Petroleum Data Analytics and Machine Learning

Catalog description

Credits 3. 3 Lecture Hours. Data analytics suitable for petroleum engineers and geoscientists; emphasis on implementation of data-driven methods on certain types of subsurface data; creation of data-driven workflows and application to subsurface data generated during petroleum engineering and geoscience operations; study of case studies with an emphasis on the use of supervised learning, classification and regression, unsupervised learning, transformations, clustering and feature extraction, and neural networks using open-source Python computational platforms; exploration of the basics of machine learning, data science and data analysis and their applications to petroleum engineering and geoscience. Prerequisite: PETE 301 or GEOP 361 , or equivalent; graduate classification; or approval of instructor.