Improved Permeability Prediction of a Heterogeneous Carbonate Reservoir Using Artificial Neural Networks Based on the Flow Zone Index Approach

Abstract

Permeability is one of the most important parameters required for reservoir characterization. Although core analysis provides more exact information, core data do not exist for all wells in the reservoir because coring is expensive and time consuming. Therefore, another approach should be sought for permeability determination. The objective of this study was to create an artificial neural network (ANN) model in order to use well log data to predict permeability in uncored wells/intervals. The well log, core, and other data were gathered from an Iranian heterogeneous carbonate reservoir. A flow zone indicator was then predicted using an ANN approach with well logs as input variables. The reservoir was thus classified into different zones based on hydraulic flow units to overcome the extreme heterogeneity. Then, a separate ANN training procedure was followed for each flow zone with log data as input variables and permeability as output. This improved method is capable of permeability prediction in heterogeneous carbonate reservoirs in uncored wells/intervals with an average error of less than 10.9%.     

DETERMINING HYDRAULIC FLOW UNITS USING A HYBRID NEURAL NETWORK AND MULTI‐RESOLUTION GRAPH‐BASED CLUSTERING METHOD: CASE STUDY FROM SOUTH PARS GASFIELD,IRAN

Hydraulic flow units are defined as reservoir units with lateral continuity whose geological properties controlling fluid flow are consistent and different from those of other flow units. Because pore‐throat size is the ultimate control on fluid flow, each flow unit has a relatively similar pore‐throat size distribution resulting in consistent flow behaviour. The relations between porosity and permeability in terms of hydraulic flow units can be used to characterize heterogeneous carbonate reservoirs. In this study, a quantitative correlation is made between hydraulic flow units and well logs in South Pars gasfield, offshore southern Iran, by integrating intelligent and clustering methods of data analysis. For this purpose, a supervised artificial neural network model was integrated with multi‐resolution graph‐based clustering (MRGC) to identify hydraulic flow units from well log data. The hybrid model provides a more precise definition of flow units compared to definitions based only on a neural network. There is a good agreement between the results of well log analyses and core‐derived flow units. The synthesized flow units derived from the well log data are sufficiently reliable to be considered as inputs in the construction of a 3D reservoir model of the South Pars field.     

The Estimation of Formation Permeability in a Carbonate Reservoir Using an Artificial Neural Network

Abstract

Reservoir permeability is an important parameter that its reliable prediction is necessary for reservoir performance assessment and management. Although many empirical formulas are derived regarding permeability and porosity in sandstone reservoirs, these correlations cannot be accurately depicted in carbonate reservoir for the wells that are not cored and for which there are no welltest data. Therefore, having a framework for estimation of these parameters in reservoirs with neither coring samples nor welltest data is crucial. Rock properties are characterized by using different well logs. However, there is no specific petrophysical log for estimating rock permeability; thus, new methods need to be developed to predict permeability from well logs. One of the most powerful tools that we applied by the authors is artificial neural network (ANN), whose advantages and disadvantages have been discussed by several authors. In particular, 767 data sets were used from five wells of Bangestan reservoir in a southwestern field of Iran. Depth, Neutron (NPHI), Density (RHOB), Sonic (DT) logs, and evaluated total porosity (PHIT) from log data were used as the input data and horizontal permeability obtained by coring was as target data. Sixty percent of these data points were used for training and the remaining for predicting the permeability (i.e., validation and testing). An appropriate ANN was developed and a correlation coefficient (R) of 0.965 was obtained by comparing permeability predictions and the actual measurements. As a result, the neural science can be used effectively to estimate formation permeability from well log data.     

Development of artificial neural network models for predicting water saturation and fluid distribution

We have developed artificial neural network (ANN) models to predict water saturation from log data. Two Middle Eastern sandstone reservoirs were investigated. In the first case, an ANN model was tested on the Haradh formation in Oman using wireline logs and core Dean–Stark data. In the second case, the ANN was used to model the saturation–height function in a complex sandstone reservoir.In the first case study, the model is based on a three-layered neural network structure. The model was successfully tested yielding a prediction of water saturation with a root mean square error (RMSE) of around 0.025 (fraction of pore volume P.V.) and a correlation factor of 0.91 to the test data. Furthermore, the ANN model was shown to be superior to conventional statistical methods such as multiple linear regression, which gave a correlation factor of 0.41.In the second case, the model yielded a saturation–height function with an RMSE of 0.079 (fraction P.V.) in saturation when using core porosity and height above free water level. This is a considerable improvement over conventional methods. The error was also greatly reduced when permeability and a lithology indicator were introduced. A minimum error of 0.045 (fraction P.V.) was obtained when using core data such as height, porosity, permeability, lithology and a functional link. We then used gamma ray, neutron, density, resistivity wireline data and the cation exchange capacity as inputs. Our best case which gave an RMSE error of 0.046 (fraction P.V.) was obtained. The ANN was then used to predict the hydrocarbon saturation in the Gharif formation and good results were obtained. The neural network model proved the robustness of saturation prediction in another field for the same formation.     

NEURAL NETWORK PREDICTION OF PERMEABILITY IN THE EL GARIA FORMATION, ASHTART OILFIELD, OFFSHORE TUNISIA

The Lower Eocene El Garia Formation forms the reservoir rock at the Ashtart oilfield, offshore Tunisia. It comprises a thick package of mainly nummulitic packstones and grainstones with variable reservoir quality. Although porosity is moderate to high, permeability is often poor to fair with some high permeability streaks. The aim of this study was to establish relationships between log‐derived data and core data, and to apply these relationships in a predictive sense to uncored intervals. An initial objective was to predict from measured logs and core data the limestone depositional texture (as indicated by the Dunham classification), as well as porosity and permeability. A total of nine wells with complete logging suites, multiple cored intervals with core plug measurements together with detailed core interpretations were available. We used a fully‐connected Multi‐Layer‐Perceptron network (a type of neural network) to establish possible non‐linear relationships. Detailed analyses revealed that no relationship exists between log response and limestone texture (Dunham class). The initial idea to predict Dunham class, and subsequently to use the classification results to predict permeability, could not therefore be pursued. However, further analyses revealed that it was feasible to predict permeability without using the depositional fabric, but using a combination of wireline logs and measured core porosity. Careful preparation of the training set for the neural network proved to be very important. Early experiments showed that low to fair permeability (1–35 mD) could be predicted with confidence, but that the network failed to predict the high permeability streaks. “Balancing ” the data set solved this problem. Balancing is a technique in which the training set is increased by adding more examples to the under‐sampled part of the data space. Examples are created by random selection from the training set and white noise is added. After balancing, the neural network's performance improved significantly. Testing the neural network on two wells indicated that this method is capable of predicting the entire range of permeability with confidence.     

Flow Zone Indicator Estimation Based on Petrophysical Studies Using an Artificial Neural Network in a Southern Iran Reservoir

Porosity is a volumetric parameter whereas permeability is a measure of a rock's flow properties and depends on pore distribution and connectivity. Thus zonation of a reservoir using flow zone indicator (FZI) can be used to evaluate reservoir quality based on porosity-permeability relationships. The objective of this study was to develop an accurate reservoir FZI with the aid of artificial neural network (ANN) utilizing available geophysical well log data and dipole sonic imager (DSI) derived body wave velocities. The efficiency of utilizing shear wave and compressional wave velocities (V_p and V_s ) in improving estimation accuracy has been evaluated as well. It is the core data were used for ANN training that involves the calculations of Reservoir Quality Index, normalized porosity (? _z ), and FZI. Correlation between FZI calculated from core data and that obtained from well log data showed that ANN model were successful for estimation of FZI from conventional well log data. The compressional wave velocity was more effective than shear ones in delivering more accurate responses to estimate FZI. On the other hand, in association with other logs, utilizing compressional and shear wave velocities caused the responses to be closer to the reality and decrease the estimation error.     

Estimation of Petroleum Reservoir Parameters Using an Integrated Approach Neural Network,Principal Component Analysis and Fisher Discriminant Analysis

A new predictive methodology is introduced, based on a combined principal component analysis (PCA), Fisher discriminant analysis (FDA), and artificial neural network (ANN) methodologies for parameters estimation of a petroleum reservoir. Prediction of continuous petrophysical parameters is often time consuming and complicated because of geological variability such as facies changes due to sedimentary and structural changes. The petrophysical parameters, however, are usually difficult to measure due to reliability considerations, limitations insights on cost, inappropriate instrument maintenance, and sensor failures, evaluated by crude diagrams of reservoir parameters valuably. PCA and FDA provides an optimal lower dimensional representation in terms of discriminating among classes of data and are developed utilizing the reservoir historical data to incorporate reliability and prediction capabilities of ANN. The developed soft sensors are applied to predict the parameters of Marun reservoir located in Ahwaz, Iran, by utilizing the available geophysical well log data. The resulting outcomes demonstrate the promising capabilities of the proposed hybrid PCA-FDA-NN methodology than the conventional back-propagation NN, FDA, and PCA algorithms.     

Body Wave Velocities Estimation From Wireline Log Data Utilizing an Artificial Neural Network for a Carbonate Reservoir,South Iran

Reservoir characterization is a prerequisite study for oil and gas field development. Body wave velocities are important parameters for reservoir characterization studies. In this research, a back-propagation artificial neural network (BP-ANN) including the Levenberg-Marquardt training algorithm was used as an intelligent tool to estimate compressional and shear wave velocities. The efficiency of utilizing density log and photoelectric effect (PEF) in improving estimation accuracy have been evaluated as well. The petrophysical data from three wells were used for constructing intelligent models in the South Pars field, Southern Iran. The fourth and fifth wells from the field were used to evaluate the reliability of the model. The results showed that a BP-ANN was successful in estimating body wave velocities and so when just gamma ray, neutron, deep resistivity (lateral log deep) were used as net work inputs, the net exactness ware comparatively low but using PEF effects increased this exactness. By using density log the net exactness noticeably grew and in this manner using both PEF and density log beside other mentioned logs as inputs approached to more real results.     

基于WT与LSSVM的储层流动单元划分方法

某研究区储层特性较为复杂,为了依据测井数据准确求取储层参数,提出基于小波变换(WT)与最小二乘支持向量机(LSSVM)相结合的储层流动单元划分方法。选取21口关键井的岩心物性资料、测井资料,依据流动层带指数划分方法将取心井储层流动单元划分成Ⅰ、Ⅱ、Ⅲ类,建立流动单元的识别规则和划分标准。将WT与LSSVM相结合对取心井储层流动单元进行学习训练,使用WT对各测井曲线分别分解为高频和低频成分,利用C5.0决策树对不同频率成分的训练样本进行参数敏感性分析得到学习所用的训练样本集,利用LSSVM训练训练样本建立流动单元预测识别模型,使用该模型对取心或非取心段储层流动单元进行预测。实验表明,基于WT与LSSVM的储层流动单元划分模型具有较高的识别精度,为储层精细评价提供一种较有效的研究方法。     

PERMEABILITY PREDICTION FROM WELL LOGS USING AN IMPROVED WINDOWING TECHNIQUE

Permeability prediction from well logs is of great importance in reservoir characterization and engineering. In this paper, a new method is proposed to correlate conventional well logs and core permeability data. It uses an improved "windowing" technique to incorporate adjacent core data to the permeability predictor in such a way that the scales of the well log and core measurements are matched. It also has the capability to evaluate the reliability of each and every prediction. The method is implemented by the use of a neural network and is demonstrated by means of a case study. The study uses a set of well logs and limited core permeability data to produce continuous permeability profiles. The results show that the permeability profiles are consistent with the core permeability and the geological sequence of the reservoir. The reliability indicator is particularly useful for examining reservoir heterogeneity and sampling.     

三肇凹陷低渗透扶杨油层流动单元划分

为了指导油田完善注采系统和加密调整,实现精细化开发提高采出率,开展了低渗透扶杨油层流动单元研究.以精细地质研究为基础,根据渗流地质参数储层渗透率、地层系数和有效厚度与生产动态测试油井产液强度和产液量的相互关系,优选地层系数为流动单元划分参数,在沉积相控约束下,应用地层系数累计概率分布拐点截断法将扶杨油层流动单元划分为好...     

基于红外光谱-神经网络预测汽油辛烷值

根据汽油组分辛烷值与红外光谱峰面积分析数据,用人工神经网络（ANN）的反向传播（BP）算法建立了汽油组分辛烷值神经网络预测模型,检验表明,ANN方法能准确地关联红外光谱分析数据与汽油组分辛烷值的关系。马达法辛烷值与研究法辛烷值预测平均误差分别为0．192,0．178。     

砂砾岩储层孔隙度和渗透率预测方法

垦西地区沙四段砂砾岩体岩块含量高,矿物多变,孔隙结构复杂,导致测井响应差异大,用传统的统计回归方法和测井解释方法计算储层孔隙度和渗透率精度很低.用基于测井相分析的参数回归法、多矿物模型测井最优化方法和BP神经网络法等方法分别计算砂砾岩孔隙度和渗透率,其目的是提高复杂岩性储层参数的解释精度,满足油藏描述和储量计算对参数精度的要求.通过与岩心分析结果对比,基于测井相分析的参数回归法较一般解释方法的解释精度高,而多矿物模型测井最优化法和BP神经网络法等非参数数学建模方法比前者的效果更好.该方法提高了现有测井信息的利用率,在垦西地区砂砾岩体应用中取得了良好的效果.     

A FUZZY LOGIC APPROACH TO ESTIMATING HYDRAULIC FLOW UNITS FROM WELL LOG DATA: A CASE STUDY FROM THE AHWAZ OILFIELD, SOUTH IRAN

Porosity-permeability relationships in the framework of hydraulic flow units can be used to characterize heterogeneous reservoir rocks. Porosity is a volumetric parameter whereas permeability is a measure of a rock's flow properties and depends on pore distribution and connectivity. Thus zonation of a reservoir using flow zone indicators and the identification of flow units can be used to evaluate reservoir quality based on porosity-permeability relationships.
In the present study, we attempt to make a quantitative correlation between flow units and well log responses using fuzzy logic in the mixed carbonate-clastic Asmari Formation at the Ahwaz oilfield, South Iran. A hybrid neuro-fuzzy approach was used to verify the results of fuzzy modelling. For this purpose, well log and core data from three wells at Ahwaz were used to make an intelligent formulation between core-derived flow units and well log responses. Data from a separate well was used for evaluation and validation of the results.
The results of this study demonstrate that there is a good agreement between core-derived and fuzzy-logic derived flow units. Fuzzy logic was successful in modelling flow units from well logs at well locations for which no core data was available.     

双孔结构储层油气产能的测井预测方法

介绍了一种基于测井资料预测双孔结构碳酸盐岩储层油气产能的新方法。根据碳酸盐岩剖面中的双孔结构储层的地质和测井特征,提取与储层产能密切相关的多个测井和地质参数,考虑这些参数与产能的非线性相关关系以及产能数据的变化特点,采用BP神经网络技术建立其储层产能的预测模型。处理了轮南油田的多口井测井资料,所预测的储层段产能与试油产能较为一致,效果良好,值得推广应用。     

神经网络在示功图类型识别中的应用

示功图是判断油井生产状况的重要依据。神经网络能够反映任意非线性的映射关系,从而可以应用于图形识别。主要讨论了BP神经网络判定示功图类型的实现过程,阐述了BP神经网络的算法结构、示功图特征的提取,并给出了部分算例结果。     

人工神经网络技术在油田储层物性预测中的应用――以西峰油田为例

与传统的测井资料解释和信息处理技术相比较,在对非均质性较强、物性参数级差较大的储集层物性预测中,人工神经网络技术具有极强的自适应和自学习能力,其通过很强的非线性映射,能够精确地建立储集层参数与测井响应之间的非线性模型。在论述神经网络技术基本原理的基础上,对西峰油田延安组和延长组储层的物性参数(孔隙度和渗透率等)进行了预测,取得了较理想的结果。预测结果表明:渗透率参数级差不大(<102)时,预测精度高;渗透率的变化范围较大(>103)时,对具有高渗透率储层的预测精度高,而对具有低渗透率储层的预测值相对误差较大。