Permeability Estimation for Natural State Modeling of Geothermal Fields with Machine Learning

2021 ◽  
Author(s):  
Ali Baser ◽  
Mustafa Sert
Keyword(s):  
Machine Learning ◽  
Natural State ◽  
Permeability Estimation ◽  
Geothermal Fields

Incorporating Dynamic Production Logging Data to the Permeability Estimation Workflow Using Machine Learning

2020 ◽  
Author(s):  
Ciro Guimaraes ◽  
Luiz Schirmer ◽  
Guilherme Schardong ◽  
Abelardo Barreto Jr. ◽  
Hélio Lopes
Keyword(s):  
Machine Learning ◽  
Permeability Estimation ◽  
Dynamic Production

Technology Focus: EOR Modeling (January 2021)

2021 ◽  
Vol 73 (01) ◽  
pp. 43-43
Author(s):  
Subodh Gupta
Keyword(s):  
Machine Learning ◽  
Porous Media ◽  
Relative Permeability ◽  
Oil Recovery ◽  
Data Science ◽  
Reservoir Characterization ◽  
Flow In Porous Media ◽  
Reservoir Modeling ◽  
Permeability Estimation ◽  
Variable Chemical

The enhanced-oil-recovery (EOR) literature produced in the past several months was dominated by reservoir modeling and characterization; flood enhancements; machine learning; and, more notably, relative permeability estimation. This last one needs to be under-stood further. Relative permeability characterizes flow in porous media, the understanding and manipulating of which is key to the success of EOR. Our fascination with the topic during the last 75 years, therefore, is understandable. Starting with a seminal paper from W.R. Purcell in 1949, we have more than 12,000 articles in the SPE collection alone on relative permeability estimation, of which more than 400 were published in the last year. Mechanics of motion is also important to mankind, but we do not have literature piling up on Newton’s laws of motion. Is it that we haven’t understood flow in porous media yet, or is it because the subject matter is so complex? The truth, perhaps, lies somewhere in between. Flow in pores that are randomly sized, randomly connected, and have variable chemical makeup is, by nature, complex and mathematically unmanageable. Relative permeability has been our attempt to lend its aggregate behavior some sense of manageability. This has always been done in a fit-for-purpose manner. What is fit for one context, however, may not be so for the others, and this uncertainty continues to churn out theses, antitheses, and syntheses. Expectedly, even more such activity arises with every improvement in computing capabilities, as is once again evident with advances in machine learning—new tools to handle old problems. That is where my first pick is for you, with some additional suggested readings in references that follow. Data analytics does much more than estimate relative permeability, and the second paper abridged here uses it to predict a flood performance. To allow a break from data science, the third paper chosen deals with the important topic of electromagnetics as applied to reservoir characterization and heating. I hope you find these to be useful and interesting reads.

Integrating Pore Geometrical Characteristics for Permeability Prediction of Tight Carbonates Utilizing Artificial Intelligence

2021 ◽  
Author(s):  
Mohammad Rasheed Khan ◽  
Shams Kalam ◽  
Asiya Abbasi
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Reservoir Characterization ◽  
Transfer Functions ◽  
Mean Squared Error ◽  
Statistical Error ◽  
Machine Learning Algorithms ◽  
Percentage Error ◽  
Neural Net ◽  
Permeability Estimation

Abstract Accurate permeability estimation in tight carbonates is a key reservoir characterization challenge, more pronounced with heterogeneous pore structures. Experiments on large volumes of core samples are required to precisely characterize permeability in such reservoirs which means investment of large amounts of time and capital. Therefore, it is imperative that an integrated model exists that can predict field-wide permeability for un-cored sections to optimize reservoir strategies. Various studies exist with a scope to address this challenge, however, most of them lack universality in application or do not consider important carbonate geometrical features. Accordingly, this work presents a novel correlation to determine permeability of tight carbonates as a function of carbonate pore geometry utilizing a combination of machine learning and optimization algorithms. Primarily, a Deep Learning Neural Network (NN) is constructed and further optimized to produce a data-driven permeability predictor. Customization of the model to tight-heterogenous pore-scale features is accomplished by considering key geometrical carbonate topologies, porosity, formation resistivity, pore cementation representation, characteristic pore throat diameter, pore diameter, and grain diameter. Multiple realizations are conducted spanning from a perceptron-based model to a multi-layered neural net with varying degrees of activation and transfer functions. Next, a physical equation is derived from the optimized model to provide a stand-alone equation for permeability estimation. Validation of the proposed model is conducted by graphical and statistical error analysis of model testing on unseen dataset. A major outcome of this study is the development of a physical mathematical equation which can be used without diving into the intricacy of artificial intelligence algorithms. To evaluate performance of the new correlation, an error metric comprising of average absolute percentage error (AAPE), root mean squared error (RMSE), and correlation coefficient (CC) was used. The proposed correlation performs with low error values and gives CC more than 0.95. A possible reason for this outcome is that the machine learning algorithms can construct relationship between various non-linear inputs (for e.g., carbonate heterogeneity) and output (permeability) parameters through its inbuilt complex interaction of transfer and activation function methodologies.

scholarly journals Analysis of the time series of seismic and deformation monitoring, obtained from closed works at the Kirovsky mine of JSC "Apatite"

2020 ◽  
Vol 9 (2) ◽  
pp. 568
Author(s):  
Gospodarikov Aleksandr P. ◽  
Morozov Konstantin V. ◽  
Revin Ilia E
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Functional Relationship ◽  
Learning Algorithms ◽  
Deformation Monitoring ◽  
Machine Learning Algorithms ◽  
Natural State ◽  
Mining Operations ◽  
Activity Data ◽  
State Of Stress

The article is devoted to the analysis of the time series, obtained from seismic and deformation monitoring from closed works of Kukisvumchorr deposit JSC "Apatite". The objective of this study is to develop a method for assessing the results of monitoring geomechanical processes in the rock mass on the example of the Kirov mine JSC "Apatit". As a result of closed works, rock masses are changing its natural state of stress. This article has consistently outlined the use of machine learning algorithms in applied problems of geomechanics and geoinformatics. By comparing the schedule of mining operations and seismic activity data with time series of deformations, it is possible to obtain a functional relationship that predicts the distribution of deformations in the rock massif. The results of a computational experiment illustrating the possibility and feasibility of using machine learning algorithms in solving geomechanics problems are presented.  

Mind wandering as data augmentation: How mental travel supports abstraction

2020 ◽  
Vol 43 ◽  
Author(s):  
Myrthe Faber
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Mental Content ◽  
Mind Wandering ◽  
Theoretical Framework ◽  
Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Sem and X-Ray Analysis of Renal and Biliary Calculi

1976 ◽  
Vol 34 ◽  
pp. 306-307
Author(s):  
R. J. Narconis ◽  
G. L. Johnson
Keyword(s):  
Chemical Constituents ◽  
Natural State ◽  
X Ray Diffraction ◽  
Chemical Methods ◽  
X Ray ◽  
Additional Dimension ◽  
Biliary Calculi ◽  
Calculus Formation ◽  
Scanning Electron

Analysis of the constituents of renal and biliary calculi may be of help in the management of patients with calculous disease. Several methods of analysis are available for identifying these constituents. Most common are chemical methods, optical crystallography, x-ray diffraction, and infrared spectroscopy. The application of a SEM with x-ray analysis capabilities should be considered as an additional alternative.A scanning electron microscope equipped with an x-ray “mapping” attachment offers an additional dimension in its ability to locate elemental constituents geographically, and thus, provide a clue in determination of possible metabolic etiology in calculus formation. The ability of this method to give an undisturbed view of adjacent layers of elements in their natural state is of advantage in determining the sequence of formation of subsequent layers of chemical constituents.

Structural integrity after cold storage of human epidermal model in hypothermosol: A correlative ultrastructural and fluorescent assay

1994 ◽  
Vol 52 ◽  
pp. 270-271
Author(s):  
Henry H. Eichelberger ◽  
John G. Baust ◽  
Robert G. Van Buskirk
Keyword(s):  
Cold Storage ◽  
Structural Integrity ◽  
Culture Media ◽  
Cell Structure ◽  
Natural State ◽  
Sodium Cacodylate ◽  
Ruthenium Tetroxide ◽  
Cacodylate Buffer ◽  
Before And After

For research in cell differentiation and in vitro toxicology it is essential to provide a natural state of cell structure as a benchmark for interpreting results. Hypothermosol (Cryomedical Sciences, Rockville, MD) has proven useful in insuring the viability of synthetic human epidermis during cold-storage and in maintaining the epidermis’ ability to continue to differentiate following warming.Human epidermal equivalent, EpiDerm (MatTek Corporation, Ashland, MA) consisting of fully differentiated stratified human epidermal cells were grown on a microporous membrane. EpiDerm samples were fixed before and after cold-storage (4°C) for 5 days in Hypothermosol or skin culture media (MatTek Corporation) and allowed to recover for 7 days at 37°C. EpiDerm samples were fixed 1 hour in 2.5% glutaraldehyde in sodium cacodylate buffer (pH 7.2). A secondary fixation with 0.2% ruthenium tetroxide (Polysciences, Inc., Warrington, PA) in sodium cacodylate was carried out for 3 hours at 4°C. Other samples were similarly fixed, but with 1% Osmium tetroxide in place of ruthenium tetroxide. Samples were dehydrated through a graded acetone series, infiltrated with Spurrs resin (Polysciences Inc.) and polymerized at 70°C.

Sign in / Sign up

Export Citation Format

Share Document