Hybrid Physics / Data Driven Approaches for Oil and Gas Applications

Dr. Srinath Madasu

Senior Technical Advisor-Data Analytics, Halliburton

Adjunct Faculty, Petroleum Engineering, University of Houston

The oil and gas industry faces challenges of real time data gathering, modeling, prediction and optimization across different applications such as exploration, drilling, fracturing, reservoir modeling and production. This talk demonstrates the capabilities of hybrid machine learning/data driven modeling and optimization by providing tools to the customers for modeling and optimization of important applications in oil and gas industry. These tools make the real time decision process easy and help answer critical questions.

You can build your own models: Why you don't need to be scared of doing your own data science

Keith Moore, Director of Product Management, SparkCognition

There are two ends of the "AI" spectrum that are often presented: AI is going to solve the world's problems one slide deck at a time OR a PhD will give you a "quick" run-through of a 4-hour deep learning tutorial. In this session, we aim to land right in the middle – how to set up problems, how to analyze and interpret your data, and finally, how to build models that can drive business value without ever needing to know Python or R.