Automation of Carbonate Rock Thin Section Description Using Cognitive Image Recognition

2021 ◽  
Author(s):  
Hesham Talaat Shebl ◽  
Mohamed Ali Al Tamimi ◽  
Douglas Alexander Boyd ◽  
Hani Abdulla Nehaid
Keyword(s):  
Thin Section ◽  
Image Recognition ◽  
Oil Recovery ◽  
Reservoir Rock ◽  
Supervised Machine Learning ◽  
Neural Net ◽  
Data Set ◽  
Thin Sections ◽  
Rock Quality ◽  
Pore Types

Abstract Simulation Engineers and Geomodelers rely on reservoir rock geological descriptions to help identify baffles, barriers and pathways to fluid flow critical to accurate reservoir performance predictions. Part of the reservoir modelling process involves Petrographers laboriously describing rock thin sections to interpret the depositional environment and diagenetic processes controlling rock quality, which along with pressure differences, controls fluid movement and influences ultimate oil recovery. Supervised Machine Learning and a rock fabric labelled data set was used to train a neural net to recognize Modified Durham classification reservoir rock thin section images and their individual components (fossils and pore types) plus predict rock quality. The image recognition program's accuracy was tested on an unseen thin section image database.

scholarly journals Ice crystal c-axis orientation and mean grain size measurements from the Dome Summit South ice core, Law Dome, East Antarctica

2016 ◽  
Author(s):  
A. Treverrow ◽  
J. Li ◽  
T. H. Jacka
Keyword(s):  
Thin Section ◽  
Ice Core ◽  
Median Number ◽  
East Antarctica ◽  
Polar Coordinates ◽  
Depth Information ◽  
Data Set ◽  
Axis Orientation ◽  
Orientation Data ◽  
Thin Sections

Abstract. We present measurements of crystal c-axis orientations and mean grain area from the Dome Summit South (DSS) ice core drilled on Law Dome, East Antarctica. These data are from 185 individual thin sections obtained between a depth of 117 m below the surface and the bottom of the DSS core at a depth of 1196 m. The median number of c-axis orientations recorded in each thin section was 100, with values ranging from 5 through to 111 orientations. The data from all 185 thin sections are provided in a single comma separated value (csv) formatted file which contains the c-axis orientations in polar coordinates, depth information for each core section from which the data were obtained, the mean grain area calculated for each thin section and other data related to the drilling site. The data set is also available as a MATLAB™ structure array. Additionally, the c-axis orientation data from each thin of the 185 thin sections are summarised graphically in figures containing a Schmidt diagram, histogram of c-axis colatitudes and rose plot of c-axis azimuths. All of these data are referenced by doi:10.4225/15/5669050CC1B3B and are available free of charge at https://data.antarctica.gov.au.

scholarly journals Sandstone Reservoir Wettability Alteration Due to Water Softening: Impact of Silica Nanoparticles on Sand Production Mechanism

2020 ◽  
Vol 10 (5) ◽  
pp. 6328-6342 ◽  
Keyword(s):  
Contact Angle ◽  
Silica Nanoparticles ◽  
Oil Recovery ◽  
Reservoir Rock ◽  
Wettability Alteration ◽  
Sand Production ◽  
Thin Sections ◽  
Low Salinity ◽  
Low Salinity Water ◽  
Salinity Water

Low salinity water in the oil reservoirs changes the wettability and increases the oil recovery factor. In sandstone reservoirs, the sand production occurs or intensifies with wettability alteration due to low salinity water injection. In any case, sand production should be stopped and there are many ways to prevent sand production. By modifying the composition of low salinity water, it can be adapted to be more compatible with the reservoir rock and formation water, which has the least formation damage. By eliminating magnesium and calcium ions, smart soft water (SSW) is created which is economically suitable for injection into the reservoirs. By stabilizing the nanoparticles in SSW, nanofluids can be prepared which with injection into the sandstones reservoir increase the oil recovery, change the wettability and increase the rock strength. In this present, SSW composition was determined by compatibility testing, and the SiO2 nanoparticle with 1000 ppm concentration was stabilized in SSW. Eight thin sections were oil wetted by using normal heptane solution and different molars of stearic acid and two thin sections were considered as base thin sections to compare the effect of wettability alteration on sand production. Thin sections were immersed in SSW and Nanofluid, the amount of contact angle and sand production were measured in both cases. The amount of sand produced and the contact angle in SSW was higher than the Nanofluid. The silica nanoparticles reduced the contact angle (more water wetting) and by sitting between the sand particles, more than 40%, it reduced sand production.

Screening Reservoir Candidates for Enhanced Oil Recovery (EOR) in Angolan Offshore Projects

2020 ◽  
Vol 1 (1) ◽  
pp. 6-10
Author(s):  
Geraldo A. R. Ramos ◽  
Bruno Elias ◽  
Kyari Yates
Keyword(s):  
Enhanced Oil Recovery ◽  
Oil Recovery ◽  
Fuzzy Inference ◽  
Reservoir Rock ◽  
Data Set ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Hydrocarbon Gas ◽  
Using Data ◽  
Takagi Sugeno

The neuro-fuzzy (NF) approach presented in this work is based on five (5) layered feedforward backpropagation algorithm applied for technical screening of enhanced oil recovery (EOR) methods. Associated reservoir rock-fluid oilfield data from successful EOR projects were used as input and predicted output in the training and validation processes, respectively. The developed model was then tested by using data set from Block B of an Angolan oilfield. The results of the sensitivity analysis between the Mamdani and the Takagi-Sugeno-Kang (TSK) approach incorporated in the algorithm has shown the robustness of the TSK ANFIS (Adaptive Neuro-Fuzzy Inference System) approach in comparison to the other approach for the prediction of a suitable EOR technique. The simulation test results showed that the model presented in this study can be used for technical selection of suitable EOR techniques. Within the area investigated (Block B, Angola) polymer, hydrocarbon gas, and combustion were identified as the suitable techniques for EOR.

scholarly journals Ice crystal <i>c</i>-axis orientation and mean grain size measurements from the Dome Summit South ice core, Law Dome, East Antarctica

2016 ◽  
Vol 8 (1) ◽  
pp. 253-263 ◽  
Author(s):  
Adam Treverrow ◽  
Li Jun ◽  
Tim H. Jacka
Keyword(s):  
Thin Section ◽  
Ice Core ◽  
Median Number ◽  
East Antarctica ◽  
Polar Coordinates ◽  
Depth Information ◽  
Data Set ◽  
Axis Orientation ◽  
Orientation Data ◽  
Thin Sections

Abstract. We present measurements of crystal c-axis orientations and mean grain area from the Dome Summit South (DSS) ice core drilled on Law Dome, East Antarctica. All measurements were made on location at the borehole site during drilling operations. The data are from 185 individual thin sections obtained between a depth of 117 m below the surface and the bottom of the DSS core at a depth of 1196 m. The median number of c-axis orientations recorded in each thin section was 100, with values ranging from 5 through to 111 orientations. The data from all 185 thin sections are provided in a single comma-separated value (csv) formatted file which contains the c-axis orientations in polar coordinates, depth information for each core section from which the data were obtained, the mean grain area calculated for each thin section and other data related to the drilling site. The data set is also available as a MATLAB™ structure array. Additionally, the c-axis orientation data from each of the 185 thin sections are summarized graphically in figures containing a Schmidt diagram, histogram of c-axis colatitudes and rose plot of c-axis azimuths. All these data are referenced by doi:10.4225/15/5669050CC1B3B and are available free of charge at https://data.antarctica.gov.au.

Exploring fake news identification using word and sentence embeddings

2021 ◽  
pp. 1-8
Author(s):  
V.T Priyanga ◽  
J.P Sanjanasri ◽  
Vijay Krishna Menon ◽  
E.A Gopalakrishnan ◽  
K.P Soman
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Network Analysis ◽  
Supervised Machine Learning ◽  
Breeding Ground ◽  
Fake News ◽  
Data Set ◽  
Highly Correlated ◽  
Use Of Social Media ◽  
The Liar

The widespread use of social media like Facebook, Twitter, Whatsapp, etc. has changed the way News is created and published; accessing news has become easy and inexpensive. However, the scale of usage and inability to moderate the content has made social media, a breeding ground for the circulation of fake news. Fake news is deliberately created either to increase the readership or disrupt the order in the society for political and commercial benefits. It is of paramount importance to identify and filter out fake news especially in democratic societies. Most existing methods for detecting fake news involve traditional supervised machine learning which has been quite ineffective. In this paper, we are analyzing word embedding features that can tell apart fake news from true news. We use the LIAR and ISOT data set. We churn out highly correlated news data from the entire data set by using cosine similarity and other such metrices, in order to distinguish their domains based on central topics. We then employ auto-encoders to detect and differentiate between true and fake news while also exploring their separability through network analysis.

scholarly journals NMR-Based Study of the Pore Types’ Contribution to the Elastic Response of the Reservoir Rock

Energies ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 1513 ◽  
Author(s):  
Naser Golsanami ◽  
Xuepeng Zhang ◽  
Weichao Yan ◽  
Linjun Yu ◽  
Huaimin Dong ◽  
...  
Keyword(s):  
Elastic Wave ◽  
Wave Velocity ◽  
Transverse Relaxation Time ◽  
Seismic Attributes ◽  
Elastic Wave Velocity ◽  
Reservoir Rock ◽  
Elastic Response ◽  
Hydrocarbon Reservoir ◽  
Statistical Ensembles ◽  
Pore Types

Seismic data and nuclear magnetic resonance (NMR) data are two of the highly trustable kinds of information in hydrocarbon reservoir engineering. Reservoir fluids influence the elastic wave velocity and also determine the NMR response of the reservoir. The current study investigates different pore types, i.e., micro, meso, and macropores’ contribution to the elastic wave velocity using the laboratory NMR and elastic experiments on coal core samples under different fluid saturations. Once a meaningful relationship was observed in the lab, the idea was applied in the field scale and the NMR transverse relaxation time (T2) curves were synthesized artificially. This task was done by dividing the area under the T2 curve into eight porosity bins and estimating each bin’s value from the seismic attributes using neural networks (NN). Moreover, the functionality of two statistical ensembles, i.e., Bag and LSBoost, was investigated as an alternative tool to conventional estimation techniques of the petrophysical characteristics; and the results were compared with those from a deep learning network. Herein, NMR permeability was used as the estimation target and porosity was used as a benchmark to assess the reliability of the models. The final results indicated that by using the incremental porosity under the T2 curve, this curve could be synthesized using the seismic attributes. The results also proved the functionality of the selected statistical ensembles as reliable tools in the petrophysical characterization of the hydrocarbon reservoirs.

scholarly journals Leveraging Road Characteristics and Contributor Behaviour for Assessing Road Type Quality in OSM

2021 ◽  
Vol 10 (7) ◽  
pp. 436
Author(s):  
Amerah Alghanim ◽  
Musfira Jilani ◽  
Michela Bertolotto ◽  
Gavin McArdle
Keyword(s):  
Machine Learning ◽  
Spatial Data ◽  
Classification Accuracy ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Data Set ◽  
Semantic Inference ◽  
Road Type ◽  
The Impact

Volunteered Geographic Information (VGI) is often collected by non-expert users. This raises concerns about the quality and veracity of such data. There has been much effort to understand and quantify the quality of VGI. Extrinsic measures which compare VGI to authoritative data sources such as National Mapping Agencies are common but the cost and slow update frequency of such data hinder the task. On the other hand, intrinsic measures which compare the data to heuristics or models built from the VGI data are becoming increasingly popular. Supervised machine learning techniques are particularly suitable for intrinsic measures of quality where they can infer and predict the properties of spatial data. In this article we are interested in assessing the quality of semantic information, such as the road type, associated with data in OpenStreetMap (OSM). We have developed a machine learning approach which utilises new intrinsic input features collected from the VGI dataset. Specifically, using our proposed novel approach we obtained an average classification accuracy of 84.12%. This result outperforms existing techniques on the same semantic inference task. The trustworthiness of the data used for developing and training machine learning models is important. To address this issue we have also developed a new measure for this using direct and indirect characteristics of OSM data such as its edit history along with an assessment of the users who contributed the data. An evaluation of the impact of data determined to be trustworthy within the machine learning model shows that the trusted data collected with the new approach improves the prediction accuracy of our machine learning technique. Specifically, our results demonstrate that the classification accuracy of our developed model is 87.75% when applied to a trusted dataset and 57.98% when applied to an untrusted dataset. Consequently, such results can be used to assess the quality of OSM and suggest improvements to the data set.

Design Chaotic Neural Network from Discrete Time Feedback Function

2013 ◽  
Vol 339 ◽  
pp. 366-371
Author(s):  
Jin Sheng Ren ◽  
Guang Chun Luo ◽  
Ke Qin
Keyword(s):  
Discrete Time ◽  
Design Methodology ◽  
Universal Design ◽  
Jacobian Matrix ◽  
Sufficient Conditions ◽  
Neural Net ◽  
Chaotic Neural Network ◽  
Data Set ◽  
Dominant Matrix ◽  
Theoretical Results

The goal of this paper is to give a universal design methodology of a Chaotic Neural Net-work (CNN). By appropriately choosing self-feedback, coupling functions and external stimulus, we have succeeded in proving a dynamical system defined by discrete time feedback equations possess-ing interesting chaotic properties. The sufficient conditions of chaos are analyzed by using Jacobian matrix, diagonal dominant matrix and Lyapunov Exponent (LE). Experiments are also conducted un-der a simple data set. The results confirm the theorem's correctness. As far as we know, both the experimental and theoretical results presented here are novel.

Micromorphology of soil structure - Description, quantification, application

Soil Research ◽  
1991 ◽  
Vol 29 (6) ◽  
pp. 777 ◽  
Author(s):  
AJ Ringrose-Voase
Keyword(s):  
Soil Structure ◽  
Pore Space ◽  
Structural Parameters ◽  
Thin Sections ◽  
Physical Measurements ◽  
Undisturbed Samples ◽  
Structure Description ◽  
Management Techniques ◽  
Pore Types ◽  
Soil Behaviour

Micromorphological observation can provide insights into soil structure and aid interpretation of soil behaviour. Undisturbed samples are taken in the field and impregnated. They are used to prepare thin sections or images of the macropore structure using fluorescent photography. Sections can also be obtained at macro, meso and submicroscopic scales. The various elements of soil structure observed micromorphologically can be classified into pore space, physical, distribution and orientation fabrics, and associated structures. Examples of the importance of features in each category are given. Image analysis, especially when computerized, provides a way of parameterizing micromorphological observations. To date it has been used primarily on images of macropore space at the meso and microscopic scales. Such images can be digitized and segmented to show pore space and solid. The pore space can be allocated to pore types. This aids the estimation of 3-D parameters from I-D and 2-D measurements made on the image using stereology. Various ways of using structural parameters to compare structures are discussed. Applications for micromorphological observations, especially when quantitative, include comparison of structures formed by different management techniques. Structural measurements can aid interpretation of soil behaviour as described by physical measurements. They also have a role in estimating the representative elementary volume, on which physical measurements should be made, and in calibrating field estimates of soil structure.

Sign in / Sign up

Export Citation Format

Share Document