Kazakhstan journal for oil & gas industryKazakhstan journal for oil & gas industry2707-42262957-806XKMG Engineering10879710.54859/kjogi108797Research ArticleA review of machine learning techniques for bottomhole pressure monitoring in production wellsZhenisD. K.dimashzhenis.pe@gmail.comhttps://orcid.org/0009-0003-4934-7347KasenovA. K.<p>PhD, Associate Professor</p>a.kasenov@kbtu.kzhttps://orcid.org/0000-0002-1007-1481IbrayevA. Ye.ak.ibrayev@kmge.kzhttps://orcid.org/0009-0005-1731-7092ShayakhmetK. N.kairgeldi.shayakhmet@byteallenergy.comhttps://orcid.org/0000-0001-9269-4545Kazakh-British Technical UniversityKMG EngineeringByteAll Energy240620257261720511202422042025Copyright © 2025, Zhenis D.K., Kasenov A.K., Ibrayev A.Y., Shayakhmet K.N.2025<p>Artificial intelligence is rapidly gaining ground in the oil and gas industry, driven by the need to improve the efficiency of reservoir development and streamline production operations. One of the most promising applications of AI is the analysis of data collected by downhole monitoring systems – particularly those designed to measure bottomhole pressure. As more permanent downhole gauges are deployed across the industry, operators now have access to continuous, real-time insight into reservoir pressure behavior. The widespread use of permanent downhole pressure gauges enables continuous, real-time data collection on reservoir pressure dynamics. As part of a broader big data environment, these data sets require modern architectures for storage, processing and analysis. By applying machine learning algorithms – such as neural networks and regression models – engineers can uncover hidden patterns, predict reservoir parameters, perform transient pressure analysis without shutting down wells, and improve real-time decision making in field operations. This paper reviews the design principles of pressure monitoring systems and examines modern big data architectures, including lambda, kappa and unified frameworks. It also highlights practical applications of machine learning algorithms using both field data and synthetic datasets. The paper demonstrates the effectiveness of combining proxy modelling with machine learning to assess inter-well connectivity and predict production behavior. The discussion is based on real-world case studies from international and Kazakh oil fields, including the use of CRMP-based digital solutions and ensemble modelling approaches.</p>pressure monitoring systemsdownhole telemetry systemsmachine learningartificial intelligenceneural networksbig data architectureproxy modelingpermanent downhole gaugesқысымды бақылау жүйелерітелеметриялық жүйелермашиналық оқытужасанды интеллектнейрондық желілерүлкен деректер архитектурасыпрокси-модельдеуішкі ұңғымалық қысым датчиктерісистемы мониторинга давлениятелеметрические системымашинное обучениеискусственный интеллектнейронные сетиархитектура больших данныхпрокси-моделированиевнутрискважинные датчики давления1.Mohamed H, Jakeman S, Al Azawi B, et al. Engineering Aspects in the Design and Implementation of Onshore Smart Oil Fields. Oil & Gas Fac. 2013;2(05):80–84. doi: 10.2118/161083-PA.2.Marcuccio S, Flygare J, Konopczynski M. Application of Pressure-Monitoring Data in Land-Based Unconventionals. SPE/CSUR Unconventional Resources Conference; 2015 Oct 20–22, 2015; Calgary, Alberta, Canada. Available from: https://onepetro.org/SPEURCC/proceedings-abstract/15URC/15URC/D021S009R006/183658.3.Charalampos C, Jing Z, Sorathia V, et al. Toward an Automatic Metadata Management Framework for Smart Oil Fields. SPE Econ & Mgmt. 2013;5(01):33–43. doi: https://doi.org/10.2118/153271-PA.4.Nadal S, Jovanovic P, Bilalli B, Romero O. Operationalizing and automating Data Governance. Journal of Big Data. 2022;9:117. 10.1186/s40537-022-00673-5.5.Yang X, Bello O, Yang L, et al. Intelligent Oilfield – Cloud Based Big Data Service in Upstream Oil and Gas. The International Petroleum Technology Conference; 2019 March 26–28; Beijing, China. Available from: https://onepetro.org/IPTCONF/proceedings-abstract/19IPTC/1-19IPTC/D011S002R001/154285.6.Müller AC, Guido S. Introduction to Machine Learning with Python. Sebastopol: O’Reilly Media, Inc.; 2016. 392 p.7.Zangl G, Hannerer J. Data Mining: Applications in the Petroleum Industry. Katy, TX: Round Oak Publishing; 2003. 222 p.8.Zheng S-Y, Li XG. Transient pressure analysis of 4D reservoir system response from permanent down hole gauges (PDG) for reservoir monitoring, testing and management. The Asia Pacific Oil and Gas Conference and Exhibition; 2007 Oct 30 – Nov 1, 2007; Jakarta, Indonesia. Available from: https://onepetro.org/SPEAPOG/proceedings-abstract/07APOGCE/07APOGCE/SPE-109112-MS/142768.9.Tian C, Horne RN. Applying Machine Learning Techniques to Interpret Flow Rate, Pressure and Temperature Data from Permanent Downhole Gauges // SPE Western Regional Meeting; 2015 Apr 27–30; Garden Grove, California, USA. Available from: https://onepetro.org/SPEWRM/proceedings-abstract/15WRM/15WRM/SPE-174034-MS/182820.10.Pan Y, Ran B, Peng Z, et al. An Effective Physics-Based Deep Learning Model for Enhancing Production Surveillance and Analysis in Unconventional Reservoirs. SPE/AAPG/SEG Unconventional Resources Technology Conference; 2019 July; Denver, Colorado, USA. Available from: https://chooser.crossref.org/?doi=10.15530%2Furtec-2019-145.11.Silva VCD. Big Data Approach for Assessing Hydraulic Interference Between Wells in Not-Controled Systems. The Offshore Technology Conference Brasil; 2019 Oct 29–31; Rio de Janeiro, Brazil. Available from: https://onepetro.org/OTCBRASIL/proceedings-abstract/19OTCB/1-19OTCB/D011S013R006/180771.12.Zhetruov ZT, Shayakhmet KN, Karsybayev KK, et al. Application of proxy models for oil reservoirs performance prediction. Kazakhstan journal for oil & gas industry. 2022;4(2):47–56. doi: 10.54859/kjogi108021.13.Albertoni A, Lake LW. Inferring interwell connectivity only from well-rate fluctuations in waterfloods. SPE Reserv. Eval. Eng. 2003;6(01):6–16. doi: https://doi.org/10.2118/83381-PA.