Lithofacies Classification Using the Multilayer Perceptron and the Self-organizing Neural Networks

Ouadfeul, Sid‐Ali; Aliouane, Leila

doi:10.1007/978-3-642-34500-5_87

Cited by 16 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thresholding is a technique used for signal and image denoising [4]. The discrete wavelet transform uses two types of filters: (1) averaging filters, and (2) detail filters.…”

Section: Discrete Wavelet Transform and Signal Denoisingmentioning

confidence: 99%

See 1 more Smart Citation

Noise Attenuation from GPR Data Using Wavelet Transform and Artificial Neural Network

Ouadfeul¹,

Aliouane²

2014

IJAPM

Self Cite

View full text Add to dashboard Cite

Abstract:In this paper, a tentative of noise attenuation from the 3D Ground Penetrating Radar (GPR) data using the wavelet transform and the Multilayer Perceptron neural network model is implanted. GPR data recorded in Algerian Sahara are filtered firstly using the discrete wavelet transform, after that a MLP machine with three layers is trained in a supervised learning mode, the input is an extracted profile from the raw 3D GPR data and the output consists of the GPR data of the same profile but after filtering. The estimated weights of connection are used to propagate the remaining non-filtered data through the implanted machine, the calculated output consists to the filtered GPR data. Comparison between the filtered data using the MLP machine and the continuous wavelet transform shows that the neural network machine can be used for S/N ratio improvement of the noisy GPR data.

show abstract

“…Thresholding is a technique used for signal and image denoising [4]. The discrete wavelet transform uses two types of filters: (1) averaging filters, and (2) detail filters.…”

Section: Discrete Wavelet Transform and Signal Denoisingmentioning

confidence: 99%

“…Artificial Neural Networks have been widely used in geophysical data processing, it has been used for lithofacies classification form well-logs data [4], and in the prediction of petrophysical parameters like porosity, permeability and water saturation [5].…”

Section: Introductionmentioning

confidence: 99%

Noise Attenuation from GPR Data Using Wavelet Transform and Artificial Neural Network

Ouadfeul¹,

Aliouane²

2014

IJAPM

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, there is a practical need for petrophysicists, when facing massive well log data, to group the wells according to the characteristic of log curves for integrated reservoir studies, such as petrophysical and geological modeling and fluid flow simulations [21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Massive Spatial Well Clustering Based on Conventional Well Log Feature Extraction for Fast Formation Heterogeneity Characterization

Li¹,

Luo

et al. 2022

Lithosphere

View full text Add to dashboard Cite

Recent enhancements in computational capacity provide an opportunity for harnessing the enormous amount of reservoir data already acquired and extracting useful information for hydrocarbon exploration, development, and production. This article reports a three-step clustering technique to determine well groups based on subsurface geological heterogeneity using feature extraction, hierarchical ensemble clustering, and spatial mapping. The first step of the presented methodology is to group the wells into different clusters based on the formation rock composition and property features extracted from well logs using the expectation maximization algorithm. The one-dimensional (1D) stacking pattern of each well log curve is expressed through a two-dimensional (2D) transformation scheme. Thus, the clustering can capture the vertical stacking patterns of well logs, which is essential for reservoir heterogeneity characterization. This base clustering process generated a feature matrix which is further grouped through the hierarchical ensemble clustering in a latent space of well logs in the second step. Through the ensemble clustering, different clustering proposals obtained from the base clustering are integrated corroboratively to reflect a comprehensive feature of all studied logs. In the third step, the spatial clustering is performed based on the ensemble results, considering the spatial distances between well locations in the target area. The results of the 2D spatial map may provide insights into the sedimentary depositional environment in terms of the lateral geological heterogeneity features. Therefore, the proposed clustering technique can present a fast geological modeling method to integrate geological heterogeneity features presented in multiple well logs, which is not yet fully utilized in traditional geomodeling approaches. The results can also support further reservoir studies, such as petrophysical modeling, reservoir modeling, and fluid flow simulation studies.

show abstract

“…The challenge is to choose a reference between these rock types, keeping in mind that raw log data have a restricted resolution and depend on environmental conditions [6], routine core data and core description have a lacking coverage and are sensitive to interpretation [3]. Artificial neural network (ANN) approaches are often employed in reservoir characterization dealing with EF and HFU modeling [7][8][9]. They are powerful tools in reservoir nonlinearity examination [10].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Rock Type Characterization Using Artificial Neural Networks in Hamra Quartzites Reservoir: A Multidisciplinary Approach

Abdallah

Benaïssa

Ouadfeul

et al. 2019

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

A new multidisciplinary workflow is suggested to re-characterize the Hamra Quartzite (QH) formation using artificial neural networks. This approach involves core description, routine core analysis, special core analysis and raw logs of fourteen wells. An efficient electrofacies clustering neural network technology based on a self-organizing map is performed. The inputs in the model computation are: neutron porosity, gamma ray and bulk density logs. According to the self-organizing map results, the reservoir is composed of five electrofacies (EF1 to EF5): EF1, EF2 and EF3 with good reservoir quality, EF4 with moderate quality, and EF5 with bad quality. Hydraulic flow units are determined from well logs and core data using the flow zone indicator (FZI) approach and the multilayer perception (MLP) method. Obtained results indicate eight optimal hydraulic flow units. Hydraulic flow units for un-cored well are determined using the MLP, the used inputs to train the neural system are: neutron porosity, gamma ray, bulk density and predefined electrofacies. A dynamic rock typing is achieved using the FZI approach and combining special core data analysis to better characterize the hydraulic reservoir behavior. A best-fit relationship between water saturation and J-function is established and a good saturation match is obtained between capillary pressure and interpreted log results.

show abstract

Lithofacies Classification Using the Multilayer Perceptron and the Self-organizing Neural Networks

Cited by 16 publications

References 0 publications

Noise Attenuation from GPR Data Using Wavelet Transform and Artificial Neural Network

Noise Attenuation from GPR Data Using Wavelet Transform and Artificial Neural Network

Massive Spatial Well Clustering Based on Conventional Well Log Feature Extraction for Fast Formation Heterogeneity Characterization

Dynamic Rock Type Characterization Using Artificial Neural Networks in Hamra Quartzites Reservoir: A Multidisciplinary Approach

Contact Info

Product

Resources

About