{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T09:11:40Z","timestamp":1763543500076,"version":"3.45.0"},"reference-count":31,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Khoury College of Computer Science, Northeastern University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Precise pore pressure prediction is highly essential for safe and effective drilling; however, the nonlinear and heterogeneous nature of the subsurface strata makes it extremely challenging. Conventional physics-based methods are not capable of handling this nonlinearity and variation. Recently, machine learning (ML) methods have been deployed by researchers to enhance prediction performance. These methods are often highly domain-specific and produce good results for the data they are trained for but struggle to generalize to unseen data. This study introduces a Hybrid Meta-Ensemble (HME), a meta model framework, as a novel data mining approach that applies ML methods and ensemble learning on well log data for pore pressure prediction. This proposed study first trains five baseline models including Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Deep Feedforward Neural Network (DFNN), Random Forest (RF), and Extreme Gradient Boost (XGBoost) to capture sequential and nonlinear relationships for pore pressure prediction. The stacked predictions are further improved through a meta learner that adaptively reweighs them according to subsurface heterogeneity, effectively strengthening the ability of ensembles to generalize across diverse geological settings. The experimentation is performed on well log data from four wells located in the Potwar Basin which is one of Pakistan\u2019s principal oil- and gas-producing regions. The proposed Hybrid Meta-Ensemble (HME) has achieved an R2 value of 0.93, outperforming the individual base models. Using the HME approach, the model effectively captures rock heterogeneity by learning optimal nonlinear interactions among the base models, leading to more accurate pressure predictions. Results show that integrating deep learning with robust meta learning substantially improves the accuracy of pore pressure prediction.<\/jats:p>","DOI":"10.3390\/computers14110499","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T08:50:07Z","timestamp":1763542207000},"page":"499","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning Models for Subsurface Pressure Prediction: A Data Mining Approach"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1579-9607","authenticated-orcid":false,"given":"Muhammad Raiees","family":"Amjad","sequence":"first","affiliation":[{"name":"Department of Earth and Environmental Sciences, Bahria School of Engineering and Applied Sciences, Bahria University, Islamabad 46000, Pakistan"}]},{"given":"Rohan Benjamin","family":"Varghese","sequence":"additional","affiliation":[{"name":"Khoury College of Computer Science, Silicon Valley Campus of Northeastern University, San Jose, CA 95113, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1201-498X","authenticated-orcid":false,"given":"Tehmina","family":"Amjad","sequence":"additional","affiliation":[{"name":"Khoury College of Computer Science, Silicon Valley Campus of Northeastern University, San Jose, CA 95113, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"ref_1","unstructured":"Eaton, B.A. (October, January 28). The equation for geopressure prediction from well logs. Proceedings of the SPE Annual Technical Conference and Exhibition, Dallas, TX, USA."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"89","DOI":"10.2118\/27488-PA","article-title":"Pore pressure estimation from velocity data: Accounting for overpressure mechanisms besides undercompaction","volume":"10","author":"Bowers","year":"1995","journal-title":"SPE Drill. Complet."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"105560","DOI":"10.1016\/j.jseaes.2023.105560","article-title":"Precise geopressure predictions in active foreland basins: An application of deep feedforward neural networks","volume":"245","author":"Amjad","year":"2003","journal-title":"J. Asian Earth Sci."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Li, H., Tan, Q., Deng, J., Dong, B., Li, B., Guo, J., Zhang, S., and Bai, W. (2023). A Comprehensive Prediction Method for Pore Pressure in Abnormally High-Pressure Blocks Based on Machine Learning. Processes, 11.","DOI":"10.3390\/pr11092603"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"19035","DOI":"10.1109\/ACCESS.2023.3349216","article-title":"Machine learning in oil and gas exploration: A review","volume":"12","author":"Lawal","year":"2024","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"104548","DOI":"10.1016\/j.cageo.2020.104548","article-title":"A machine learning methodology for multivariate pore-pressure prediction","volume":"143","author":"Yu","year":"2020","journal-title":"Comput. Geosci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2655","DOI":"10.1007\/s11053-023-10244-x","article-title":"Sembar formation as an unconventional prospect: New insights in evaluating shale gas potential combined with deep learning","volume":"32","author":"Amjad","year":"2023","journal-title":"Nat. Resour. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"105173","DOI":"10.1016\/j.rineng.2025.105173","article-title":"Lithofacies and sandstone reservoir characterization for geothermal assessment through artificial intelligence","volume":"26","author":"Naseer","year":"2025","journal-title":"Results Eng."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Elmgerbi, A., and Thonhauser, G. (2025, January 21\u201323). Assessing the Potential of Advanced Sensor Technologies and IoT in Predicting Downhole Drilling Issues. Proceedings of the SPE Gas & Oil Technology Showcase and Conference, GOTECH, Dubai City, UAE.","DOI":"10.2118\/224796-MS"},{"key":"ref_10","first-page":"94104","article-title":"Concepts and techniques","volume":"340","author":"Han","year":"2006","journal-title":"Morgan Kaufmann"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.earscirev.2011.06.001","article-title":"Pore pressure prediction from well logs: Methods, modifications, and new approaches","volume":"108","author":"Zhang","year":"2011","journal-title":"Earth-Sci. Rev."},{"key":"ref_12","first-page":"5611","article-title":"Smart predictions of petrophysical formation pore pressure via robust data-driven intelligent models, Multiscale Multidiscip. Model","volume":"7","author":"Krishna","year":"2024","journal-title":"Exp. Des."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6079","DOI":"10.1007\/s13369-018-3574-7","article-title":"New Model for Pore Pressure Prediction While Drilling Using Artificial Neural Networks","volume":"44","author":"Ahmed","year":"2018","journal-title":"Arab. J. Sci. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"13807","DOI":"10.1021\/acsomega.1c01340","article-title":"Data-Driven Modeling Approach for Pore Pressure Gradient Prediction while Drilling from Drilling Parameters","volume":"6","author":"Abdelaal","year":"2021","journal-title":"ACS Omega"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"110156","DOI":"10.1016\/j.petrol.2022.110156","article-title":"A novel approach to pore pressure modeling based on conventional well logs using convolutional neural network","volume":"211","author":"Matinkia","year":"2022","journal-title":"J. Pet. Sci. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1886","DOI":"10.1002\/ese3.1112","article-title":"Research on prediction methods of formation pore pressure based on machine learning","volume":"10","author":"Huang","year":"2022","journal-title":"Energy Sci. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1799","DOI":"10.1016\/j.jrmge.2022.01.012","article-title":"Machine learning and data-driven prediction of pore pressure from geophysical logs: A case study for the Mangahewa gas field, New Zealand","volume":"14","author":"Radwan","year":"2022","journal-title":"J. Rock Mech. Geotech. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3455","DOI":"10.1007\/s11053-021-09852-2","article-title":"Predicting formation pore-pressure from well-log data with hybrid machine-learning optimization algorithms","volume":"30","author":"Farsi","year":"2021","journal-title":"Nat. Resour. Res."},{"key":"ref_19","first-page":"11318","article-title":"Real-time prediction of formation pressure gradient while drilling","volume":"12","author":"Abdelaal","year":"2022","journal-title":"Nature"},{"key":"ref_20","first-page":"3737873","article-title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","volume":"58","author":"Shi","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"ref_21","first-page":"2","article-title":"Recurrent neural networks","volume":"5","author":"Medsker","year":"2001","journal-title":"Des. Appl."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1016\/j.asej.2020.11.011","article-title":"Extreme gradient boosting (Xgboost) model to predict the groundwater levels in Selangor Malaysia","volume":"12","author":"Osman","year":"2021","journal-title":"Ain Shams Eng. J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","article-title":"A survey of convolutional neural networks: Analysis, applications, and prospects","volume":"33","author":"Li","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_24","unstructured":"Warwick, P.D. (2007). Overview of the geography, geology and structure of the Potwar regional framework assessment project study area, north-ern Pakistan. Regional Studies of the Potwar Plateau Area, northern Pakistan. U.S. Geological Survey. Bulletin 2078\u2013A, Available online: https:\/\/www.academia.edu\/download\/34058136\/B2078_chapter_A.pdf."},{"key":"ref_25","first-page":"ID1","article-title":"Statistical modeling for real-time pore pressure prediction from predrill analysis and well logs","volume":"84","author":"Paglia","year":"2019","journal-title":"Geosci. World"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1515\/geo-2020-0311","article-title":"Improved gas sand facies classification and enhanced reservoir description based on calibrated rock physics modelling: A case study","volume":"13","author":"Shakir","year":"2021","journal-title":"Open Geosci."},{"key":"ref_27","unstructured":"Gao, Y., Chen, M., Liu, P., Yan, G., Sun, D., Wu, J., Liang, L., Huang, Y., Huang, Y., and Sun, M. (March, January 27). Pore Pressure Prediction Using Machine Learning Method. Proceedings of the Offshore Technology Conference Asia, Kuala Lumpur, Malaysia."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Hu, N., Han, B., Long, T., Tan, Q., Deng, J., Liu, W., Feng, Y., Li, X., Yang, H., and Shang, G. (2024, January 18\u201320). Pore Pressure Prediction Model Based on XGBOOST: A Case Study of Complex Geological Strata in Block K. Proceedings of the ARMA\/DGS\/SEG International Geomechanics Symposium, ARMA, Kuala Lumpur, Malaysia. Available online: https:\/\/onepetro.org\/armaigs\/proceedings-abstract\/IGS24\/IGS24\/632582.","DOI":"10.56952\/IGS-2024-0454"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Shi, X., Gou, J., Gong, W., Cao, J., Cao, S., Wang, G., and Ramezanzadeh, A. (2025, January 8\u201311). Machine Learning-Based Pore Pressure Prediction in Deep Reservoirs: Model Comparison and Optimized Application of XGBoost. Proceedings of the ARMA US Rock Mechanics\/Geomechanics Symposium, ARMA, Santa Fe, New Mexico. Available online: https:\/\/onepetro.org\/ARMAUSRMS\/proceedings-abstract\/ARMA25\/ARMA25\/786137.","DOI":"10.56952\/ARMA-2025-0373"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.petsci.2023.09.001","article-title":"A hybrid machine learning optimization algorithm for multivariable pore pressure prediction","volume":"21","author":"Deng","year":"2024","journal-title":"Pet. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2727","DOI":"10.1016\/j.jrmge.2024.09.049","article-title":"Pore pressure prediction based on conventional well logs and seismic data using an advanced machine learning approach","volume":"17","author":"Ehsan","year":"2024","journal-title":"J. Rock Mech. Geotech. Eng."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/11\/499\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T09:07:55Z","timestamp":1763543275000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/11\/499"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":31,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["computers14110499"],"URL":"https:\/\/doi.org\/10.3390\/computers14110499","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,17]]}}}