×
1
  • Class and Course

    Hands on Machine Learning for Geoscientists and Engineers

    The five-day in-person course will focus on imparting practical ML skills for geological and reservoir engineering applications. Utilizing Python as the programming language, participants will be exposed to a comprehensive curriculum that covers exploratory data analysis, data preparation for modelling, and the application of fundamental ML concepts to real-world industry scenarios.

     

    In our daily class, we follow a three-part structure. We begin each session with a review of fundamental concepts, ensuring a strong foundation of knowledge. Next, we dive into live coding demos where you actively participate, experiencing hands-on learning as we code together. Finally, we culminate each session with guided exercises that provide valuable practical experience, focusing on real-world geological and engineering tasks and datasets. Get ready for an immersive learning journey that combines theory, application, and exploration in the field of ML for geoscientists and engineers.

    Hands-on Activities

    • Volumetric calculations with NumPy 
    • Formation Evaluation and EDA with Pandas 
    • Type well analysis with Pandas 
    • Well log prediction 
    • Predicting cumulative production
    • Facies analysis and clustering 
    • Production trends prediction using clustering analysis
    • 3D Facies modelling using ML
    • CO2 emissions prediction (Time series)




    Introduction

    • What is Machine Learning (ML)?
    • Examples of ML applications in geosciences and reservoir engineering

     

    Python crash course

    • Python libraries commonly used in ML
    • Variables, data types and basic operations
    • List, dictionaries, and loops
    • Functions

     

    NumPy

    • Filtering
    • Indexing
    • Slicing

    Exploratory Data Analysis (EDA)

    • Importance of data preprocessing and cleaning
    • Feature engineering: extracting meaningful features from data

     

    Pandas

    • Data cleaning
    • Data manipulation
    • Data visualization

    ML Overview

    • Types of ML tasks
    • ML workflow: data splitting, model training, validation, and evaluation
    • Model validation techniques: cross-validation
    • Understanding model errors and the bias-variance trade-off
    • Learning curves: assessing model performance

     

    ML for Regression

    • Fundamental algorithms
    • Cross Validation
    • Feature importance: SHAP values

    ML for Clustering

    • Handling high-dimensional data: the curse of dimensionality
    • Dimensionality reduction techniques: principal component analysis (PCA), UMAP
    • Interpreting and evaluating clustering results


    ML for Classification

    • Common metrics for classification: accuracy, precision, recall, F1-score
    • Confusion matrix
    • Grid Search and randomized grid search for hyperparameter optimization
    • Model evaluation and comparison


    The course is designed to accommodate those with no prior coding experience by introducing Python basics and guiding participants through hands-on exercises using geological and reservoir engineering datasets.


    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.

    Icon
    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.