PAPER

SEG Technical Program Expanded Abstracts 2016, 2016

This paper presents the subsurface characterization by applying integrated three dimensional seismic attributes analysis on a 3D seismic dataset from OPO field, within the western Niger Delta basin. The volume attributes aimed at extracting features associated with hydrocarbon presence detection, net pay evaluation and porosity estimation for optima reservoir characterization. Neural network (NN) derived chimney properties prediction attribute was used to evaluate the integrity of the delineated structural traps. Common contour binning was employed for hydrocarbon prospect evaluation, while the Seismic coloured inversion was also applied for net pay evaluation. Amplitude anomalies were used to delineate bright spots and flat spots; good reservoirs in term of their porosity models, and fluid content and contacts (GOC & OWC) were identified in the area through common contour binning, seismic colour inversion and supervised NN classification.

SEG Technical Program Expanded Abstracts 1999, 1999

A new method was developed to use core, well log, and post-stack seismic data to identify reservoir lithologies between wells. The method was based on a combination of rock physics modeling, seismic attribute generation and pattern recognition via neural network analysis. The result was a new lithologically calibrated attribute that showed the producing wells to be inside the indicated oil sand area and the non-producing wells to be outside this area.

Iraqi Journal of Science, 2021

The EMERGE application from Hampsson-Russell suite programs was used in the present study. It is an interesting domain for seismic attributes that predict some of reservoir three dimensional or two dimensional properties, as well as their combination. The objective of this study is to differentiate reservoir/non reservoir units with well data in the Yamama Formation by using seismic tools. P-impedance volume (density x velocity of P-wave) was used in this research to perform a three dimensional seismic model on the oilfield of Nasiriya by using post-stack data of 5 wells. The data (training and application) were utilized in the EMERGE analysis for estimating the reservoir properties of P-wave velocity, in addition to the neural network analysis and deriving relations between them at well locations. P- wave velocity slices of reservoir units (Yb1, Yb2, and Yc) of Yamama Formation were prepared to determine the enhancement trends within these units. From a general economic poi...

Journal of Petroleum Exploration and Production, 2021

In an attempt to reduce the errors and uncertainties associated with predicting reservoir properties for static modeling, seismic inversion was integrated with artificial neural network for improved porosity and water saturation prediction in the undrilled prospective area of the study field, where hydrocarbon presence had been confirmed. Two supervised neural network techniques (MLFN and PNN) were adopted in the feasibility study performed to predict reservoir properties, using P-impedance volumes generated from model-based inversion process as the major secondary constraint parameter. Results of the feasibility study for predicted porosity with PNN gave a better result than MLFN, when correlated with well porosity, with a correlation coefficient of 0.96 and 0.69, respectively. Validation of the prediction revealed a cross-validation correlation of 0.88 and 0.26, respectively, for both techniques, when a random transfer function derived from a given well is applied on other well lo...

2015

Lithofacies identification can provide qualitative information about rocks. It can also explain rock textures which are important components for hydrocarbon reservoir description Sarvak Formation is an important reservoir which is being studied in the Marun oil field, in the Dezful embayment (Zagros basin). This study establishes quantitative relationships between digital well logs data and routine petrographic data, obtained from thin sections description. Attempts were made to predict lithofacies in 13 wells, all drilled in the Marun oil field. Seven well logs, namely, Gamma Ray (SGR and CGR), Deep Resistivity (RD), Formation Density (RHOB), Neutron Porosity (PHIN), Sonic log (DT), and photoelectric factor (PEF) as input data and thin section/core-derived lithofacies were used as target data in the ANN (artificial neural network) to predict lithofacies. The results show a strong correlation between the given data and those obtained from ANN (R²= 95%). The performance of the model has been measured by the Mean Squared Error function which doesn't exceed 0.303. Hence, neural network techniques are recommended for those reservoirs in which facies geometry and distribution are key factors controlling the heterogeneity and distribution of rock properties. Undoubtedly, this approach can reduce uncertainty and save plenty of time and cost for the oil industry.

Geologia Croatica, 2009

The Kloštar oil fi eld is situated in the northern part of the Sava Depression within the Croatian part of the Pannonian Basin. The major petroleum reserves are confi ned to Miocene sandstones that comprise two production units: the Lower Pontian I sandstone series and the Upper Pannonian II sandstone series. We used well logs from two wells through these sandstones as input data in the neural network analysis, and used spontaneous potential and resistivity logs (R 16 and R 64) as the input in network training. The fi rst analysis included prediction of lithology, which was defi ned as either sandstone or marl. These two rock types were assigned categorical values of 1 or 0 which were then used in numerical analysis. The neural network was also used to predict hydrocarbon saturation in selected wells. The input dataset was extended to depth and categorical lithology. The prediction results were excellent, because the training and prediction dataset showed little disagreement between the true and predicted values. At present, this study represents the best and most useful application of neural networks in the Croatian part of the Pannonian Basin.

this paper, presents the results of applying to two of four main reservoir parameters, i.e., Sand

Central European Geology

Lithofacies definition in the subsurface is an important factor in modeling, regardless of the scale being at reservoir or basin level. In areas with low exploration level, modeling of lithofacies distribution presents a complicated task as very few inputs are available. For this purpose, a case study in the Požega Valley was selected with only one existing well and several seismic sections within an area covering roughly 850 km 2. For the task of expanding the input data set for lithofacies modeling, neural network analysis was performed that incorporated interpreted lithofacies (sandstone, siltite, marl, and breccia-conglomerate) in a single well and attribute data gathered from a seismic section. Three types of different neural networks were used for the analysis: multilayer perceptron, radial-basis function, and probabilistic neural network. As a result, three lithofacies models were built alongside a seismic section based upon predictions acquired from the neural networks. Three lithofacies were successfully predicted on the section while the breccia-conglomerate was either missing or underpredicted and mostly positioned in a geologically invalid interval. Results obtained by single networks differed from one another, which indicated that a result from a single network should not be treated as representative; thus, the facies distribution for modeling should be acquired from either an ensemble of neural networks or several neural networks. Analysis showed the initial potential of the usability of neural networks and seismic attribute analysis on vintage seismic sections with possible drawbacks of the applications being pointed out.

Heliyon, 2019

A computerized advanced statistical analysis which involves the characterization of reservoir elements involving mapping of lithofacies and pore fluids through crossplots of basic seismic variables in both bi-variate and trivariate domains and functional transformations including rotation of axes have been used as discriminant tools over "AIB-EX" Oil Field, Niger Delta. The methodology encompasses reconstruction of geologic lithofacies information from geophysical logs. Reservoir characterization, rock physics analysis and log inversion were carried out using IHS Kingdom Advanced and Origin software. Three reservoir zones namely A, B, and C were analyzed. The obtained results characterized the reservoir elements as: shale, sandy-shale, shaly-sand and sand (with respective GR counts and P-wave velocity of 105-125 API and 2400-3600 m/s, 75-105 API and 2100-5000 m/s, 45-75 API and 2200-4750 m/s, and 10-45 API and 2000-4600 m/s) which represents seismic scale sedimentary units called lithofacies. Also, the results of both the bi-variate crossplots (GR and P-wave velocity) and tri-variate crossplots (GR, P-wave velocity, and resistivity) have not only differentiated the different lithology but have discriminated the saturating fluid (water or hydrocarbon). The pore fluids were further characterized as either brine or oil based on powerful discriminant tools such as plots of acoustic impedance versus porosity and elastic impedance versus porosity. Conclusively, the result of the research confirmed that hydrocarbon reservoirs can be discriminated with varying degree of effectiveness in various domains using the adopted approach. The obtained result, which can also be used to calibrate seismic inversion, yielded a reliable seismic lithofacies map in the presence of high resolution 3-D seismic data.

geopersia, 2015

Lithofacies identification can provide qualitative information about rocks. It can also explain rock textures which are importantcomponents for hydrocarbon reservoir description Sarvak Formation is an important reservoir which is being studied in the Marun oilfield, in the Dezful embayment (Zagros basin). This study establishes quantitative relationships between digital well logs data androutine petrographic data, obtained from thin sections description. Attempts were made to predict lithofacies in 13 wells, all drilled inthe Marun oil field. Seven well logs, namely, Gamma Ray (SGR and CGR), Deep Resistivity (RD), Formation Density (RHOB),Neutron Porosity (PHIN), Sonic log (DT), and photoelectric factor (PEF) as input data and thin section/core-derived lithofacies wereused as target data in the ANN (artificial neural network) to predict lithofacies. The results show a strong correlation between the givendata and those obtained from ANN (R²= 95%). The performance of the model has bee...