• Class and Course

    Applied Statistical Modeling and Data Analytics for Petroleum Engineers and Geoscientists

    This Course seeks to provide a practical guide to many of the classical and modern statistical techniques that have become, or are becoming, mainstream for oil and gas professionals. It is intended to serve as a “how to” guide for the practicing petroleum engineer or geoscientist interested in applying statistical modeling and data analytics techniques in reservoir characterization, reservoir modeling/diagnostics and performance predictions. Examples related to both conventional and unconventional reservoirs will be presented and the participants will analyze data using public domain software.
    There is a growing trend towards the use of  statistical modeling and data analytics for analyzing the performance petroleum reservoirs, particularly unconventional reservoirs. The goal is to “mine the data” and develop data-driven insights to understand and optimize reservoir response. The process involves: (1) acquiring and managing data in large volumes, of different varieties, and at high velocities, and (2) using statistical techniques to discover hidden patterns of association and relationships in these large, complex, multivariate datasets. However, the subject remains a mystery to most petroleum engineers and geoscientists because of the statistics-heavy jargon and the use of complex algorithms. This course will provide an introduction to statistical modeling and data analytics for reservoir performance analysis by focusing on: (a) easy-to-understand descriptions of the commonly-used concepts and techniques, and (b) case studies demonstrating the value-added proposition for these methods.
    This course is on the application of statistics and data analytics for practitioners. As such, it strikes a judicious balance between statistical rigor and formalism and practical considerations regarding the fundamentals and applicability of various relevant concepts. Beginning with a foundational discussion of exploratory data analysis, probability distributions and linear regression modeling, the course focuses on fundamentals and practical examples of such key topics as: Multivariate data reduction and clustering, Machine learning for regression and classification(for developing data-driven input-output models from production data as an alternative to physics-based models), Proxy construction using experimental design (for building fast statistical surrogate models of reservoir performance from simulator outputs for history matching and uncertainty analysis) and Uncertainty quantification for performance forecasting. Data sets from the petroleum geosciences are extensively used to demonstrate the applicability of these techniques.

    Day 1

    Exploratory Data Analysis

    • Univariate Data
    • Bivariate Data
    • Multivariate Data
    • Fitting Distributions to Data
    • Other Properties of Distributions and Their Evaluation

    Regression Modeling and Analysis

    • Simple Linear Regression
    • Multiple Regression
    • Nonparametric Transformation and Regression
    • Field Application for Nonparametric Regression

    Day 2

    Multivariate Data Analysis

    • Principal Component Analysis
    • Cluster Analysis
    • Discriminant Analysis
    • Field Application: The Salt Creek Data Set

    Day 3

    Uncertainty Quantification

    • Uncertainty Characterization
    • Uncertainty Propagation
    • Uncertainty Importance Assessment
    • Moving Beyond Monte Carlo Simulation
    • Treatment of Model Uncertainty
    • Elements of a Good Uncertainty Analysis Study

    Day 4

    Experimental Design and Response Surface Analysis

    • General Concepts
    • Experimental Design
    • Metamodeling Techniques
    • An Illustration of Experimental Design and Response Surface Modeling
    • Field Application of Experimental Design and Response Surface Modeling

    Day 5

    Data-Driven Modeling and Performance Predictions

    • Introduction
    • Modeling Approaches
    • Computational Considerations
    • Unconventional Field Examples

    Discussion and Wrap-up

    • Key Takeaways
    • Final Thoughts

    Geoscientists, Engineers

    • Visualizing univariate, bivariate and multivariate data
    • Fitting simple and multiple linear regression models to observed data
    • Developing a non-parametric regression model from given data
    • Reducing data dimensionality with Principal Component Analysis
    • Grouping data with k-means and hierarchical clustering
    • Identifying classification boundary between clusters using discriminant analysis
    • Applying machine learning techniques (e.g., random forest, gradient boosting machine, support
    vector regression, kriging model) for predictive modeling
    • Generating decision rules with classification tree analysis
    • Translating model input uncertainty into uncertainty in model predictions using Monte Carlo
    simulation and analytical alternatives
    • Analyzing input-output dependencies from Monte-Carlo simulation results
    • Creating an experimental design and fitting a response surface to the results

    Upcoming Classes

    Set a training goal, and easily track your progress

    Customize your own learning journey and track your progress when you start using a defined learning path.

    In just few simple steps, you can customize your own learning journey in the discipline of your interest based on your immediate, intermediate and transitional goals. Once done, you can save it in NExTpert, the digital learning ecosystem, and track your progress.
    © 2024 SLB Limited. All rights reserved.