806–817 (2023).
Ouyang, S. M. et al. Grouting volume prediction for underground water-sealed caverns based on TPE–GBT model. Mod. Tunn. Technol. 61, 138–145 (2024).
Tong, F. et al. A hybrid ICEEMDAN-BO-GRU model for real-time grouting parameter prediction. Appl. Soft Comput. 185, 113912 (2025).
Shi, Z. Z. et al. Surrogate model for dam foundation grouting volume prediction based on improved multiple kernel extreme learning machine. Water Resour. Hydropower Eng. 52, 57–66 (2021).
Sun, D. et al. Intelligent prediction of grouting in fractured rock masses. Intelligent Geoengineering 2, 66–79 (2025).
Zhu, Y. S. et al. Research on an ISSA-Stacking ensemble learning surrogate model of dam foundation grouting volume prediction. J. Tianjin Univ. Sci. Technol. 57, 174–185 (2024).
Li, R. et al. Explainable rock mass classification under imbalanced TBM data using ensemble learning. Eng. Appl. Artif. Intell. 162, 112641 (2025).
Abdulrahman, S. et al. Hybrid-optimized ensemble models for predicting compressive strength of fly ash and slag concrete. Mater. Today Commun. 38, 113762 (2025).
Sagi, O. & Rokach, L. Ensemble learning: A survey. WIREs Data Min. Knowl. Discov. 8, e1249 (2018).
Tang, Y. et al. Multi-output prediction of TBM operation parameters using stacking ensemble algorithms. Tunn. Undergr. Space Technol. 152, 105952 (2024).
Chen, T. & Guestrin, C. XGBoost: a scalable tree boosting system. In Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 785–794ACM, (2016).
Ke, G. et al. LightGBM: a highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 30, 3146–3154 (2017).
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).
McDonald, G. C. Ridge regression. WIREs Comput. Stat. 1, 93–100 (2009).
Kumar, D. R. et al. Application of random forest and optimization techniques in forecasting the axial load capacity of lipped channel cold-formed steel sections. J. Soft Comput. Civ. Eng. 10, e1950 (2026).
Liashchynskyi, P. Grid search, random search, and genetic algorithm for hyperparameter optimization. Preprint at (2019). https://arxiv.org/abs/1912.06059
Wang, X. et al. Recent advances in Bayesian optimization. ACM Comput. Surv. 55, 1–36 (2023).
Jabar, A. B. & Thangavel, P. ANN-PSO modelling for predicting buckling of self-compacting concrete column containing RHA properties. Matéria 28, e20230102 (2023).
Negi, G. et al. Grey wolf optimizer: a review and applications. Int. J. Syst. Assur. Eng. Manag. 12, 1–8 (2021).
McGovern, A. et al. Making the black box more transparent. Bull. Am. Meteorol. Soc. 100, 2175–2199 (2019).
Lundberg, S. M. & Lee, S. I. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30, 4765–4774 (2017).
Rouhani, M. M. & Dolatshahi, A. Advanced hybrid models for predicting dynamic compressive strength of rocks: Exploring various input scenarios and introducing novel empirical approaches. Results Eng. 28, 107947 (2025).
Zhe, Y. et al. Prediction model for grouting volume using borehole image features and explainable artificial intelligence. Constr. Build. Mater. 470, 140626 (2025).
Rouhani, M. M., Namin, F. S. & Chakeri, H. Screw conveyor speed prediction for EPB-TBM excavations using hybrid deep learning models. Results Eng. 28, 108064 (2025).
Mishra, D. et al. A review of ensemble learning methods. Int. J. Res. Publ Rev. 6, 3795 (2025).
Pinheiro, J. M. H. et al. The impact of feature scaling in machine learning: Effects on regression and classification tasks. IEEE Access 13, 199903–199931 (2025).
Winter, E. The Shapley value. In Handbook of Game Theory with Economic Applications Vol. 3 (eds Aumann, R. J. & Hart, S.) 2025–2054 (Elsevier, 2002).
Nagelkerke, N. J. D. A note on a general definition of the coefficient of determination. Biometrika 78, 691–692 (1991).
Willmott, C. J. & Matsuura, K. Advantages of the mean absolute error over the root mean square error. Clim. Res. 30, 79–82 (2005).
Sedgwick, P. Pearson’s correlation coefficient. BMJ https://doi.org/10.1136/bmj.e4483 (2012).
Acknowledgements
This work has been supported by China Gezhouba Group Co., Ltd. (CGGC).
Funding
This work is funded by China Energy Engineering Corporation Limited (CEEC) through the Intelligent Grouting System Research and Development Program (CEEC2024-KJZX-03).
Author information
Authors and Affiliations
Contributions
Yahui Ma: Conceptualization, formal analysis, methodology, software, validation, writing—original draft. Zhanquan Yuan: Project administration, supervision, writing—review and editing. Bo Xiong: Resources, supervision. Hongwei Lei: Methodology, software. Weiquan Zhao: Funding acquisition, investigation, supervision, writing—review and editing.
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.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, 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 changes were made. 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/4.0/.
About this article
Cite this article
Ma, Y., Yuan, Z., Xiong, B. et al. Curtain grouting volume prediction using a Bayesian-optimized stacking ensemble model with SHAP analysis. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45538-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45538-6
