Abstract
In blasting engineering, accurate prediction of peak particle velocity (PPV) is essential to ensuring the safety of surrounding structures. In machine-learning-based PPV prediction, symmetric loss functions (e.g. MSE) are commonly adopted as optimisation objectives. However, these functions treat overestimation and underestimation equally, making them ill-suited for applications with stringent safety requirements, where hazardous underestimation must be avoided. To address this limitation, a risk-oriented hybrid ensemble model is proposed to enhance both safety and reliability while maintaining high prediction accuracy. Three gradient-boosting tree models—LightGBM, XGBoost, and CatBoost—are employed as base learners and integrated using a stacking framework. To obtain near-optimal configurations for the three base learners, Bayesian Optimisation (BO), Grey Wolf Optimiser (GWO), and Particle Swarm Optimisation (PSO) are employed for hyperparameter tuning. Building on the ensemble framework, an asymmetric safety assessment system is proposed. Model performance near the PPV safety threshold is quantified using the asymmetric weighted mean squared error (W-MSE) and the hazardous low-estimation rate (HLR). The results indicate that the integrated model achieves strong overall performance and effectively suppresses hazardous underestimation. The integrated model demonstrates clear advantages in PPV prediction. Moreover, it provides a reusable paradigm for embedding engineering safety constraints into machine learning training and evaluation, thereby offering reliable technical support for safety planning and risk minimisation in blasting projects.
Similar content being viewed by others
Data availability
If necessary, the raw data in the manuscript can be obtained by contacting the first author or corresponding author.The code used for data preprocessing, model training, hyperparameter optimization, and performance evaluation in this study is publicly available in a GitHub repository and archived with a permanent DOI (https://doi.org/10.5281/zenodo.18058377).
Abbreviations
- PPV:
-
Peak particle velocity
- BO-LGBM:
-
Bayesian optimisation–light gradient boosting machine
- GWO-XGBoost:
-
Grey wolf optimisation–extreme gradient boosting
- PSO-CatBoost:
-
Particle swarm optimisation–categorical boosting
- LGBM/LightGBM:
-
Light gradient boosting machine
- XGBoost:
-
Extreme gradient boosting
- CatBoost:
-
Categorical boosting
- BO:
-
Bayesian optimisation
- GWO:
-
Grey wolf optimisation
- PSO:
-
Particle swarm optimisation
- WOA:
-
Whale optimisation algorithm
- GA:
-
Genetic algorithm
- Jaya:
-
Jaya optimisation algorithm
- MOPSO:
-
Multi-objective PSO
- PCA:
-
Principal component analysis
- RFE:
-
Recursive feature elimination
- CART:
-
Classification and regression tree
- KNN:
-
K-nearest neighbors
- SVM:
-
Support vector machine
- SVR:
-
Support vector regression
- ANN:
-
Artificial neural network
- BPNN:
-
Back-propagation neural network
- ELM:
-
Extreme learning machine
- EWT:
-
Empirical wavelet transform
- IM:
-
Itemset mining
- RBF:
-
Radial basis function
- DT:
-
Decision tree
- RF:
-
Random forest
- GPR:
-
Gaussian process regression
- LSSVM:
-
Least-squares SVM
- MLR:
-
Multiple linear regression
- LSTM:
-
Long short-term memory
- CSO:
-
Cuckoo search optimisation
- RVM:
-
Relevance vector machine
- MARS:
-
Multivariate adaptive regression splines
- VAF:
-
Variance accounted for
- MVRA:
-
Multivariate regression analysis
- SHAP:
-
SHapley Additive exPlanations
- USBM:
-
U.S. bureau of mines formula
- R2 :
-
Coefficient of determination
- RMSE:
-
Root mean square error
- MAE:
-
Mean absolute error
- MSE:
-
Mean squared error
- PBIAS:
-
Percent bias
- a20:
-
A20 index
- WI:
-
Willmott index of agreement
- W-MSE:
-
Weighted mean squared error
- HLR:
-
Hazardous low-estimation rate
References
Ma, Z. X. et al. Intelligent optimization of blasting parameters in railroad tunnels based on blasting quality control. J. Constr. Eng. Manag. 151, 04025094 (2025).
Heath, D. J., Gad, E. F. & Wilson, J. L. Blast vibration and environmental loads acting on residential structures: State-of-the-art review. J. Perform. Constr. Facil. 30, 04015021 (2016).
Guo, J. W., Fei, H. L. & Yan, Y. Research and advances in the characteristics of blast-induced vibration frequencies. Buildings 15, 892 (2025).
Zhou, J., Zhang, Y. L. & Qiu, Y. G. State-of-the-art review of machine learning and optimization algorithms applications in environmental effects of blasting. Artif. Intell. Rev. 57, 5 (2024).
Gao, Y. F., Fu, H. X., Rong, X. & Paneiro, G. Ground-borne vibration model in the near field of tunnel blasting. Appl. Sci. 13, 87 (2022).
Zou, P., Wang, L., Dai, Y. & Zhang, C. Y. Construction and application of blasting vibration prediction system based on SSA-XGBoost. Blasting 40, 199–205 (2023).
Indian Standard Institute. Criteria for safety and design of structures subjected to underground blast (IS 6922). Indian Standard Institute (1973).
Morena, B. I. Prediction of blast vibrations from quarries using machine learning algorithms and empirical formulae (University of the Witwatersrand, 2019).
Xie, L. K., Yu, Q. L., Liu, J. D., Wu, C. P. & Zhang, G. Prediction of ground vibration velocity induced by long hole blasting using a particle swarm optimization algorithm. Appl. Sci. 14, 3839 (2024).
Khan, M. F. H. et al. Ground vibration effect evaluation due to blasting operations. Heliyon 11, e41759 (2025).
Nguyen, H., Choi, Y., Monjezi, M., Van Thieu, N. & Tran, T. T. Predicting different components of blast-induced ground vibration using earthworm optimisation-based adaptive neuro-fuzzy inference system. Int. J. Min. Reclam. Environ. 38, 99–126 (2024).
Shi, J. J., Guo, S. C. & Zhang, W. Expansion of blast vibration attenuation equations for deeply buried small clearance tunnels based on dimensional analysis. Front. Earth Sci. 10, 889504 (2022).
Xu, S. D., Li, Y. H., Liu, J. P. & Zhang, F. P. Optimization of blasting parameters for an underground mine through prediction of blasting vibration. J. Vib. Control 25, 1585–1595 (2019).
Dong, L. J., Li, X. B., Xu, M. & Li, Q. Y. Comparisons of random forest and support vector machine for predicting blasting vibration characteristic parameters. Procedia Eng. 26, 1772–1781 (2011).
Nguyen, H. et al. Evaluating and predicting blast-induced ground vibration in open-cast mine using ANN: a case study in Vietnam. SN Appl. Sci. 1, 125 (2019).
Monjezi, M., Ghafurikalajahi, M. & Bahrami, A. Prediction of blast-induced ground vibration using artificial neural networks. Tunnell. Undergr. Space Technol. 26, 46–50 (2011).
Rana, A. et al. Predicting blast-induced ground vibrations in some Indian tunnels: A comparison of decision tree, artificial neural network and multivariate regression methods. Min. Metall. Explor. 37, 1039–1053 (2020).
Aruna, M. et al. Enhancing safety in surface mine blasting operations with IoT-based ground vibration monitoring and prediction system integrated with machine learning. Sci. Rep. 15, 3999 (2025).
Dzimunya, N., Besa, B. & Nyirenda, R. Prediction of ground vibrations induced by bench blasting using the random forest algorithm. J. S. Afr. Inst. Min. Metall. 123, 123–132 (2023).
Fissha, Y. et al. Evaluation and prediction of blast-induced ground vibrations: A Gaussian process regression (GPR) approach. Mining 3, 659–682 (2023).
Arthur, C. K. et al. Prediction of blast-induced ground vibration at a limestone quarry: an artificial intelligence approach. Appl. Sci. 12, 9189 (2022).
Yuan, H. et al. Assessment of peak particle velocity of blast vibration using hybrid soft computing approaches. J. Comput. Des. Eng. 12, 154–176 (2025).
Zhang, W. T. et al. Prediction of peak vibration velocity of open-pit mine blasting based on PCA-WOA-XGBoost. Eng. Blast. 30, 155–167 (2024).
Guo, J., Zhang, C., Xie, S. D. & Liu, Y. Research on the prediction model of blasting vibration velocity in the Dahuangshan mine. Appl. Sci. 12, 5849 (2022).
Zhou, J., Qiu, Y. G., Khandelwal, M., Zhu, S. L. & Zhang, X. L. Developing a hybrid model of Jaya algorithm-based extreme gradient boosting machine to estimate blast-induced ground vibrations. Int. J. Rock Mech. Min. Sci. 145, 104856 (2021).
Fissha, Y. et al. Predicting ground vibration during rock blasting using relevance vector machine improved with dual kernels and metaheuristic algorithms. Sci. Rep. 14, 20026 (2024).
Chi, X. H., Yue, Y. L., Jin, Z. P., Zhang, P. F. & Sun, X. PSO-SVM machine learning for blasting vibration velocity prediction in open pit mines. Preprints (2025).
Guo, J., Zhao, P. D. & Li, P. F. Prediction and optimization of blasting-induced ground vibration in open-pit mines using intelligent algorithms. Appl. Sci. 13, 7166 (2023).
Jahed Armaghani, D., Kumar, D., Samui, P., Hasanipanah, M. & Roy, B. A novel approach for forecasting of ground vibrations resulting from blasting: Modified particle swarm optimization coupled extreme learning machine. Eng. Comput. 37, 3221–3235 (2021).
Tao, Y. B., Chen, Q. S., Xiao, C. C., Zhu, M. & Qiu, J. H. Artificial intelligence models for predicting ground vibrations in deep underground mines to ensure the safety of their surroundings. Appl. Sci. 14, 4771 (2024).
Amiri, M., Hasanipanah, M. & Bakhshandeh Amnieh, H. Predicting ground vibration induced by rock blasting using a novel hybrid of neural network and itemset mining. Neural Comput. Appl. 32, 14681–14699 (2020).
Nguyen, H., Choi, Y., Bui, X. N. & Nguyen-Thoi, T. Predicting blast-induced ground vibration in open-pit mines using vibration sensors and support vector regression-based optimization algorithms. Sensors 20, 132 (2019).
Hosseini, S. et al. Assessment of the ground vibration during blasting in mining projects using different computational approaches. Sci. Rep. 13, 18582 (2023).
Bui, X. N., Nguyen, H., Tran, Q. H., Nguyen, D. A. & Bui, H. B. Predicting ground vibrations due to mine blasting using a novel artificial neural network-based cuckoo search optimization. Nat. Resour. Res. 30, 2663–2685 (2021).
Sutha, A., Tangaramvong, S. C. & Gao, W. Chaotic enhanced leader slime mold algorithm for dome structures with frequency constraints. Sci. Rep. 15, 31165 (2025).
Sutha, A., Tangaramvong, S. C., Pyone, E. C. & Gao, W. Artemisinin slime mold algorithm for large-scale truss optimization under frequency constraints. Structures 80, 110045 (2025).
Weng, W. S., Zhang, M. L., Zhao, Y. & Wang, H. L. Prediction of blast vibration velocity based on multi-model dynamic weighting ensemble. Mech. Adv. Mater. Struct. 32, 1–18 (2025).
Hosseini, S., Pourmirzaee, R., Armaghani, D. J. & Sabrisabri, M. M. Prediction of ground vibration due to mine blasting in a surface lead–zinc mine using machine learning ensemble techniques. Sci. Rep. 13, 6591 (2023).
Bozkurt Keser, S., Yavuz, M. & Erten, G. E. Advancing the prediction and evaluation of blast-induced ground vibration using deep ensemble learning with uncertainty assessment. Geosciences 15, 182 (2025).
Ke, G. L. et al. Lightgbm: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 30 (2017).
Dai, Z. H. & Huang, W. G. Improving energy management practices through accurate building energy consumption prediction: Analyzing the performance of LightGBM, RF, and XGBoost models with advanced optimization strategies. Electr. Eng. 107, 1–23 (2025).
Cui, J. X. & Yang, B. A review of Bayesian optimization methods and applications. J. Softw. 29, 3068–3090 (2018).
Sun, M. Z. et al. Research on prediction of PPV in open-pit mine used RUN-XGBoost model. Heliyon https://doi.org/10.1016/j.heliyon.2024.e28246 (2024).
Sadeghian, Z., Akbari, E., Nematzadeh, H. & Motameni, H. A review of feature selection methods based on meta-heuristic algorithms. J. Exp. Theor. Artif. Intell. 37, 1–51 (2025).
Cai, M., Sun, J., Li, P. D. & Bao, Q. Comparative analysis of three machine learning algorithms in regression applications. Intell. Comput. Appl. 12, 165–170 (2022).
Shahnazar, A. et al. A new developed approach for the prediction of ground vibration using a hybrid PSO-optimized ANFIS-based model. Environ. Earth Sci. 76, 527 (2017).
Shylaja, G. & Prashanth, R. A systematic survey of hybrid ML techniques for predicting peak particle velocity (PPV) in open-cast mine blasting operations. Artif. Intell. Rev. 58, 203 (2025).
Yan, Y., Guo, J. W., Bao, S. J. & Fei, H. L. Prediction of peak particle velocity using hybrid random forest approach. Sci. Rep. 14, 30793 (2024).
Kaplan, S. & Garrick, B. J. On the quantitative definition of risk. Risk Anal. 1, 11–27 (1981).
Ministry of Public Security of the People’s Republic of China. Safety regulations for blasting (GB 6722–2014). China Planning Press, Beijing, China (2014).
Ali, S. et al. Explainable artificial intelligence (XAI): What we know and what is left to attain trustworthy artificial intelligence. Inf. Fusion 99, 101805 (2023).
Abdollahi, A., Li, D., Deng, J. & Amini, A. An explainable artificial-intelligence-aided safety factor prediction of road embankments. Eng. Appl. Artif. Intell. 136, 108854 (2024).
Acknowledgements
The work described in this paper was supported by the National Natural Science Foundation of China (52304108), Central guide local science and technology development fund project (regional science and technology innovation system project) (254Z3801G), Basic research projects of shijiazhuang universities in hebei province (241790797A), Zhangjiakou Basic Research and Talent Training Program Project (2511012A), Graduate Innovation Fund Project of Hebei University of Architecture (XY2025106), Graduate Innovation Fund Project of Hebei University of Architecture (XY2026024).
Funding
Hebei University of Architecture.
Author information
Authors and Affiliations
Contributions
Ge Lijie was responsible for writing the paper. He Jianhui was responsible for the typesetting and review of the paper. Zhang Zhuang was responsible for the theoretical derivation of the paper content. Yin Lujun was responsible for the model construction part of the paper content. Jia Shiqi was responsible for the data processing part of the paper content. Zhao Yan was responsible for the visualisation and figure preparation of the paper.
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-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
Ge, L., He, J., Zhang, Z. et al. Particle peak velocity prediction based on risk-oriented hybrid ensemble learning. Sci Rep (2026). https://doi.org/10.1038/s41598-026-48622-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-48622-z
