Course will be held via Zoom: 10–12 November 2020, 6:30 pm–10:00 pm (CDT)
The course will focus on a Machine Learning workflow in the upstream Oil and Gas domain to generate synthetic Gamma-Ray Logs by applying Artificial Intelligence (AI) Techniques and then learning the various aspects of deploying this workflow in an end-to-end solution that a Geoscientist can use.
Gamma ray logs are recorded in virtually every oil and gas well drilled. Shales are often more radioactive than reservoir rocks such as sandstone, limestone. The shape of the gamma ray log with respect to depth assists in correlating layers from one well to another. While planning the drilling operation of a new well, synthetic Gamma Ray is very useful in determining Rock Type and formations, so that the Drilling Engineer can plan drilling parameters like RPM, WOB, Mud weight etc. in a better way. This improves the efficiency of the Drilling Operation, creates safe environment and potentially saves huge costs.
The course begins with an introduction to the various phases of designing and implementing a Machine Learning based solution. It then goes into the details of each phase describing the people skills, tools, techniques and methodologies required to complete the tasks successfully. The details of the Synthetic Gamma ray Logs prediction use case are then discussed with the attendees. This is followed by a quick primer on Data Analytics and Python so that the attendees can work on the instructor guided hands-on tutorial to build the machine learning model using python. The next part of the course discusses the various aspects of operationalizing the Machine Learning model as a workflow solution that an end-user can use. The last part of the course presents a real-life case-study including the demo of a complete end-to-end workflow starting from data ingestion and ending with an operationalized solution.
Why This Course Stands Out:
Focus on using Machine Learning to solve real Oil and Gas problems and convert these into end-user centric solutions. This is a comprehensive course covering not only Machine Learning but also the various other aspects of building and deploying a successful ML based solution including Data Ingestion, Pre-processing, Data Lake, Machine Learning and operationalization.
- Identify use case and pain points
- Identify and collect the relevant data
- Quick Introduction to Machine Learning techniques and Python
- Build/Train and test the Machine Learning Model using Python
- Validation of the model results by Domain Experts
- Build solution and operationalize
- Demo of a working end-to-end Machine Learning solution
- Open Discussion