Author: Samhita Shah
The results are in! Emerson’s Rock Type Classification (RTC) with Machine Learning has been announced as the winner of the 2019 Hart Energy Meritorious Awards for Engineering (MEA) Innovation in the category of Exploration/Geoscience. The MEA program recognizes new products and technologies that demonstrate innovation in concept, design and application.
“Our magazine and its predecessors have consistently honored technical innovation that allows our industry to overcome seemingly impossible challenges,” said Jennifer Presley, Executive Editor of E&P. “The Meritorious Awards for Engineering Innovation reflect the best of the best in technological advancement.”
The Rock Type Classification with Machine Learning application combines the latest innovations in geoscience, algorithms and statistical models to help oil and gas operators overcome the limitations of traditional methods for predicting facies and rock types from seismic data.
Earlier solutions deployed deterministic or stochastic seismic inversion methods to offer a first level approximation to a facies or rock type model. Unfortunately, such approaches suffer from non-uniqueness, lack the resolution required to accurately predict thin beds or intermediate-type facies, and frequently fail to model the high degree of heterogeneity that characterizes many oil and gas reservoirs.
To address these limitations, the Emerson Exploration & Production (E&P) Software team has developed a Supervised Machine Learning approach called Democratic Neural Network Association (DNNA). The method reconciles multiple data sets to predict facies away from the wellbore. It employs an “ensemble” of many neural networks running in parallel that simultaneously learn from the multi-resolution well bore and seismic data using different strategies and associations. This architecture minimizes the possibility of biasing. It includes a secondary training stage where seismic data is introduced away from the well bore and “voted” on for training set inclusion, to stabilize network training while preventing overlearning.
The outcome of this process is a probabilistic facies model description of the reservoir. It predicts the most probable facies distribution and associated maximum probability, and the probability relative to each facies.
This results in less guesswork when quantifying uncertainty in rock type distribution. Results are interactively generated in a 2D and 3D environment for in-depth analysis and are reservoir simulation ready. The outcome is critical for reservoir geologists and engineers to better understand reservoir behavior.
Once considered “nice-to-have technologies”, the sheer volume of well and seismic data that needs to be analyzed has made Machine Learning an effective approach for transformation and analysis of subsurface data. Automated Machine Learning produces outputs in minutes or hours rather than months or years.
And, since Machine Learning integrates data of different resolutions (core, wireline and seismic data) and different domains, it becomes a collaboration agent where geologists, reservoir engineers, and geophysicists can work together to ensure that disparate data is calibrated, and results validated. It is ideal for Cloud implementation.
To overcome your own seemingly impossible challenges in predicting facies and rock types and improve the certainty of your E&P decision making, visit the Rock Type Classification with Machine Learning section of the website.
From Jim: You can also connect and interact with other oil & gas E&P experts in the Oil & Gas group in the Emerson Exchange 365 community. And, if you’ll be in Houston, Texas for the May 6-9 Offshore Technology Conference (OTC), make sure to stop by the Emerson booth #2261 (sign up for a free exhibit pass) to see this application in action and speak with Emerson E&P experts.
