JOURNAL OF ROCK MECHANICS

JOURNAL OF ROCK MECHANICS

Prediction of Safe Mud Weight Window Using Hybrid Machine Learning Models Based on Multilayer Perceptron and Meta heuristic Optimization Algorithms

Articles in Press

Document Type : Original Article

Authors
Meysam Rajabi 1
hamzeh ghorbani 2
Seyed Vahid Alavi Nezhad Khalil Abad 3
1 Birjand University of Technology
2 Graduated in Petroleum Engineering, Young Researchers and Elite Club, Islamic Azad University, Ahvaz, Iran
3 Department of Civil Engineering, Birjand University of Technology
10.22034/irsrm.2026.583681.1082
Abstract
Accurate determination of the safe mud weight window is a critical challenge in drilling engineering, with direct implications for wellbore stability, lost circulation prevention, and reduction of non-productive time (NPT) and associated operational costs. In this study, hybrid machine learning (ML) models were developed to predict the lower bound of the mud weight window — defined by the collapse pressure — and the upper bound — constrained by the fracture pressure gradient. To this end, a multilayer perceptron (MLP) neural network was integrated with four distinct optimization algorithms: the Firefly Algorithm (FA), Gravitational Search Algorithm (GSA), Artificial Bee Colony (ABC) and Imperialist Competitive Algorithm (ICA). The dataset comprised well-log and geomechanical data acquired from three wells in an gas field located in southern Iran. Following data normalization, the dataset was partitioned into training (70%), validation (15%), and test (15%) subsets. When assessing the safe mud weight window within the test subset of the Multi-Layer Perceptron-Gravitational Search algorithm, minimal errors are evident for both the minimum drilling mud weight pressure (RMSE = 12.283 psi; R2 = 0.9014) and the maximum mud weight pressure during drilling (RMSE = 12.536 psi; R2 = 0.9417). These findings indicate that hybrid machine learning frameworks can substantially enhance the predictive accuracy of the safe mud weight window and offer a robust, data-driven decision-support tool for real-time drilling operations.
Keywords
Safe Mud Weight Window
Petroleum Geomechanics
Machine Learning
Multilayer Perceptron
Metaheuristic Optimization
[1] Chen, C. Ji, G. Wang, H. Huang, H. Baud, P. Wu, Q. (2022). Geology-engineering integration to improve drilling speed and safety in ultra-deep clastic reservoirs of the Qiulitage structural belt. Advances in Geo-Energy Research, (6), 347-356.
[2] Asadi, A. (2017). Application of artificial neural networks in prediction of uniaxial compressive strength of rocks using well logs and drilling data. Procedia Engineering, (191), 279-286.
[3] Perchikolaee, RS. Shadizadeh, SR. Shahryar, K. Kazemzadeh, E. (2010). Building a Precise Mechanical Earth Model and its Application in Drilling Operation Optimization: A Case Study of Asmari Formation in Mansuri Oil Field. SPE, 132204.
[4] Zevgolis, IE. Deliveris, AV. Koukouzas, NC. (2018). Probabilistic design optimization and simplified geotechnical risk analysis for large open pit excavations. Computers and Geotechnics, (103), 153-164.
[5] Jiang, G. Tengfei, D. Kaixiao, CUI. Yinbo, HE. Xiaohu, Q. Lili, Y. (2022). Research status and development directions of intelligent drilling fluid technologies. Petroleum Exploration and Development, (49), 660-670.
[6] Khakzad, N. Khan, F. Amyotte, P. (2013). Quantitative risk analysis of offshore drilling operations: A Bayesian approach. Safety science, (57), 108-117.
[7] Al-Nutaifi, AM. (2014). Wellbore Instability Analysis in a Highly Fractured Carbonate Gas Reservoirs. International Petroleum Technology Conference, Kuala Lumpur, Malaysia, 1-10.
[8] Maleki, S. Gholami, R. Rasouli, V. Moradzadeh, A. Riabi, RG. Sadaghzadeh, F. (2014). Comparison of different failure criteria in prediction of safe mud weigh window in drilling practice. Earth-Science Reviews, (136), 36-58.
[9] Akbarpour, M. Abdideh, M. (2020). Wellbore stability analysis based on geomechanical modeling using finite element method. Modeling Earth Systems and Environment, (6), 617-626.
[10] Epelle, EI. Gerogiorgis, DI. (2020). A review of technological advances and open challenges for oil and gas drilling systems engineering. AIChE Journal, (66), 16842.
[11] Jung, H. Jeon, J. Choi, D. Park, J-Y. (2021). Application of machine learning techniques in injection molding quality prediction: Implications on sustainable manufacturing industry. Sustainability, (13), 4120.
[12] Zhang, W. Li, H. Li, Y. Liu, H. Chen, Y. Ding, X. (2021). Application of deep learning algorithms in geotechnical engineering: a short critical review. Artificial Intelligence Review, (54), 1-41.
[13] Abidin, MH. (2014). Pore pressure estimation using artificial neural network. A project dissertation submitted to the bachelor of Petroleum Engineering, PETRONAS University of Technology.
[14] Kiss, A. Fruhwirth, RK. Pongratz, R. Maier, R. Hofstätter, H. (2018). Formation breakdown pressure prediction with artificial neural networks. SPE, D023S09R02.
[15] Ahmed, A. Elkatatny, S. Ali, A. Abughaban, M. Abdulraheem, A. (2020). Application of artificial intelligence techniques in predicting the lost circulation zones using drilling sensors. Journal of Sensors, (2020), 1-18.
[16] Zahiri, J. Abdideh, M. Ghaleh Golab, E. (2019). Determination of safe mud weight window based on well logging data using artificial intelligence. Geosystem Engineering, (22), 193-205.
[17] Matinkia, M. Amraeiniya, A. Behboud, MM. Mehrad, M. Bajolvand, M. Gandomgoun, MH. (2022). A novel approach to pore pressure modeling based on conventional well logs using convolutional neural network. Journal of Petroleum Science and Engineering, (211), 110-156.
[18] Phan, DT. Liu, C. AlTammar, MJ. Han, Y. Abousleiman, YN. (2022). Application of artificial intelligence to predict time-dependent mud-weight windows in real time. SPE Journal, (27), 39-59.
[19] Beheshtian,S., Rajabi,M., Davoodi,S., Wood,D.A, Ghorbani,H., Mohamadian,N., Ahmadi Alvar,M., Band,S. (2022),  Robust computational approach to determine the safe mud weight window using well-log data from a large gas reservoir, Marine and Petroleum Geology (142) ,105772.
[20] Zhang, W., Li, H., Liu, Y., & Chen, X. (2025). Machine learning approach for prediction of safe mud weight window based on geochemical drilling log data. Frontiers in Earth Science, 13, 1529320. https://doi.org/10.3389/feart.2025.1529320
[21] Chen, C., Wang, G., Huang, H., Wu, Q., & Baud, P. (2025). Prediction of mud weight window based on geological sequence matching and a physics-driven machine learning model. Processes, 13(7), 2255. https://doi.org/10.3390/pr13072255
 [22] Gao, G. Hazbeh, O. Davoodi, S. Tabasi, M. Rajabi, M. Ghorbani, H. et al. (2023). Prediction of fracture density in a gas reservoir using robust computational approaches. Frontiers in Earth Science, (10), 1023578.
[23] Sánchez-Gutiérrez, ME. González-Pérez, PP. (2022). Multi-Class Classification of Medical Data Based on Neural Network Pruning and Information-Entropy Measures. Entropy, (24), 196.
[24] Ross, A. Leroux, N. De Riz, A. Marković, D. Sanz-Hernández, D. Trastoy, J. et al. (2023). Multilayer spintronic neural networks with radiofrequency connections. Nature Nanotechnology, (1), 1-8.
[25] Guo, H. Guo, C. Xu, B. Xia, Y. Sun, F. (2021). MLP neural network-based regional logistics demand prediction. Neural Computing and Applications, (33), 3939-3952.
[26] Desai, M. Shah, M. (2021). An anatomization on breast cancer detection and diagnosis employing multi-layer perceptron neural network (MLP) and Convolutional neural network (CNN). Clinical eHealth, (4), 1-11.
[27] Da Silva, IN. Hernane Spatti, D. Andrade Flauzino, R. Liboni, LHB. dos Reis Alves, SF. et al. (2017). Artificial neural network architectures and training processes. Switzerland: Springer, 62 .
[28] Gautam, GD. Mishra, DR. (2019). Firefly algorithm based optimization of kerf quality characteristics in pulsed Nd: YAG laser cutting of basalt fiber reinforced composite. Composites, (176), 107340.
[29] Ghorbani, H. Moghadasi, J. Wood, DA. (2017). Prediction of gas flow rates from gas condensate reservoirs through wellhead chokes using a firefly optimization algorithm. Journal of Natural Gas Science and Engineering, (45), 256-271.
[30] Çelik, Y. Kutucu H. (2018). Solving the Tension/Compression Spring Design Problem by an Improved Firefly Algorithm, IDDM, (1), 1-7.
[31] Naserbegi, A. Aghaie, M. Minuchehr, A. Alahyarizadeh, G. (2018). A novel exergy optimization of Bushehr nuclear power plant by gravitational search algorithm (GSA). Energy, (148), 373-385.
[32] Rashedi, E. Rashedi, E. Nezamabadi-Pour, H. (2018). A comprehensive survey on gravitational search algorithm. Swarm and evolutionary computation, (41), 141-158.
[33] Duman, S. Sönmez, Y. Güvenç, U. Yörükeren, N. (2012). Optimal reactive power dispatch using a gravitational search algorithm. IET generation, transmission & distribution, (6), 563-576.
[34] Hashemi, A. Dowlatshahi, MB. Nezamabadi-Pour, H. (2021). Gravitational Search Algorithm: Theory, Literature Review, and Applications. Handbook of AI-based Metaheuristics, Boca Raton: CRC Press, 119-150.
[35] Sharma, A. Choudhary, S. Pachauri, RK. Shrivastava, A. Kumar, D. (2020). A review on artificial bee colony and it’s engineering applications. Journal of Critical Reviews, (7), 4097-4107.
[36] Aslan, S. Karaboga, D. (2022). A genetic Artificial Bee Colony algorithm for signal reconstruction based big data optimization. Applied Soft Computing, (88), 106053.
[37] Rahnema, N. Gharehchopogh, FS. (2020). An improved artificial bee colony algorithm based on whale optimization algorithm for data clustering. Multimedia Tools and Applications, (79), 32169-32194.
[38] Talatahari, S. Azar, BF. Sheikholeslami, R. Gandomi, AH. (2012). Imperialist competitive algorithm combined with chaos for global optimization. Communications in Nonlinear Science and Numerical Simulation, (17), 1312-1319.
[39] Mesleh, AM. (2017). Lung Cancer Detection Using Multi-Layer Neural Networks with Independent Component Analysis: A Comparative Study of Training Algorithms. Jordan Journal of Biological Sciences, (10), 239-249.
[40] Shawli, A. (2011). Scoring the SF-36 health survey in scleroderma using independent component analysis and principle component analysis. Master of Science thesis. McGill University, Department of Mathematics and Statistics.
[41] Rutledge, DN. Bouveresse, DJ-R. (2013). Independent components analysis with the JADE algorithm. TrAC Trends in Analytical Chemistry, (50), 22-32.
[42] Ghasemi, M. Ghavidel, S. Ghanbarian, MM. Massrur, HR. Gharibzadeh, M. (2014). Application of imperialist competitive algorithm with its modified techniques for multi-objective optimal power flow problem: a comparative study. Information Sciences, (281), 225-247.
[43] Li, B. Tang, ZB. (2022). Double-assimilation of prosperity and destruction oriented improved imperialist competitive algorithm with computational thinking. IEEE, (1), 1-8.
[44] Bizon, K. Continillo, G. Lombardi, S. Sementa, P. Vaglieco, BM. (2016). Independent component analysis of cycle resolved combustion images from a spark ignition optical engine. Combustion and Flame, (163), 258-269.
JOURNAL OF ROCK MECHANICS

Articles in Press, Accepted Manuscript
Available Online from 21 June 2026