Driving digital rock towards machine learning: Predicting permeability with gradient boosting and deep neural networks

Судаков, Олег Валериевич; Burnaev, Evgeny; Koroteev, Dmitry

doi:10.1016/j.cageo.2019.02.002

Cited by 180 publications

(76 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Then we use a network proposed by Sudakov et al [14] to estimate the porosity from a MCT image. This network has fewer layers than Inception-V3 but is able to accept 3D 100 x 100 x 100 voxel images.…”

Section: Workflow Description Machine Learning Conceptsmentioning

confidence: 99%

See 1 more Smart Citation

Digital core repository coupled with machine learning as a tool to classify and assess petrophysical rock properties

Hébert¹,

Porcher²,

Planes³

et al. 2020

E3S Web Conf.

View full text Add to dashboard Cite

To make efficient use of image-based rock physics workflow, it is necessary to optimize different criteria, among which: quantity, representativeness, size and resolution. Advances in artificial intelligence give insights of databases potential. Deep learning methods not only enable to classify rock images, but could also help to estimate their petrophysical properties. In this study we prepare a set of thousands highresolution 3D images captured in a set of four reservoir rock samples as a base for learning and training. The Voxilon software computes numerical petrophysical analysis. We identify different descriptors directly from 3D images used as inputs. We use convolutional neural network modelling with supervised training using TensorFlow framework. Using approximately fifteen thousand 2D images to drive the classification network, the test on thousand unseen images shows any error of rock type misclassification. The porosity trend provides good fit between digital benchmark datasets and machine learning tests. In a few minutes, database screening classifies carbonates and sandstones images and associates the porosity values and distribution. This work aims at conveying the potential of deep learning method in reservoir characterization to petroleum research, to illustrate how a smart image-based rock physics database at industrial scale can swiftly give access to rock properties.

show abstract

Section: Workflow Description Machine Learning Conceptsmentioning

confidence: 99%

“…Araya-Polo et al [13] used a deep learning architecture to instantaneously predict permeability of clastic rocks from high resolution Scanning Electron Microscopy images. Sudakov et al [14] validated a 3D CNN method for predicting permeability of digital Berea sandstone volume subsets.…”

Section: Introductionmentioning

confidence: 99%

Digital core repository coupled with machine learning as a tool to classify and assess petrophysical rock properties

Hébert¹,

Porcher²,

Planes³

et al. 2020

E3S Web Conf.

View full text Add to dashboard Cite

show abstract

“…The main research application for medical imaging was classification, and many works have covered this topic in detail (Antony et al, 2016;Çiçek et al, 2016;Hosseini-Asl et al, 2016;Kawahara et al, 2017;Korez et al, 2016;Miao et al, 2016;Milletari et al, 2016;Moeskops et al, 2016;Payan & Montana, 2015;Ronneberger et al, 2015;van Grinsven et al, 2016;Wolterink et al, 2016). For digital rock image processing, we are starting to investigate if results similar to that obtained in the medical field can be obtained for geomaterials (Alqahtani et al, 2018;Sudakov et al, 2018). The main limitation, however, is access to geomaterial training data.…”

Section: Introductionmentioning

confidence: 99%

Digital Rock Segmentation for Petrophysical Analysis With Reduced User Bias Using Convolutional Neural Networks

Niu

Mostaghimi

Shabaninejad

et al. 2020

Water Resources Research

View full text Add to dashboard Cite

Pore‐scale digital images are usually obtained from microcomputed tomography data that has been segmented into void and grain space. Image segmentation is a crucial step in the process of digital rock analysis that can influence pore‐scale characterization studies and/or the numerical simulation of petrophysical properties. This is concerning since all segmentation methods have user‐selected parameters that result in biases. Convolutional neural networks (CNNs) provide a way forward since once trained, CNN can provide consistent and reliable image segmentation with no user‐defined inputs. In this paper, a CNN is used to segment digital sandstone data, and various ground truth data sets are tested. The ground truth images are created based on high‐resolution microcomputed tomography data and corresponding scanning electron microscope data. The results are evaluated in terms of porosity, permeability, and pore size distribution computed from the segmented data. We find that watershed‐based segmentation provides a wide range of possible petrophysical values depending on user‐selected thresholds, whereas CNN provides a smaller variance when trained on scanning electron microscope data. It can be concluded that CNN offers a reliable and consistent way to segment digital sandstone data for petrophysical analyses.

show abstract

“…In many cases machine learning allow handling the forecasting problems for cases when the accuracy of physics-driven or empirical models is limited by uncertainties of their input parameters and can provide a fast approximation, or the so-called surrogate models, to estimate selected properties based on the results of real measurements (for details, see [4]). Surrogate models are a wellknown way of solving various industrial engineering problems including oil industry [2,3,9,13,17,18,20].…”

Section: Introductionmentioning

confidence: 99%

Gradient boosting to boost the efficiency of hydraulic fracturing

Makhotin

Koroteev

Burnaev

2019

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

In this paper, we present a data-driven model for forecasting the production increase after hydraulic fracturing (HF). We use data from fracturing jobs performed at one of the Siberian oilfields. The data includes features, characterizing the jobs, and geological information. To predict an oil rate after the fracturing machine learning (ML) technique was applied. We compared the ML-based prediction to a prediction based on the experience of reservoir and production engineers responsible for the HF-job planning. We discuss the potential for further development of ML techniques for predicting changes in oil rate after HF.

show abstract

Driving digital rock towards machine learning: Predicting permeability with gradient boosting and deep neural networks

Cited by 180 publications

References 26 publications

Digital core repository coupled with machine learning as a tool to classify and assess petrophysical rock properties

Digital core repository coupled with machine learning as a tool to classify and assess petrophysical rock properties

Digital Rock Segmentation for Petrophysical Analysis With Reduced User Bias Using Convolutional Neural Networks

Gradient boosting to boost the efficiency of hydraulic fracturing

Contact Info

Product

Resources

About