Occurred Monday, 1 August Wednesday, 31 August 2022, 8:00 a.m.–5:00 p.m.  |  Virtual Short Course via Zoom (Tulsa, Oklahoma time)

short course image
 
Who Should Attend
This course is designed for geology, geophysics, petroleum engineering, and mineral resources exploration and development professionals and students interested in strengthening their knowledge of Python programming and learning about its applications to Artificial Intelligence (Machine Learning and Deep Learning).
Objectives

By the end of the course, participants should be able to:

  • Use the primary functionalities of Python and selected packages of the Python language (Numpy / SciPy / Pandas / Matplotlib / Seaborn), through a project in Google Colab
  • Apply the basic concepts of Artificial Intelligence and primary Artificial Intelligence algorithms, particularly in the areas of Machine Learning and Deep Learning applied to geoscientific data (electrical well logs, seismic, well production data, and geochemical data of minerals).
  • Apply geoscientific data analysis and visualization techniques using Python libraries
  • Interpret output obtained by the prediction models
  • Use libraries for Machine Learning (Scikit-Learn) and Deep Learning (Keras, TensorFlow and PyTorch)
Course Content

Artificial Intelligence for Oil and Gas Using Python equips participants with the theoretical and practical knowledge needed to apply Machine Learning and Deep Learning concepts to the fields of geosciences and engineering.

Machine Learning is a subfield of Artificial Intelligence, which is based on trying to imitate the actions of human beings through the training of algorithms. This branch of Data Science is booming in various areas of geosciences, including electrical well log interpretation, reservoir characterization, seismic interpretation, identification of areas with high mining potential, among others.

Deep Learning focuses on the use of neural networks and applying the "back-propagation" method to adjust errors resulting from different iterations, and, when enough data is available, to obtain results far superior to those obtained by "classical" learning algorithms in Machine Learning.

This course will allow participants to apply the knowledge and algorithms learned immediately, both in their research, as well as in their professional career.

Course Format

Artificial Intelligence for Oil and Gas Using Python includes four self-paced independent study modules, along with three interactive working sessions with the instructor.

The format allows participants to work at their own pace and to reach out to the instructor for support throughout the week and during the live sessions.

Course modules will be available for viewing on the website from August 1- 31, 2022. Live sessions take place over three Saturdays, on August 6, 13 and 27, from 8 a.m. – 12 p.m. CDT/COT (GMT -5).

Course modules will be delivered in English, and the instructor will conduct working sessions in English and Spanish, accommodating participants’ preference.

Course Modules
Session 1: Python Basics
  • Types of Data and Data Management
  • Definition and Execution of Functions
  • Primary Python Libraries:
    • Numpy
    • SciPy
    • Pandas
    • Matplotlib
    • Seaborn
  • Exploratory Data Analysis
  • Exercises:
    • Plot a geochemical dataset
    • Visualize, organize, and analyze an oil/gas production dataset
Session 2: Applied Python in Geology and Geophysics

Wavelet (Ricker) in time and frequency

  • Well logs
  • Display Geospatial Data (Mineral information)
  • Seismic volume load
  • Post-Stack seismic attributes calculation
  • Exercises:
    • Generate a Ormsby, and Butterworth wavelet (Time and Domain)
    • Calculate Coherence Attributes using Python
Session 3: Machine Learning
  • Supervised vs. Unsupervised
  • Regression:
    • Lineal
    • Logistic Regression
  • Classification
    • KNN
    • SVM
  • Clustering
    • K- Means
    • Decision Trees
  • Dimension Reduction
    • Principal Component Analysis (PCA)
  • Exercises:
    • Facies Classification of Well Logs
    • Use Regression Methods to forecast production in an oil well
Session 4: Deep Learning
  • Programming a Neural Network (step by step)
  • Application of Neural Networks for facies prediction
  • Neural Networks for:
    • Missing Well logs
    • Production forecast of an oil well
  • Use CNN for object detection in seismic images
  • Exercises:
    • Use CNN to predict salt bodies in a seismic dataset
    • Classify 3D Seismic Facies using Deep Neural Networks
Working Session Schedule

August 6
Python Basics & Applied Python

August 13
Machine Learning

August 27
Deep Learning

Course Study Modules

These recordings are only available to the registered participants of the course. Click on the picture or the title of the video for viewing.

 
Roderick Perez Altamar
Laura Becerra Technical Professional - ACGGP
Diana Ruiz Vásquez AAPG Latin America & Caribbean Region Events Coordinator

What Can I Do?

Add Item

Enter Notes:
 
* You must be logged in to name and customize your collection.
Recommend Recommend
Printable Version Printable Version Email to a friend Email to a friend

About Us

AAPG Non-endorsement Policy

The American Association of Petroleum Geologists (AAPG) does not endorse or recommend any products and services that may be cited, used or discussed in AAPG publications or in presentations at events associated with AAPG.