A multiple-input deep residual convolutional neural network for reservoir permeability prediction

Masroor, Maryam; Niri, Mohammad Emami; Sharifinasab, Mohammad Hassan

doi:10.1016/j.geoen.2023.211420

Cited by 30 publications

(9 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, using GMDH to predict the formation permeability from well log data, trying to estimate the nuclear magnetic resonance-derived permeability from conventional well logs by hiring GMDH. Masroor et al showed a decrease in the computation time by 70% for permeability prediction from well log data when a combination of the modified Levenberg–Marquardt technique and GMDH was applied . Mahdaviara et al estimated the permeability of some heterogeneous carbonate reservoirs with respect to the porosity, irreducible water saturation, and pore-specific surface area by applying GMDH and GEP algorithms .…”

Section: Introductionmentioning

confidence: 99%

Modeling Permeability Using Advanced White-Box Machine Learning Technique: Application to a Heterogeneous Carbonate Reservoir

Zhao,

Guo,

Mohammadian

et al. 2023

ACS Omega

View full text Add to dashboard Cite

From exploration to production, the permeability of reservoir rocks is essential for various stages of all types of hydrocarbon field development. In the absence of costly reservoir rock samples, having a reliable correlation to predict rock permeability in the zone(s) of interest is crucial. To predict permeability conventionally, petrophysical rock typing is done. This method divides the reservoir into zones of similar petrophysical properties, and the permeability correlation for each zone is independently developed. The challenge of this approach is that the success depends upon the reservoir's complexity and heterogeneity and the methods and parameters used for rock typing. As a result, in the case of heterogeneous reservoirs, conventional rock typing methods and indices fail to predict the permeability accurately. The target area is a heterogeneous carbonate reservoir in southwestern Iran with a permeability range of 0.1−127.0 md. In this work, two approaches were used. First, based on permeability, porosity, the radius of pore throats at mercury saturation of 35% (r35), and connate water saturation (S wc ) as inputs of K-nearest neighbors, the reservoir was classified into two petrophysical zones, and then, permeability for each zone was estimated. Due to the heterogeneous nature of the formation, the predicted permeability results needed to be more accurate. In the second part, we applied novel machine learning algorithms, modified group modeling data handling (GMDH), and genetic programming (GP) to develop one universal permeability equation for the whole reservoir of interest as a function of porosity, the radius of pore throats at mercury saturation of 35% (r35), and connate water saturation (S wc ). The novelty of the current approach is that despite being universal, the models developed using GP and GMDH performed substantially better than zone-specific permeability, index-based empirical, or data-driven models used in the literature, such as FZI and Winland. The predicted permeability using GMDH and GP resulted in accurate prediction with R 2 of 0.99 and 0.95, respectively, in the heterogeneous reservoir of interest. Moreover, as this study aimed to develop an explainable model, different parameter importance analyses were also applied to the developed permeability models, and r35 was found to be the most impactful feature.

show abstract

Section: Introductionmentioning

confidence: 99%

Modeling Permeability Using Advanced White-Box Machine Learning Technique: Application to a Heterogeneous Carbonate Reservoir

Zhao,

Guo,

Mohammadian

et al. 2023

ACS Omega

View full text Add to dashboard Cite

show abstract

“…Machine learning is effectively used by Man et al (2021) to boost the prediction of permeability and reduces uncertainty in reservoir modeling. Recently, a variety of conventional methods and machine learning algorithms were investigated in determining hydraulic flow units (HFUs), and the performance of each method was evaluated (Fernandes et al, 2023a;Kianoush et al, 2022bKianoush et al, , 2023cKianoush et al, 2023a;Masroor et al, 2023;mohammadinia et al, 2023;Shi et al, 2023;Yu et al, 2023). Salavati et al (2023) used hydraulic flow units, multi-resolution graphbased clustering, and fuzzy c-mean clustering methods to determine rock types.…”

Section: Introductionmentioning

confidence: 99%

Determining the petrophysical rock types utilizing the Fuzzy C-means Clustering technique and the concept of hydraulic flow units

Eftekhari,

Memariani,

Maleki

et al. 2023

Preprint

View full text Add to dashboard Cite

Rock types are the reservoir's most essential properties and show special facies with a defined range of porosity and permeability. This study used the fuzzy c-means clustering technique to identify rock types in 280 core samples obtained from one of the wells drilled in the Asmari reservoir located in the Mansouri field. Four hydraulic flow units were determined for studied data after classifying the flow zone index with histogram analysis, normal probability analysis, and the sum of square error methods. Then the two methods of flow zone index and fuzzy c-means clustering were used to determine the rock types in given wells according to the results obtained from the implementation of these two methods in-depth, and continuity index acts, the fuzzy c-means methods with continuity number 3.12 compared to flow zone index with continuity number 2.77 shows more continuity in depth. Amounts of porosity and permeability of the different reservoir rock samples have high dispersion; the relationship between these two parameters improves by using hydraulic flow unit techniques significantly. In this study, the relationship between porosity and permeability of correlation coefficient improves and increases in each hydraulic flow unit by using the flow zone index method so that in the general case for all samples increased from 0.55 to 0.81 in the first hydraulic flow unit, 0.94 in the second hydraulic flow unit, 0.85 in the third hydraulic flow unit and 0.94 in the fourth hydraulic flow unit that this is because the samples were characterized by similar flow properties in a hydraulic flow unit. In comparison, the correlation coefficient is obtained less than the general case in the fuzzy c-means method in all hydraulic flow units.

show abstract

“…Compilation of core porosity and permeability are used to identify these units. Yasmaniar et al (2018) utilized Artificial Neural Network (ANN) to determine the permeability of different Rock Type Using the Hydraulic Flow Unit Concept (Ding et al, 2022;Kharrat et al, 2009;Kianoush et al, 2023c;Mahadasu and Singh, 2022;Masroor et al, 2023;Rafik and Kamel, 2017). Oliveira et al (2020) demonstrated that an inter-clustering process is recommended when selecting data points associated with representative volumes and local spots characterizing HFUs.…”

Section: Introductionmentioning

confidence: 99%

“…Machine learning is effectively used by Man et al (2021) to boost the prediction of permeability and reduces uncertainty in reservoir modeling. Recently, a variety of conventional methods and machine learning algorithms were investigated in determining hydraulic flow units (HFUs), and the performance of each method was evaluated (Fernandes et al, 2023a;Forbes Inskip et al, 2020;Kianoush et al, 2022bKianoush et al, , 2023cKianoush et al, 2023a;Masroor et al, 2023;mohammadinia et al, 2023;Shi et al, 2023;Yu et al, 2023). Salavati et al (2023) used hydraulic flow units, multi-resolution graph-based clustering, and fuzzy c-mean clustering methods to determine rock types.…”

Section: Introductionmentioning

confidence: 99%

Determining the petrophysical rock types utilizing the Fuzzy C-means Clustering technique and the concept of hydraulic flow units

Eftekhari,

Memariani,

Maleki

et al. 2023

Preprint

View full text Add to dashboard Cite

Rock types are the reservoir's most essential properties and show special facies with a defined range of porosity and permeability. This study used the fuzzy c-means clustering technique to identify rock types in 280 core samples from one of the wells drilled in the Asmari reservoir in the Mansouri field, SW Iran. Four hydraulic flow units were determined for studied data after classifying the flow zone index with histogram analysis, normal probability analysis, and the sum of square error methods. Then the two methods of flow zone index and fuzzy c-means clustering were used to determine the rock types in given wells according to the results obtained from the implementation of these two methods in-depth, and continuity index acts, the fuzzy c-means methods with continuity number 3.12 compared to flow zone index with continuity number 2.77 shows more continuity in depth. The relationship between porosity and permeability improved using hydraulic flow unit techniques significantly. In this study, the correlation coefficient between porosity and permeability improves and increases in each hydraulic flow unit using the flow zone index method. So that in the general case, all samples increased from 0.55 to 0.81 in the first hydraulic flow unit and finally 0.94 in the fourth hydraulic flow unit. The samples were characterized by similar flow properties in a hydraulic flow unit. In comparison, the correlation coefficient is obtained less than the general case in the fuzzy c-means method in all hydraulic flow units.

show abstract

A multiple-input deep residual convolutional neural network for reservoir permeability prediction

Cited by 30 publications

References 40 publications

Modeling Permeability Using Advanced White-Box Machine Learning Technique: Application to a Heterogeneous Carbonate Reservoir

Modeling Permeability Using Advanced White-Box Machine Learning Technique: Application to a Heterogeneous Carbonate Reservoir

Determining the petrophysical rock types utilizing the Fuzzy C-means Clustering technique and the concept of hydraulic flow units

Determining the petrophysical rock types utilizing the Fuzzy C-means Clustering technique and the concept of hydraulic flow units

Contact Info

Product

Resources

About