The numbers of machine learning technologies used in subsurface characterization work is increasing with more company rely on data driven to assist in performing any evaluation. In this study, a supervised random forest machine learning approach was utilized in two stages; first stage was to predict static reservoir using well logs and core as inputs. The output is then used as the basis in the second stage to predict initial oil rate (Qi) and subsequently to determine estimated ultimate recovery (EUR) at targeted interval as proposed in the first stage. Static reservoir machine learning prediction outputs were benchmark with available routine core analysis with the result showed R2 of 88% respectively. For initial oil rate (Qi) prediction, a total of 9000 observation points from 20 wells were extracted for training and blind testing process by using variables such as permeability, net thickness, well choke size, well flowing pressure, average pressure, water cut, irreducible water saturation (Swi), and historical production rate. The estimated ultimate recovery (EUR) is then predicted utilizing the thickness of that unit and the decline rate that is obtained from the neighboring wells that has produced from the said reservoir as the analogue. The Qi and EUR results from machine learning is compared with the estimated Qi and EUR using conventional methods for verification purpose. The results from machine learning dynamic properties prediction showed 97% R2 for training while the testing score mean is 87% against the historical data. High R2 from static and dynamic machine learning prediction indicated that the method was reliable and able to assist petroleum engineer in reservoir potential evaluation process.
Accurate prediction of porosity and permeability are crucial to the understanding of fluid distribution and hydrocarbon potential within targeted reservoir. However, increasing reservoir heterogeneity always possess a challenge to conventional method that simplify these complexities, while the high cost of coring acquisition makes it more difficult to validate the result. This paper describes an innovative technique for reservoir properties prediction that combines well logs, core analysis and machine learning tested at 5 wells located in a brownfield offshore Malaysia. Standard well logs of gamma ray, bulk density and neutron porosity were used as main inputs with routine core analysis as targeted outputs. The inputs data were checked and corrected for any light hydrocarbon or borehole washout effect that may affect the learning process. Due to nonlinear relationship between the variables, classification machine learning method of Random Forest was chosen for the study. The ratio of training and blind test was set at 70:30. The algorithm then tested at 100% of the data and benchmarked with core porosity, core permeability and human evaluation judgment based on well logs response at uncored interval. Both porosity and permeability prediction showed R2 of 85% and 80% during blind test which indicated high reliability on training model algorithm. In general, prediction result has a very good correlation with core data at good and thick sand. While at shaly sand, the correlation quality was reduced. At uncored interval, the prediction quality showed a realistic reading when comparing with well logs data response. This further proved the confident in the machine learning algorithm away from core interval. The R2 for porosity prediction was observed higher compare to permeability with average of possibly due to smaller scale ranges. The study showed another perspective to predict reservoir properties using a data driven approach and indicated a very promising result. No constant was used as compared to empirical calculation which introduced less uncertainty into the model. With reduce dependability in core data, the saved cost can be utilized in another multidiscipline task to increase the hydrocarbon recovery.
Predicting permeability in low-medium quality reservoirs (> 10 md to <100mD) is important in brownfields since many of them can still produce hydrocarbons. Developing an approach relating geologic properties to permeability prediction can increase field reserves and extend producing life. The common practice of predicting permeability includes linear regressions of core-porosities vs. core-permeabilities applying different lithofacies. However, these methods discount data scattering around regression-lines. This paper describes an innovative-technique for permeability prediction that combines rock-types, flow-zone-indicator (FZI), and machine-learning techniques (ML). FZI is a reservoir-flow-unit that controls hydraulic fluid-flow and is influenced by pore-geometry resulting from diagenetic-processes. In reservoirs, pore-geometry usually is heterogenous due to mineral-composition, rock-texture, cementation, and compaction. Thus,the commonly used permeability equation of Kozeny-Carman (KC) equation still can be used but it needs to be modified for better connecting FZI to hydraulic-flow-units. The modified KC equation incorporates heterogeneous poregeometry as a non-linear-function of porosity by adding cementation-exponent (m) into the equation, where the original KC equation assumes m is equal to one. The semi-log cross-plot between Reservoir-Quality-Index (RQI) vs. PHIZ*Por(m-1) (or FZIm) from the modified KC equation can be constructed using rock-type class. The ML approach was applied to predict FZI groups using 4 standard-logs: gamma-ray, resistivity, density, and neutron-porosity. Cross-plots of RQI vs. PHIZ (conventional FZI) can be compared to RQI vs. PHIZ*Por(m-1) (modified FZI model) usingdata from 11cored wells in oil field offshore Malaysia. The modified FZI model shows less data clustering compared to the conventional FZI model, shown by higher R2 coefficient correlation accuracy. The proposed modified FZI model shows narrower permeability range at low porosity which is a good indication of more accurate hydraulic-flow-unit interpretation. When applying the original and modified FZI models, each lithofacies may occur in more than one hydraulic-flow-unit due to pore-geometry difference within the same lithofacies. Furthermore, the hydraulic-flow-unit generated by the modified FZI model is more sensitive to total porosity when comparing to original FZI model. Each generated hydraulic-flow-unit has better correlation to total porosity and with less scattered permeability at the same porosity. The permeability calculated by modified FZI model was then verified with core permeability showing an excellent overall match. On the ML technique, the "Random Forests" technique will be utilized due to recognized as one of the most recent ML algorithm(s) developed as an innovative technique based on both classifications and regression trees techniques. The Random Forests technique has shown its great accuracy on predictive exactness for these challenge permeability estimations. The prediction quality was benchmark by R2 value of > 0.9 for all crossplots (porosity, permeability, and water saturation) when comparing to routine core analysis lab measurements.
Predicting the spatial distribution of rock properties is the key to a successful reservoir evaluation for hydrocarbon potential. However, a reservoir with a complex environmental setting (e.g. shallow marine) becomes more challenging to be characterized due to variations of clay, grain size, compaction, cementation, and other diagenetic effects. The assumption of increasing permeability value with an increase of porosity may not be always the case in such an environment. This study aims to investigate factors controlling the porosity and permeability relationships at Lower J Reservoir of J20, J25, and J30, Malay Basin. Porosity permeability values from routine core analysis were plotted accordingly in four different sets which are: lithofacies based, stratigraphic members based, quartz volume-based, and grain-sized based, to investigate the trend in relating porosity and permeability distribution. Based on petrographical studies, the effect of grain sorting, mineral type, and diagenetic event on reservoir properties was investigated and characterized. The clay type and its morphology were analyzed using X-ray Diffractometer (XRD) and Spectral electron microscopy. Results from porosity and permeability cross-plot show that lithofacies type play a significant control on reservoir quality. It shows that most of the S1 and S2 located at top of the plot while lower grade lithofacies of S41, S42, and S43 distributed at the middle and lower zone of the plot. However, there are certain points of best and lower quality lithofacies not located in the theoretical area. The detailed analysis of petrographic studies shows that the diagenetic effect of cementation and clay coating destroys porosity while mineral dissolution improved porosity. A porosity permeability plot based on stratigraphic members showed that J20 points located at the top indicating less compaction effect to reservoir properties. J25 and J30 points were observed randomly distributed located at the middle and bottom zone suggesting that compaction has less effect on both J25 and J30 sands. Lithofacies description that was done by visual analysis through cores only may not correlate-able with rock properties. This is possibly due to the diagenetic effect which controls porosity and permeability cannot visually be seen at the core. By incorporating petrographical analysis results, the relationship between porosity, permeability, and lithofacies can be further improved for better reservoir characterization. The study might change the conventional concept that lower quality lithofacies does not have economic hydrocarbon potential and unlock more hydrocarbon-bearing reserves especially in these types of environmental settings.
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.