Comparison of linear regression and a probabilistic neural network to predict porosity from 3‐D seismic attributes in Lower Brushy Canyon channeled sandstones, southeast New Mexico

Geophysics ◽  
2001 ◽  
Vol 66 (5) ◽  
pp. 1349-1358 ◽  
Author(s):  
Daniel J. Leiphart ◽  
Bruce S. Hart
Keyword(s):  
Neural Network ◽  
New Mexico ◽  
Linear Regression ◽  
Regression Model ◽  
Seismic Data ◽  
Time Window ◽  
Probabilistic Neural Network ◽  
Seismic Attributes ◽  
Oil Field ◽  
Reservoir Properties

The Lower Brushy Canyon Formation of the Delaware Basin, New Mexico, consists of a series of overlying sand‐filled channels and associated fans separated by laterally extensive organic siltstone and carbonate interbeds. This laterally and vertically complex geology creates the need for precise interwell estimation of reservoir properties. In this paper we integrate wireline log and 3‐D seismic data to directly predict porosity in the area of an existing oil field in southeast New Mexico. The 3‐D seismic data were used to interpret the location of major stratigraphic markers between wells, and these seismic horizons were used to constrain a time window for a volume‐based attribute analysis. Stepwise regression and crossvalidation were used to combine seismic attributes to predict porosity in wells where the porosity was known from the well logs. The results of a linear regression porosity model showed good correlation [Formula: see text] between seven seismic attributes and the observed porosity logs at 11 wells in the study area, but the porosity volume created from the regression model did not display the known geologic features. A probabilistic neural network was then trained to look for a nonlinear relationship between the input data (the seven attributes) and the observed porosity at the 11 wells. The correlation was better [Formula: see text], but the biggest improvement over the linear regression model came in the more geologically realistic predicted porosity distribution.

Applications of Artificial Neural Networks for Seismic Facies Classification

2021 ◽  
Vol 73 (02) ◽  
pp. 68-69
Author(s):  
Chris Carpenter
Keyword(s):  
Neural Network ◽  
Seismic Data ◽  
Reservoir Characterization ◽  
Probabilistic Neural Network ◽  
Oil Field ◽  
Seismic Facies ◽  
Data Set ◽  
Full Field ◽  
Facies Classification

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 200577, “Applications of Artificial Neural Networks for Seismic Facies Classification: A Case Study From the Mid-Cretaceous Reservoir in a Supergiant Oil Field,” by Ali Al-Ali, Karl Stephen, SPE, and Asghar Shams, Heriot-Watt University, prepared for the 2020 SPE Europec featured at the 82nd EAGE Conference and Exhibition, originally scheduled to be held in Amsterdam, 1-3 December. The paper has not been peer reviewed. Facies classification using data from sources such as wells and outcrops cannot capture all reservoir characterization in the interwell region. Therefore, as an alternative approach, seismic facies classification schemes are applied to reduce the uncertainties in the reservoir model. In this study, a machine-learning neural network was introduced to predict the lithology required for building a full-field Earth model for carbonate reservoirs in southern Iraq. The work and the methodology provide a significant improvement in facies classification and reveal the capability of a probabilistic neural network technique. Introduction The use of machine learning in seismic facies classification has increased gradually during the past decade in the interpretation of 3D and 4D seismic volumes and reservoir characterization work flows. The complete paper provides a literature review regarding this topic. Previously, seismic reservoir characterization has revealed the heterogeneity of the Mishrif reservoir and its distribution in terms of the pore system and the structural model. However, the main objective of this work is to classify and predict the heterogeneous facies of the carbonate Mishrif reservoir in a giant oil field using a multilayer feed-forward network (MLFN) and a probabilistic neural network (PNN) in nonlinear facies classification techniques. A related objective was to find any domain-specific causal relationships among input and output variables. These two methods have been applied to classify and predict the presence of different facies in Mishrif reservoir rock types. Case Study Reservoir and Data Set Description. The West Qurna field is a giant, multibillion-barrel oil field in the southern Mesopotamian Basin with multiple carbonate and clastic reservoirs. The overall structure of the field is a north/south trending anticline steep on the western flank and gentle on the eastern flank. Many producing reservoirs developed in this oil field; however, the Mid- Cretaceous Mishrif reservoir is the main producing reservoir. The reservoir consists of thick carbonate strata (roughly 250 m) deposited on a shallow water platform adjacent to more-distal, deeper-water nonreservoir carbonate facies developing into three stratigraphic sequence units in the second order. Mishrif facies are characterized by a porosity greater than 20% and large permeability contrast from grainstones to microporosity (10-1000 md). The first full-field 3D seismic data set was achieved over 500 km2 during 2012 and 2013 in order to plan the development of all field reservoirs. A de-tailed description of the reservoir has been determined from well logs and core and seismic data. This study is mainly based on facies log (22 wells) and high-resolution 3D seismic volume to generate seismic attributes as the input data for the training of the neural network model. The model is used to evaluate lithofacies in wells without core data but with appropriate facies logs. Also, testing was carried out in parallel with the core data to verify the results of facies classification.

Reservoir property prediction using abductive networks

Geophysics ◽  
2010 ◽  
Vol 75 (1) ◽  
pp. P1-P9 ◽  
Author(s):  
Osama A. Ahmed ◽  
Radwan E. Abdel-Aal ◽  
Husam AlMustafa
Keyword(s):  
Statistical Methods ◽  
Seismic Data ◽  
Polynomial Regression ◽  
Seismic Attributes ◽  
Oil Field ◽  
Attribute Selection ◽  
Reservoir Properties ◽  
Seismic Amplitude ◽  
Porosity Logs ◽  
High Degree

Statistical methods, such as linear regression and neural networks, are commonly used to predict reservoir properties from seismic attributes. However, a huge number of attributes can be extracted from seismic data and an efficient method for selecting an attribute subset with the highest correlation to the property being predicted is essential. Most statistical methods, however, lack an optimized approach for this attribute selection. We propose to predict reservoir properties from seismic attributes using abductive networks, which use iterated polynomial regression to derive high-degree polynomial predictors. The abductive networks simultaneously select the most relevant attributes and construct an optimal nonlinear predictor. We applied the approach to predict porosity from seismic data of an area within the 'Uthmaniyah portion of the Ghawar oil field, Saudi Arabia. The data consisted of normal seismic amplitude, acoustic impedance, 16 other seismic attributes, and porosity logs from seven wells located in the study area. Out of 27 attributes, the abductive network selected only the best two to six attributes and produced a more accurate and robust porosity prediction than using the more common neural-network predictors. In addition, the proposed method requires no effort in choosing the attribute subset or tweaking their parameters.

Theory-guided data science-based reservoir prediction of a North Sea oil field

2020 ◽  
Vol 39 (10) ◽  
pp. 742-750
Author(s):  
Jonathan E. Downton ◽  
Olivia Collet ◽  
Daniel P. Hampson ◽  
Tanya Colwell
Keyword(s):  
Neural Network ◽  
North Sea ◽  
Seismic Data ◽  
Data Science ◽  
Oil Field ◽  
Sampled Data ◽  
Reservoir Properties ◽  
Reservoir Prediction ◽  
Data Set ◽  
The Neural Network

Data science-based methods, such as supervised neural networks, provide powerful techniques to predict reservoir properties from seismic and well data without the aid of a theoretical model. In these supervised learning approaches, the seismic-to-rock property relationship is learned from the data. One of the major factors limiting the success of these methods is whether there exists enough labeled data, sampled over the expected geology, to train the neural network adequately. To overcome these issues, this paper explores hybrid theory-guided data science (TGDS)-based methods. In particular, we build a two-component model in which the outputs of the theory-based component are the inputs in the data science component. First, we simulate many pseudowells based on the well statistics in the project area. The reservoir properties, such as porosity, saturation, mineralogy, and thickness, are all varied to create a well-sampled data set. Elastic and synthetic seismic data are then generated using rock physics and seismic theory. The resulting collection of pseudowell logs and synthetic seismic data, called the synthetic catalog, is used to train the neural network. The derived operator is then applied to the real seismic data to predict reservoir properties throughout the seismic volume. This TGDS method is applied to a North Sea data set to characterize a Paleocene oil sand reservoir. The TGDS results better characterize the geology and well control, including a blind well, compared to a solely theory-based approach (deterministic inversion) and a data science-based approach (neural network using only the original wells). These results suggest that theory and data science can complement each other to improve reservoir characterization predictions.

Unsupervised machine learning using 3D seismic data applied to reservoir evaluation and rock type identification

2021 ◽  
pp. 1-69
Author(s):  
Marwa Hussein ◽  
Robert R. Stewart ◽  
Deborah Sacrey ◽  
Jonny Wu ◽  
Rajas Athale
Keyword(s):  
Machine Learning ◽  
Seismic Data ◽  
Rock Type ◽  
Seismic Attributes ◽  
Reservoir Quality ◽  
3D Seismic ◽  
Reservoir Properties ◽  
Unsupervised Machine Learning ◽  
Amplitude Data ◽  
3D Seismic Data

Net reservoir discrimination and rock type identification play vital roles in determining reservoir quality, distribution, and identification of stratigraphic baffles for optimizing drilling plans and economic petroleum recovery. Although it is challenging to discriminate small changes in reservoir properties or identify thin stratigraphic barriers below seismic resolution from conventional seismic amplitude data, we have found that seismic attributes aid in defining the reservoir architecture, properties, and stratigraphic baffles. However, analyzing numerous individual attributes is a time-consuming process and may have limitations for revealing small petrophysical changes within a reservoir. Using the Maui 3D seismic data acquired in offshore Taranaki Basin, New Zealand, we generate typical instantaneous and spectral decomposition seismic attributes that are sensitive to lithologic variations and changes in reservoir properties. Using the most common petrophysical and rock typing classification methods, the rock quality and heterogeneity of the C1 Sand reservoir are studied for four wells located within the 3D seismic volume. We find that integrating the geologic content of a combination of eight spectral instantaneous attribute volumes using an unsupervised machine-learning algorithm (self-organizing maps [SOMs]) results in a classification volume that can highlight reservoir distribution and identify stratigraphic baffles by correlating the SOM clusters with discrete net reservoir and flow-unit logs. We find that SOM classification of natural clusters of multiattribute samples in the attribute space is sensitive to subtle changes within the reservoir’s petrophysical properties. We find that SOM clusters appear to be more sensitive to porosity variations compared with lithologic changes within the reservoir. Thus, this method helps us to understand reservoir quality and heterogeneity in addition to illuminating thin reservoirs and stratigraphic baffles.

Case study: Seismic resolution and reservoir characterization of thin sands using multiattribute analysis and bandwidth extension in the Daqing field, China

2020 ◽  
Vol 8 (1) ◽  
pp. T89-T102
Author(s):  
David Mora ◽  
John Castagna ◽  
Ramses Meza ◽  
Shumin Chen ◽  
Renqi Jiang
Keyword(s):  
Seismic Data ◽  
Reservoir Characterization ◽  
Statistical Significance ◽  
Physical Property ◽  
Seismic Attributes ◽  
Oil Field ◽  
Thin Layers ◽  
Inversion Method ◽  
Bandwidth Extension ◽  
Multiattribute Analysis

The Daqing field, located in the Songliao Basin in northeastern China, is the largest oil field in China. Most production in the Daqing field comes from seismically thin sand bodies with thicknesses between 1 and 15 m. Thus, it is not usually possible to resolve Daqing reservoirs using only conventional seismic data. We have evaluated the effectiveness of seismic multiattribute analysis of bandwidth extended data in resolving and making inferences about these thin layers. Multiattribute analysis uses statistical methods or neural networks to find relationships between well data and seismic attributes to predict some physical property of the earth. This multiattribute analysis was applied separately to conventional seismic data and seismic data that were spectrally broadened using sparse-layer inversion because this inversion method usually increases the vertical resolution of the seismic. Porosity volumes were generated using target porosity logs and conventional seismic attributes, and isofrequency volumes were obtained by spectral decomposition. The resulting resolution, statistical significance, and accuracy in the determination of layer properties were higher for the predictions made using the spectrally broadened volume.

Application of a convolutional neural network in permeability prediction: A case study in the Jacksonburg-Stringtown oil field, West Virginia, USA

Geophysics ◽  
2019 ◽  
Vol 84 (6) ◽  
pp. B363-B373 ◽  
Author(s):  
Zhi Zhong ◽  
Timothy R. Carr ◽  
Xinming Wu ◽  
Guochang Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Regression Model ◽  
Bulk Density ◽  
Carbon Storage ◽  
Oil Field ◽  
Well Logs ◽  
Storage Site ◽  
Core Samples ◽  
Permeability Prediction

Permeability is a critical parameter for understanding subsurface fluid flow behavior, managing reservoirs, enhancing hydrocarbon recovery, and sequestering carbon dioxide. In general, permeability is measured in the laboratory based on subsurface core samples, calculated from well logs or estimated from well tests. However, laboratory measurements and well tests are expensive, time-consuming, and usually limited to a few core samples or wells in a hydrocarbon field or carbon storage site. Machine-learning techniques are good options for generating a rapid, robust, and cost-effective permeability prediction model because of their strengths to recognize the potential interrelationships between input and output variables. Convolutional neural networks (CNN), as a good pattern recognition algorithm, are widely used in image processing, natural language processing, and speech recognition, but are rarely used with regression problems and even less often in reservoir characterization. We have developed a CNN regression model to estimate the permeability in the Jacksonburg-Stringtown oil field, West Virginia, which is a potential carbon storage site and enhanced oil recovery operations field. We also evaluate the concept of the geologic feature image, which is converted from geophysical well logs. Five variables, including two commonly available conventional well logs (the gamma rays [GRs] and bulk density) and three well-log-derived variables (the slopes of the GR and bulk density curves, and shale content), are used to generate a geologic feature image. The CNN treats the geologic feature image as the input and the permeability as the desired output. In addition, the permeability predicted using traditional backpropagation artificial neural networks, which are optimized by genetic algorithms and particle swarm optimization, is compared with the permeability estimated using our CNN. Our results indicate that the CNN regression model provides more accurate permeability predictions than the traditional neural network.

scholarly journals Porosity Prediction Using Neural Network Based on Seismic Inversion and Seismic Attributes

2019 ◽  
Vol 125 ◽  
pp. 15006
Author(s):  
Taufik Mawardi Sinaga ◽  
M. Syamsu Rosid ◽  
M. Wahdanadi Haidar
Keyword(s):  
Neural Network ◽  
Probabilistic Neural Network ◽  
Average Frequency ◽  
Seismic Attributes ◽  
Seismic Inversion ◽  
Carbonate Reservoir ◽  
Neural Network Method ◽  
Time Migration ◽  
The Neural Network ◽  
Network Method

It has done a study of porosity prediction by using neural network. The study uses 2D seismic data post-stack time migration (PSTM) and 2 well data at field “T”. The objective is determining distribution of porosity. Porosity in carbonate reservoir is actually heterogeneous, complex and random. To face the complexity the neural network method has been implemented. The neural network algorithm uses probabilistic neural network based on best seismic attributes. It has been selected by using multi-attribute method with has high correlation. The best attributes which have been selected are amplitude envelope, average frequency, amplitude weighted phase, integrated absolute amplitude, acoustic impedance, and dominant frequency. The attribute is used as input to probabilistic neural network method process. The result porosity prediction based on probabilistic neural network use non-linear equation obtained high correlation coefficient 0.86 and approach actual log. The result has a better correlation than using multi-attribute method with correlation 0.58. The value of distribution porosity is 0.05–0.3 and it indicates the heterogeneous porosity distribution generally from the bottom to up are decreasing value.

scholarly journals Predicting the COVID-19 positive cases in India with concern to Lockdown by using Mathematical and Machine Learning based Models

2020 ◽  
Author(s):  
Ajit Kumar Pasayat ◽  
Satya Narayan Pati ◽  
Aashirbad Maharana
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Regression Model ◽  
Growth Model ◽  
Linear Regression Model ◽  
Exponential Growth ◽  
Time Window ◽  
Epidemic Curve ◽  
First Case ◽  
Exponential Growth Model

In this study, we analyze the number of infected positive cases of COVID-19 outbreak with concern to lockdown in India in the time window of February 11th 2020 to Jun 30th 2020. The first case in India was reported in Kerala on January 30th 2020. To break the chain of spreading, Government announced a nationwide lockdown on March 24th 2020, which is increased two times. The Ongoing lockdown 3.0 is over on May 18th, 2020. We derived how the lockdown relaxation is going to impact on containment of the outbreak. Here the Exponential Growth Model has been used to derive the epidemic curve based on the data collected from February 11th 2020, to May 11th 2020, and the Machine Learning based Linear Regression model that gives the epidemic curve to predict the cases with the continuous flow of the lockdown. We estimate that if the lockdown is continuing with more relaxation, then the estimated infected cases reach up to 1.16 crores by June 30th 2020, and the lockdown would persist with current restriction, then the expected predicted infected cases are 5.69 lacs. The Exponential Growth Model and the Linear Regression Model are advantageous to predict the number of affected cases of COVID-19. These models can be used for forecasting in long term intervals. It shows from our result that lockdown with certain restriction has a vital role in preventing the spreading of this epidemic in this current situation.

Sign in / Sign up

Export Citation Format

Share Document