Artificial Neural Networks applied to estimate permeability, porosity and intrinsic attenuation using seismic attributes and well-log data

Iturrarán-Viveros, Ursula; Parra, Jorge O.

doi:10.1016/j.jappgeo.2014.05.010

Cited by 98 publications

(20 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Genetic algorithm represents parameters as an encoded binary string and works with the binary strings to minimize the cost, while the other works with the continuous parameters themselves to minimize the cost [13]. Genetic algorithms have had a great measure of success in search and optimization problems.…”

Section: The Principal Methodologymentioning

confidence: 99%

“…This continuous genetic algorithm also has the advantage of requiring less storage than the binary genetic algorithm because a single number represents the variable instead of Nbits. The continuous genetic algorithm is inherently faster than the binary genetic algorithm, because the chromosomes do not have to be decoded prior to the evaluation of the cost function [13].…”

Section: The Principal Methodologymentioning

confidence: 99%

“…the function depicts the closeness of a given solution to the desired result. we have to minimize the average some square error between the measured porosity from well log and the output of genetic algorithm [13]. selection: it is important operator in genetic algorithm and represent the stage of a genetic algorithm in which individual genomes are chosen from a population for later breeding (using the crossover operator).in this study used three types of selection roulette wheel selection, tournament selection and random selection [18].…”

Section: Genetic Algorithm Proceduresmentioning

confidence: 99%

See 2 more Smart Citations

Novel Multi-Gen Multi Parameter Genetic Algorithm Representation for Attributes Selection and Porosity Prediction

Saleh¹,

Tuama²

2016

IJCA

View full text Add to dashboard Cite

Many applications require a careful selection of attributes or features from a much larger set of data. This attributes selection problem need to optimized. In order to tackle this problem this paper proposes a binary-real code multi-gen multi-parameter genetic algorithm for attributes selection from large seismic data and prediction of effective porosity. Genetic Algorithm (GA) uses three selection methods for this purpose, mean square error and correlation coefficient are two witness criteria to choose the best subset of attributes that minimize the error and give high prediction of porosity.

show abstract

Section: The Principal Methodologymentioning

confidence: 99%

Section: The Principal Methodologymentioning

confidence: 99%

Section: Genetic Algorithm Proceduresmentioning

confidence: 99%

See 1 more Smart Citation

Novel Multi-Gen Multi Parameter Genetic Algorithm Representation for Attributes Selection and Porosity Prediction

Saleh¹,

Tuama²

2016

IJCA

View full text Add to dashboard Cite

show abstract

“…Artificial neural networks (ANNs), which follow an empirical risk minimization of the training errors, are common form of learning machines that have been already considered. Different architectures of ANNs have been applied successfully for the prediction of lithofacies [ Chen and Rubin , ; Dubois et al ., ] or hydraulic properties in petroleum reservoirs [ Mohaghegh et al ., ; Wong et al ., ; Lee and Datta‐Gupta , ; Shokir et al ., ; Al‐Anazi et al ., ; Elshafei and Hamada , ; Kharrat et al ., ; Iturrarán‐Viveros and Parra , ] from cross hole or borehole geophysics data. However, despite their potential effectiveness, ANNs present some important drawbacks [ Camps‐Valls et al ., ]: (i) design and training often results in a complex, time‐consuming task, in which many parameters must be tuned; (ii) minimization of the training errors can lead to poor generalization performance; and (iii) performance can be degraded when working with small (sparse) data sets.…”

Section: Introductionmentioning

confidence: 99%

Predicting hydrofacies and hydraulic conductivity from direct-push data using a data-driven relevance vector machine approach: Motivations, algorithms, and application

et al. 2015

View full text Add to dashboard Cite

The spatial heterogeneity of hydraulic conductivity (K) exerts a major control on groundwater flow and solute transport. The heterogeneous spatial distribution of K can be imaged using indirect geophysical data as long as reliable relations exist to link geophysical data to K. This paper presents a nonparametric learning machine approach to predict aquifer K from cone penetrometer tests (CPT) coupled with a soil moisture and resistivity probe (SMR) using relevance vector machines (RVMs). The learning machine approach is demonstrated with an application to a heterogeneous unconsolidated littoral aquifer in a 12 km 2 subwatershed, where relations between K and multiparameters CPT/SMR soundings appear complex. Our approach involved fuzzy clustering to define hydrofacies (HF) on the basis of CPT/SMR and K data prior to the training of RVMs for HFs recognition and K prediction on the basis of CPT/SMR data alone. The learning machine was built from a colocated training data set representative of the study area that includes K data from slug tests and CPT/SMR data up-scaled at a common vertical resolution of 15 cm with K data. After training, the predictive capabilities of the learning machine were assessed through cross validation with data withheld from the training data set and with K data from flowmeter tests not used during the training process. Results show that HF and K predictions from the learning machine are consistent with hydraulic tests. The combined use of CPT/SMR data and RVM-based learning machine proved to be powerful and efficient for the characterization of high-resolution K heterogeneity for unconsolidated aquifers.

show abstract

“…To predict Q −1 logs in the old wells, we used artificial neural networks (see Iturrarán-Viveros and Parra, 2014) and rock physical models to verify the attenuation anomalies. We used the Gamma test (Jones, 2004), a mathematically nonparametric and nonlinear smooth modeling tool, to estimate Q −1 by selecting the best combination of well logs (well 3) as inputs for the artificial NN.…”

Section: Introductionmentioning

confidence: 99%

Attenuation and velocity estimation using rock physics and neural network methods for calibrating reflection seismograms

Parra

Iturrarán-Viveros

Parra³

et al. 2015

Interpretation

Self Cite

View full text Add to dashboard Cite

Velocity logs are the most important data used to evaluate rock, fluid, and geotechnical properties of hydrocarbon reservoirs. As a complementary physical property, P-wave attenuation (Q −1 ) can be used as an indicator of lithology and fluid saturation in oil and gas reservoir characterization. We implemented an inversion selfconsistent rock physical model to predict P-and S-wave velocities in two old wells near a new well containing a complete suite of logs at the Waggoner Ranch oil reservoir in northeast Texas. We selected a training data set from the new well to test the algorithm that was subsequently applied to predict velocity data in the two old wells. We used an attenuation log from the new well to perform data analysis via the Gamma test, a mathematically nonparametric nonlinear smooth modeling tool, to choose the best input combination of well logs to train an artificial neural network (NN) for estimating Q −1 . Then, the NN was applied to predict attenuation logs in the old wells. The Q −1 logs detected oil-saturated sand that was modeled with a rock physical model. This is a significant result that revealed for the first time that oil, gas, and water saturations of sand can be quantified from an attenuation anomaly estimated from full-waveform sonic data. In addition, water, oil, and gas saturations of the sand were determined from Q −1 anomalies observed in the old wells. This confirms the productivity of the Upper Milham oil-saturated sand intercepted by the three wells. The velocity, density, and Q −1 logs were used to generate synthetic seismograms to calibrate seismic data to verify and evaluate the work flow for predicting velocity and attenuation logs in older wells. This demonstrated that attenuation logs can discriminate between anomalies due to lithology and those due to oil and gas saturation. IntroductionThe characterization of oil and gas fields relies on knowledge of the distribution of rock-physics properties of the reservoir based on well log data. P-and S-wave velocities are the most important data used to evaluate reservoir rock and fluid properties, as well as geotechnical rock properties. Similarly, P-wave attenuation (Q −1 ) can be used as an indicator of lithology; pore structure; clay, sand, and fluid content; and hydrocarbon saturation. For most old wells, P-and S-wave velocity logs and attenuation data are missing. When new wells are drilled at such sites, service companies provide complete suites of logs to small oil and gas producers. The producers can then integrate new data with existing data to better delineate the reservoir and to estimate new reserves. To facilitate data integration, several investigators have developed regression analysis methods to predict P-and S-wave data at the vicinities of new wells where the complete suite of logs is available (Augusto and Martins, 2010). These authors extend

show abstract

Artificial Neural Networks applied to estimate permeability, porosity and intrinsic attenuation using seismic attributes and well-log data

Cited by 98 publications

References 25 publications

Novel Multi-Gen Multi Parameter Genetic Algorithm Representation for Attributes Selection and Porosity Prediction

Novel Multi-Gen Multi Parameter Genetic Algorithm Representation for Attributes Selection and Porosity Prediction

Predicting hydrofacies and hydraulic conductivity from direct-push data using a data-driven relevance vector machine approach: Motivations, algorithms, and application

Attenuation and velocity estimation using rock physics and neural network methods for calibrating reflection seismograms

Contact Info

Product

Resources

About