Abstract
Accurate and real-time prediction of lost circulation is essential for ensuring drilling safety and operational efficiency. Existing data-driven approaches, however, often lack effective integration of domain expertise, which limits their reliability in field applications. To bridge this gap, this study develops an intelligent hybrid model (PSO-BP) that systematically incorporates field-based insights into a machine learning framework. The key contributions are twofold: first, through expert-guided analysis of comprehensive mud logging data, characteristic parameters, including total pit volume, standpipe pressure, flow-in/out difference, and top drive load, are identified as effective indicators of lost circulation; second, a novel prediction model is established by employing Particle Swarm Optimization (PSO) to optimize the initial weights and thresholds of a Backpropagation (BP) neural network, thereby enhancing its convergence speed and predictive stability. Compared with standard BP, Beetle Antennae Search (BAS)-BP, and Genetic Algorithm (GA)-BP models, the proposed PSO-BP model demonstrates superior accuracy in forecasting lost circulation incidents. Validation under actual drilling conditions confirms its practical effectiveness. This research provides a robust and interpretable tool for early loss detection, contributing significantly to risk mitigation, cost reduction, and overall drilling efficiency.
Data availability
The datasets generated and analysed during the present study are not publicly available because of applicable institutional guidelines but are available from the corresponding author upon reasonable request.
References
Ivan, K., Sergey, I. & Dmitry, P. Detection of lost circulation in drilling wells employing sensor data using machine learning technique. Procedia Comput. Sci. 183, 1104–1113 (2019).
Mohammad, S. Application of decision tree, artificial neural network, and adaptive neuro-fuzzy inference system on predicting lost circulation: a case study from Marun oil field. J. Petrol. Sci. Eng. 177, 236–249 (2019).
Sun, W. F., Liu, K. & Zhang, D. Z. A kick and lost circulation monitoring method combining Bi-GRU and drilling conditions. Petroleum Drill. Techniques. 51 (3), 37–44 (2023).
Seabe, P. L., Moutsinga, R. B. & Pindza, E. Forecasting crypto currency prices using LSTM, GRU, and bi-directional LSTM. Fractal Fract. 7 (2), 203 (2023).
Kim, J. Finding the best performing pretrained CNN model for image classification: Using a class activation map to spot abnormalparts in diabetic retinopathy image. Am. J. Biomedical Life Sci. 9 (4), 176–181 (2021).
Galdino, J. F., Oliveira, G. M. & Franco, A. T. Gas kick detection and pressure transmission in thixotropic, compressible drilling fluids. J. Petrol. Sci. Eng. 180, 138–149 (2019).
Zhang, Z., Lai, X. & Lu, C. D. Lost circulation and kick accidents warning based on Bayesian network for the drilling process. Explor. Eng. (Rock Soil. Drill. Tunneling). 47 (4), 114–121 (2020).
Xu, Y. H., Hu, C. H. & Wu, Q. Research on particle swarm optimization in LSTM neural networks for rainfall-runoff simulation. J. Hydrol. 608, 127553 (2022).
Zhang, X., Tian, Y. Y. & Han, Z. L. Research on lost circulation prediction and diagnosis theoretical model based on machine learning algorithm. Drill. Eng. 49 (2), 58–66 (2022).
Yin, H. & Wang, H. B. Intelligent research of complex loss circulation’ warning based on CBR. Bull. Sci. Technol. 34 (4), 195–201 (2018).
Jin, Y., Lu, Y. H. & Li, Z. J. A new method predicting pre-drilling risk in lost circulation formation. 30(3), 24–30 (2008).
Ma, J. Q., You, L. J. & Kang, Y. L. Geological- geophysical method of prediction lost circulation in fractured carbonate formation. 33(3), 90–93 (2010).
Moazzeni, A. R. & Nabaei, M. Prediction of lost circulation using virtual intelligence in one of Iranian Oilfields. Nigeria Annual International Conference and Exhibition, Calabar, Nigeria, (2010).
Xie, P., Jiang, L. W. & Zhao, Y. Research on real-time prediction and analysis based on neural network for well kick and lost circulation. 11, 23–30 (2018).
Zhang, X. Study on lost circulation diagnosis and decision-making system based on case-based reasoning (China University of Petroleum, 2019).
Li, X. S., Zhang, X. & Guan, Z. Development of the drilling mud loss and overflow intelligent alarm system based on the image recognition technology. 28, 48–56 (2021).
Ahmed, K. A., Ali, A. B. & Hayder, A. Intelligent decisions to stop or mitigate lost circulation based on machine learning. Energy 183, 1104–1113 (2019).
Acknowledgements
We acknowledge the contribution of all authors on the whole MS.
Funding
Funding was supported by Research on Automated Crawler Core Drilling Equipment and Process Technology (E210100721).
Author information
Authors and Affiliations
Contributions
We acknowledge the contribution of all authors on the whole MS. Zhenrong Wang completed the whole structure of the MS; Maolin Yang completed the data processing and conception; Ping Du completed the data analysis and figures; Yuing Zhou completed part conception and language, revision.
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
Wang, Z., Yang, M., Du, P. et al. Prediction model of lost circulation based on drilling parameters with PSO-BP neural network. Sci Rep (2026). https://doi.org/10.1038/s41598-026-44613-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-44613-2
