Course Description

In this course, we will teach participants various machine learning techniques and tools necessary to train, test, and apply a model from scratch. We will use open source and easy to learn language such as Python to build workflows using different libraries (pre-built code samples) to perform various tasks in an interactive session. In other words, we make the entire coding experience and set up easy, pleasant, and straightforward. 

There is no need to have any experience in machine learning, data science, linear algebra, or coding. We will teach every step of the way, anyone in the organization who has the slightest passion for implementing AI, ML and deciphering essential information from the data is welcome to attend. We will also accommodate those who have a higher level of experience with implementing AI and ML using python.

Course Objectives

By the end of this course, participant will be able to:

• Understand machine learning fundamentals and its applications in the oil and gas industry.
• Use Python for implementing machine learning workflows and data analysis.
• Manipulate and visualize data using Pandas, Matplotlib, Seaborn, Plotly, and Cufflinks.
• Preprocess data for machine learning, handling outliers, missing data, and scaling.
• Build and evaluate supervised machine learning models (linear regression, logistic regression, K-nearest neighbors, decision trees, random forests, support vector machines, neural networks).
• Apply dimensionality reduction and clustering algorithms for unsupervised learning.
• Select and fine-tune machine learning models using cross-validation and grid search.
• Solve oil and gas industry problems with machine learning (e.g., frac pump failure detection, rock properties prediction, pipeline leak detection).
• Analyze and interpret machine learning model results for subsurface decision-making.
• Work on customized exercises with real-world oil and gas datasets.
   

Who Can Benefit

• Reservoir Engineers
• Petroleum Engineers
• Geoscientists
• Field Engineers