Optimization of production prilling using Bayesian statistics, advanced statistical models, and multivariate analysis: A Comparative study of methods
DOI:
https://doi.org/10.65093/aci.v16.n2.2025.30Keywords:
production drilling optimization, Bayesian statistics, random forests, partial least squares regression (PLS)Abstract
Production drilling in mining is a key process for achieving extraction targets and cost optimization. This paper presents a comprehensive computational and statistical study based on real-world drilling data from a mine in northern Chile. Three complementary approaches are implemented: (i) Bayesian inference to estimate productivity parameters with quantified uncertainty, (ii) advanced statistical modeling—including random forests and partial least squares regression—to predict drilled advance and capture nonlinear interactions, and (iii) multivariate analysis through principal component analysis and logistic regression to identify structural patterns and classify performance. The methodological pipeline integrates data cleaning, imputation, encoding, and cross-validation with company-level balancing. Results demonstrate that integrating these approaches enables the detection of critical variables, optimization of operational parameters, and improvement of predictive traceability. Practical implications for operational management are discussed, and performance metrics across models are compared, providing a reproducible, data-driven framework for decision-making in mining production drilling.
Downloads
References
Bae, S., Lee, H. & Kim, J. (2023). Adaptive bayesian optimization for real-time drilling rate optimization. IEEE Access, 11, 27826–27837.
Blei, D.M., Kucukelbir, A. & McAuliffe, J.D. (2017). Variational inference: A review for statisticians. Journal of the American Statistical Association, 112 (518), 859–877. https://doi.org/10.1080/01621459.2017.1285773
Boukredera, N., Othmani, A., Mellouk, A., Moualek, I. & Idiri, Z. (2025). Ai-driven optimization of drilling performance through torque management using machine learning and differential evolution. Processes, 13 (5),1472. https://doi.org/10.3390/pr13051472
Breiman, L. (2001). Random forests. Machine Learning, 45 (1), 5–32. https://doi.org/10.1023/A:1010933404324
Cihan, P. (2025). Bayesian hyperparameter optimization of machine learning models for predicting biomass gasifi- cation gases. Applied Sciences, 15 (3), 1018. https://doi.org/10.3390/app15031018
Cortes, P. & Onate, E. (2010). Optimization of drilling patterns using genetic algorithms. Computers and Geotechnics, 37 (3), 405–412.
Du, G. & Chen, A. (2025). Coal mine accident risk analysis with large language models and bayesian networks. Sustainability, 17 (5), 1896. https://doi.org/10.3390/su17051896
Fauriat, W. & Zio, E. (2020). Optimization of an aperiodic sequential inspection and condition-based maintenance policy driven by value of information. Reliability Engineering & System Safety, 204, 107133. https://doi.org/10.1016/j.ress.2020.107133
Gelman, A., Carlin, J. B., Stern, H.S., Dunson, D.B., Vehtari, A. & Rubin, D.B. (2013). Bayesian data analysis. Chapman and Hall/CRC. ISBN 978-1439840955. https://doi.org/10.1201/b16018
Hastie, T., Tibshirani, R. & Friedman, J. (2009). The elements of statistical learning. Springer Series in Statistics. https://doi.org/10.1007/978-0-387-84858-7
Jolliffe, I.T. (2002). Principal Component Analysis. Springer, 2nd edition.
Li, Z., Chen, H., Zhang, Y., Zhou, X., Huang, J. & Xu, Q. (2025). Bayesian network-based earth-rock dam breach probability analysis integrating machine learning. Water, 17 (21), 3085. https://doi.org/10.3390/w17213085
Liu, M., Yang, R., Bian, H., Sun, P., and Li, C. (2025). Mtgnn-bayesian-if-dbscan for time-series anomaly detection with applications in industrial drilling. Sensors, 25(15):4717. https://doi.org/10.3390/s25154717
Mohammad, D. & Belayneh, M. (2024). Field telemetry drilling dataset modeling with multivariable regression, gmdh, ann, and gmdh–ann. Applied Sciences, 14(6), 2273. https://doi.org/10.3390/app14062273
Shen, R., Luo, G. & Su, A. (2025). Bayesian optimization for chemical synthesis in the era of artificial intelligence: Advances and applications. Processes, 13 (9), 2687. https://doi.org/10.3390/pr13092687
Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B (Methodological), 58(1), 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
Wold, S., Ruhe, A., Wold, H. & Dunn, W. (1984). The collinearity problem in linear regression. the partial least squares (pls) approach to generalized inverses. SIAM Journal on Scientific and Statistical Computing, 5 (3), 735–743. https://doi.org/10.1137/0905052
Yi, Z., Li, Z., Yi, M., Wang, D. & Cheng, P. (2025). Intelligent real-time risk evaluation and drilling parameteroptimization for enhanced safety in deep-well operations. Processes, 13 (10), 3102. https://doi.org/10.3390/pr13103102
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
