Using commercial numerical reservoir simulators to build a full field reservoir model and simultaneously history match multiple dynamic variables for a highly complex, offshore mature field in Malaysia, had proven to be challenging, manpower intensive, highly expensive, and not very successful. This field includes almost two hundred wells that have been completed in more than 60 different, non-continuous reservoir layers. The field has been producing oil, gas and water for decades. The objective of this article is to demonstrate how Artificial Intelligence (AI) and Machine Learning is used to build a purely data-driven reservoir simulation model that successfully history match all the dynamic variables for all the wells in this field and subsequently used for production forecast. The model has been validated in space and time. The AI and Machine Learning technology that was used to build the dynamic reservoir simulation and modeling is called spatio-temporal learning. Spatio-temporal learning is a machine-learning algorithm specifically developed for data-driven modeling of the physics of fluid flow through porous media. Spatio-temporal learning is used in the context of Deconvolutional Neural Networks. In this article Spatio-temporal Learning and Deconvolutional Neural Networks will be explained. This new technology is the result of more than 20 years of research and development in the application of AI and Machine Learning in reservoir modeling. This technology develops a coupled reservoir and wellbore model that for this particular oil & gas field in Malaysia uses choke setting, well-head pressure and well-head temperature as input and simultaneously history matches Oil production, GOR, WC, reservoir pressure, and water saturation for more than a hundred wells through a completely automated process. Once the data-driven reservoir model is developed and history matched, it is blind validated in space and time in order to establish a reliable and robust reservoir model to be used for decision making purposes and opportunity generation to maximise the field value. The concepts and the methodology of history match of multiple wells, individual offshore platforms, and the entire field will be presented in this article along with the results of blind validation and production forecasting. Results of using this model to perform uncertainty quantification will also be presented. A case study of a highly complex mature field with large number of wells and years of production has been used to be studied and simulated by this data-driven approach. Time, efforts, and resources required for the development of the dynamic reservoir simulation models using AI and Machine Learning is considerably less than time and resources required using the commercial numerical simulators. It is validated that the TDM developed model can make very reasonable prediction of field behavior and production from the existing wells based on modification of operational constraints and can be a prudent complementary tool to conventional numerical simulators for such complex assets.
Low resistivity low contrast (LRLC) pays/intervals mostly are being examined via behind casing analysis and produced thru production enhancement works from idle wells in numerous oil fields in Malaysian Basin. However, with the aim of unlocking hydrocarbon volumetric LRLC potential, it should include seismic data analysis in addition to formation analysis behind casing. In the past, these LRLC intervals were often ignored and considered as water-wet sands due to high water saturation or as tight sands. These intervals, which contain significant reserves, have been recognized and presented in several technical papers explaining its appropriate identification and evaluation techniques using well-data (logs and samples/cores). The economic importance of LRLC pay sands in the Malaysian Basin has just recently been demonstrated. These pays may lead to a large areal extent and may contain ten to hundred millions barrels of hydrocarbons. The integration and proper techniques of petrophysics and geophysics may become a vital approach for understanding the hydrocarbon distribution (volumetric) within a large areal extent. The possible environment of depositional for developing LRLC reservoirs are: 1) deep water fans including MTD (mass transport deposit), 2) turbidites, 3) shoreface (middle to lower part), 4) delta complex (i.e. delta front and toe deposits), and 5) channel fills. The LRLC may not occurred in alluvial fans and aeolian deposits. These 5 environment of depositions may accumulate several types of LRLC sediments such as: laminated intervals; bioturbated intervals (with dispersed and/or structural clays); altered framework grains and/or smaller grain size (i.e. silty sand reservoir). The thinly laminated sand is probably the most significant reservoir in term of producing hydrocarbon comparing to the other LRLC types. The understanding of logging tools (wireline, LWD) and its responses can be used to build petrophysical and rock-physic models that can evaluate these LRLC reservoirs. But having available advanced logs such as NMR, Image, sonic (Vp and Vs) logs, it is a plus for a better analysis. Furthermore, an elastic property (rock physics) from seismic data may establish a clear separation for different lithology and fluid saturation on LRLC sands and may lead to future recommendation work on LRLC reservoir characterization. The objective of this paper is to provide the above understanding with explanation and examples. Introduction In Malaysia basins, the LRLC (Low Resisitivity Low Contrast) sands are being recognized and brought into production recently. Previously, these sands were considered negligible in term of its commercial; but now, it has enough evidence confirming by available well-data that these sands are of economic importance. With occurrences of numerous productive intervals have been indentified, it encourages us on understanding further on its geologic background, depositional scheme, geophysic assessment, and proper formation evaluation from available well-data such as well-logs, cores, and production history.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.