scholarly journals Ensemble Learning for Predicting TOC from Well-Logs of the Unconventional Goldwyer Shale

Energies ◽  
2021 ◽  
Vol 15 (1) ◽  
pp. 216
Author(s):  
Partha Pratim Mandal ◽  
Reza Rezaee ◽  
Irina Emelyanova
Keyword(s):  
Ensemble Learning ◽  
Supervised Machine Learning ◽  
Well Logs ◽  
Estimation Accuracy ◽  
Canning Basin ◽  
The Core ◽  
Data Points ◽  
Shale Reservoirs ◽  
Petrophysical Logs ◽  
Rock Eval

Precise estimation of total organic carbon (TOC) is extremely important for the successful characterization of an unconventional shale reservoir. Indirect traditional continuous TOC prediction methods from well-logs fail to provide accurate TOC in complex and heterogeneous shale reservoirs. A workflow is proposed to predict a continuous TOC profile from well-logs through various ensemble learning regression models in the Goldwyer shale formation of the Canning Basin, WA. A total of 283 TOC data points from ten wells is available from the Rock-Eval analysis of the core specimen where each sample point contains three to five petrophysical logs. The core TOC varies largely, ranging from 0.16 wt % to 4.47 wt % with an average of 1.20 wt %. In addition to the conventional MLR method, four supervised machine learning methods, i.e., ANN, RF, SVM, and GB are trained, validated, and tested for continuous TOC prediction using the ensemble learning approach. To ensure robust TOC prediction, an aggregated model predictor is designed by combining the four ensemble-based models. The model achieved estimation accuracy with R2 value of 87%. Careful data preparation and feature selection, reconstruction of corrupted or missing logs, and the ensemble learning implementation and optimization have improved TOC prediction accuracy significantly compared to a single model approach.

Lithofacies classification in the Marcellus Shale by applying a statistical clustering algorithm to petrophysical and elastic well logs

2016 ◽  
Vol 4 (2) ◽  
pp. SE31-SE49 ◽  
Author(s):  
Kristen Schlanser ◽  
Dario Grana ◽  
Erin Campbell-Stone
Keyword(s):  
Clustering Algorithm ◽  
Marcellus Shale ◽  
Organic Content ◽  
Recognition Algorithm ◽  
Well Logs ◽  
Well Log ◽  
The Core ◽  
Petrophysical Logs ◽  
Marcellus Formation ◽  
Facies Models

Interpreting shale lithofacies is an important step in identifying productive zones in the Marcellus Shale gas play; the target reservoir can be less than 3 m (10 ft) thick with overlying shales that appear similar on certain petrophysical well logs and in the core. However, these nonreservoir-quality shales contain widely varying organic and mechanical properties. To distinguish between reservoir- and nonreservoir-quality shale facies, this classification method applies a pattern-recognition algorithm, expectation maximization, to a set of commonly available petrophysical and elastic well logs to create 1D shale facies models along the wellbore. The statistical algorithm classifies the petrophysical and elastic well-log data into defined facies using the theory that each well log contains a distribution of Gaussian curves for each facies. The method is applied to 12 wells across Pennsylvania and northern West Virginia, and it is able to discriminate between shale facies based on organic content and brittleness, characteristics which are not always evident in core. To verify the geologic accuracy of the facies models, the results are compared with the core data, well logs, mudlogs, and regional stratigraphic studies when available. In addition, we were able to designate a lithofacies-defined top to the Marcellus Formation in parts of the Appalachian Basin where the gradational contact with the overlying Mahantango Formation is poorly defined on petrophysical logs.

Petrophysical and geochemical interpretations of well logs from the pre-Carboniferous succession in Barnicarndy 1, Canning Basin, Western Australia

2021 ◽  
Vol 61 (1) ◽  
pp. 253
Author(s):  
Liuqi Wang ◽  
Dianne S. Edwards ◽  
Adam Bailey ◽  
Lidena K. Carr ◽  
Chris J. Boreham ◽  
...  
Keyword(s):  
Western Australia ◽  
Well Logs ◽  
Canning Basin

scholarly journals Predicting Obstetric Disease With Machine Learning Applied to Patient-Reported Data (Preprint)

2018 ◽  
Author(s):  
Danielle Bradley ◽  
Erin Landau ◽  
Adam Wolfberg ◽  
Alex Baron
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Mobile Apps ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Obstetric Outcomes ◽  
Patient Reported ◽  
Data Points ◽  
Reported Data

BACKGROUND The rise of highly engaging digital health mobile apps over the past few years has created repositories containing billions of patient-reported data points that have the potential to inform clinical research and advance medicine. OBJECTIVE To determine if self-reported data could be leveraged to create machine learning algorithms to predict the presence of, or risk for, obstetric outcomes and related conditions. METHODS More than 10 million women have downloaded Ovia Health’s three mobile apps (Ovia Fertility, Ovia Pregnancy, and Ovia Parenting). Data points logged by app users can include information about menstrual cycle, health history, current health status, nutrition habits, exercise activity, symptoms, or moods. Machine learning algorithms were developed using supervised machine learning methodologies, specifically, Gradient Boosting Decision Tree algorithms. Each algorithm was developed and trained using anywhere from 385 to 5770 features and data from 77,621 to 121,740 app users. RESULTS Algorithms were created to detect the risk of developing preeclampsia, gestational diabetes, and preterm delivery, as well as to identify the presence of existing preeclampsia. The positive predictive value (PPV) was set to 0.75 for all of the models, as this was the threshold where the researchers felt a clinical response—additional screening or testing—would be reasonable, due to the likelihood of a positive outcome. Sensitivity ranged from 24% to 75% across all models. When PPV was adjusted from 0.75 to 0.52, the sensitivity of the preeclampsia prediction algorithm rose from 24% to 85%. When PPV was adjusted from 0.75 to 0.65, the sensitivity of the preeclampsia detection or diagnostic algorithm increased from 37% to 79%. CONCLUSIONS Algorithms based on patient-reported data can predict serious obstetric conditions with accuracy levels sufficient to guide clinical screening by health care providers and health plans. Further research is needed to determine whether such an approach can improve outcomes for at-risk patients and reduce the cost of screening those not at risk. Presenting the results of these models to patients themselves could also provide important insight into otherwise unknown health risks.

scholarly journals ARBTools: A Tricubic Spline Interpolator for Three-Dimensional Scalar or Vector Fields

2019 ◽  
Author(s):  
Paul Walker ◽  
Ulrich Krohn ◽  
Carty David
Keyword(s):  
Magnetic Field ◽  
Vector Field ◽  
Vector Fields ◽  
Three Dimensional ◽  
Spline Method ◽  
Particle Trajectories ◽  
The Core ◽  
Numerical Integrators ◽  
Data Points ◽  
System Requirements

ARBTools is a Python library containing a Lekien-Marsden type tricubic spline method for interpolating three-dimensional scalar or vector fields presented as a set of discrete data points on a regular cuboid grid. ARBTools was developed for simulations of magnetic molecular traps, in which the magnitude, gradient and vector components of a magnetic field are required. Numerical integrators for solving particle trajectories are included, but the core interpolator can be used for any scalar or vector field. The only additional system requirements are NumPy.

Petrophysical Rocks: Electrofacies and Lithofacies

2014 ◽  
Author(s):  
John H. Doveton
Keyword(s):  
Particle Size ◽  
Physical Properties ◽  
Sedimentary Rocks ◽  
Well Control ◽  
The Core ◽  
Lateral Extent ◽  
Petrophysical Logs ◽  
Definition Of

Many years ago, the classification of sedimentary rocks was largely descriptive and relied primarily on petrographic methods for composition and granulometry for particle size. The compositional aspect broadly matches the goals of the previous chapter in estimating mineral content from petrophysical logs. With the development of sedimentology, sedimentary rocks were now considered in terms of the depositional environment in which they originated. Uniformitarianism, the doctrine that the present is the key to the past, linked the formation of sediments in the modern day to their ancient lithified equivalents. Classification was now structured in terms of genesis and formalized in the concept of “facies.” A widely quoted definition of facies was given by Reading (1978) who stated, “A facies should ideally be a distinctive rock that forms under certain conditions of sedimentation reflecting a particular process or environment.” This concept identifies facies as process products which, when lithified in the subsurface, form genetic units that can be correlated with well control to establish the geological architecture of a field. The matching of facies with modern depositional analogs means that dimensional measures, such as shape and lateral extent, can be used to condition reasonable geomodels, particularly when well control is sparse or nonuniform. Most wells are logged rather than cored, so that the identification of facies in cores usually provides only a modicum of information to characterize the architecture of an entire field. Consequently, many studies have been made to predict lithofacies from log measurements in order to augment core observations in the development of a satisfactory geomodel that describes the structure of genetic layers across a field. The term “electrofacies” was introduced by Serra and Abbott (1980) as a way to characterize collective associations of log responses that are linked with geological attributes. They defined electrofacies to be “the set of log responses which characterizes a bed and permits it to be distinguished from the others.” Electrofacies are clearly determined by geology, because physical properties of rocks. The intent of electrofacies identification is generally to match them with lithofacies identified in the core or an outcrop.

scholarly journals Depositional facies model and reservoir characterization of USANI field 1, Niger delta basin, Nigeria

2017 ◽  
Vol 5 (2) ◽  
pp. 57 ◽  
Author(s):  
Godwin Aigbadon ◽  
A.U Okoro ◽  
Chuku Una ◽  
Ocheli Azuka
Keyword(s):  
Tidal Flat ◽  
Water Saturation ◽  
Well Logs ◽  
Physical Analysis ◽  
Well Log ◽  
Delta Front ◽  
Depositional Facies ◽  
Facies Model ◽  
Core Data ◽  
The Core

The 3-D depositional environment was built using seismic data. The depositional facies was used to locate channels with highly theif zones and distribution of various sedimentary facies. The integration core data and the gamma ray log trend from the wells within the studied interval with right boxcar/right bow-shape indicate muddy tidal flat to mixed tidal flat environments. The bell–shaped from the well logs with the core data indicate delta front with mouth bar, the blocky box- car trend from the well logs with the core data indicate tidal point bar with tidal channel fill. The integration of seismic to well log tie display a good tie in the wells across the field. The attribute map from velocity analysis revealed the presence of hydrocarbons in the identified sands (A, B, C, D1, D2, D4, D5). The major faults F1, F2, F3 and F4 with good sealing capacity are responsible for hydrocarbon accumulation in the field. Detailed petro physical analysis of well log data showed that the studied interval are characterized by sand-shale inter-beds. Eight reservoirs were mapped at depth intervals of 2886m to 3533m with their thicknesses ranging from 12m to 407m. Also the Analysis of the petrophysical results showed that porosity of the reservoirs range from 14% to 28 %; permeability range from 245.70 md to 454.7md; water saturation values from 21.65% to 54.50% and hydrocarbon saturation values from 45.50% to 78.50 %. The by-passed hydrocarbons were identified and estimated in low resistivity pay sands D1, D2 at depth of 2884m – 2940m, sand D5 at depth of 3114m – 3126m respectively. The model serve as a basis for establishing facies model in the field.

scholarly journals Degrees of Freedom at the Start of the Second 100 Years: A Pedagogical Treatise

2019 ◽  
Vol 2 (4) ◽  
pp. 396-405
Author(s):  
Joseph Lee Rodgers
Keyword(s):  
Statistical Models ◽  
Degrees Of Freedom ◽  
Introductory Statistics ◽  
Core Concept ◽  
Traditional Treatment ◽  
The Core ◽  
History Of ◽  
Data Points

Degrees of freedom is a critical core concept within the field of statistics. Virtually every introductory statistics class treats the topic, though textbooks and the statistical literature show mostly superficial treatment, weak pedagogy, and substantial confusion. Fisher first defined degrees of freedom in 1915, and Walker provided technical treatment of the concept in 1940. In this article, the history of degrees of freedom is reviewed, and the pedagogical challenges are discussed. The core of the article is a simple reconceptualization of the degrees-of-freedom concept that is easier to teach and to learn than the traditional treatment. This reconceptualization defines a statistical bank, into which are deposited data points. These data points are used to estimate statistical models; some data are used up in estimating a model, and some data remain in the bank. The several types of degrees of freedom define an accounting process that simply counts the flow of data from the statistical bank into the model. The overall reconceptualization is based on basic economic principles, including treating data as statistical capital and data exchangeability (fungibility). The goal is to stimulate discussion of degrees of freedom that will improve its use and understanding in pedagogical and applied settings.

scholarly journals A Systematic Measurement of Street Quality through Multi-Sourced Urban Data: A Human-Oriented Analysis

2019 ◽  
Vol 16 (10) ◽  
pp. 1782 ◽  
Author(s):  
Lingzhu Zhang ◽  
Yu Ye ◽  
Wenxin Zeng ◽  
Alain Chiaradia
Keyword(s):  
Public Health ◽  
Physical Activity ◽  
Holistic Approach ◽  
Analytical Framework ◽  
Supervised Machine Learning ◽  
Fine Grained ◽  
Quantitative Measurements ◽  
Data Points ◽  
New Research ◽  
Urban Data

Many studies have been made on street quality, physical activity and public health. However, most studies so far have focused on only few features, such as street greenery or accessibility. These features fail to capture people’s holistic perceptions. The potential of fine grained, multi-sourced urban data creates new research avenues for addressing multi-feature, intangible, human-oriented issues related to the built environment. This study proposes a systematic, multi-factor quantitative approach for measuring street quality with the support of multi-sourced urban data taking Yangpu District in Shanghai as case study. This holistic approach combines typical and new urban data in order to measure street quality with a human-oriented perspective. This composite measure of street quality is based on the well-established 5Ds dimensions: Density, Diversity, Design, Destination accessibility and Distance to transit. They are combined as a collection of new urban data and research techniques, including location-based service (LBS) positioning data, points of interest (PoIs), elements and visual quality of street-view images extraction with supervised machine learning, and accessibility metrics using network science. According to these quantitative measurements from the five aspects, streets were classified into eight feature clusters and three types reflecting the value of street quality using a hierarchical clustering method. The classification was tested with experts. The analytical framework developed through this study contributes to human-oriented urban planning practices to further encourage physical activity and public health.

The Unconventional Shale Reservoirs of Jafurah Basin: An Integrated Petrophysical Evaluation Using Cores and Advanced Well Logs

2017 ◽  
Author(s):  
Ghadeer Al-Sulami ◽  
Mohammed Boudjatit ◽  
Mohammed Al-Duhailan ◽  
Salvatore Di Simone
Keyword(s):  
Well Logs ◽  
Shale Reservoirs ◽  
Petrophysical Evaluation
Sign in / Sign up

Export Citation Format

Share Document