Intro to Unstructured Data and Machine Learning in Oil and Gas
PLEASE register using Eventbrite as well as SPE: https://www.eventbrite.com/e/78492066885
This course is aimed at people without a background in machine learning, software engineering, or data science. The purpose of the course is to help people who are immersed in the oil and gas industry to gain a practical understanding of what unstructured data is, what value there is in it, how it can be utilized, and why this is now relevant. Much of unstructured data mining is based on machine learning, so this course also seeks to instill memorable intuitive understanding of machine learning. This course does not require any use of computers. The course consists of these segments:
1) The differences between structured and unstructured data will be explored, and emphasis will be placed on why unstructured data is crucial to firms in the oil and gas industry. The drastic inefficiencies created by mismanagement of unstructured data will be given context by the growth in private equity backing, the lower hydrocarbon price environment, the proliferation of data sources, and the aftermath of the big crew change.
2) Attendees will engage in an interactive simulation of a typical oil and gas workflow involving structured and unstructured data.
3) Incumbent solutions, including data file structuring projects and off-the-shelf enterprise search tools, will be considered. Each will be evaluated based on its ability to return accurate and relevant information to users in a useful format and at speeds that do not inhibit seamless operations.
4) Attendees will engage in an interactive simulation of each of the two typical incumbent solutions to handle unstructured data.
5) The basics of machine learning will be explained in simple and intuitive terms, including a few examples.
6) Attendees will engage in an interactive application of machine learning to solve a problem. This application will be a simulation not requiring the use of any electronics.
7) Three case studies will be explored showing results and highlighting value added of a new (to oil and gas) class of solution. The first study involved implementation of a tool to help workers navigate historical reports to extract knowledge to make better decisions in real time. The second study involved implementation of a tool to serve as a surrogate for a retiring subject matter expert so that less experienced employees could still get good answers to questions. The third case study has not been completed, yet, but it involves simply using a tool to automatically fill out missing fields in a database from data scattered across unstructured reports.
The Cannon Houston (Satellite Location)
675 Bering Drive Suite 200
Houston , Texas 77057