is now open for the Artificial Intelligence and Big Data Technical Meeting 2020,
sponsored by the EAGE Local Chapter Houston. Florian Basier
, Senior Product Developer at Emerson E&P Software, will present a paper, "Accounting for ML Weaknesses to Design Better Neural Networks for Petrophysics" as part of this one-day technical meeting.
In recent years, Deep Learning has proven able to tackle difficult E&P problems,but is still to become an industry standard. On real datasets, challenges such as lack of data, poor distribution or the quality of training labels are reducing prediction accuracy, while networks errors are not correlated with confidence scores. In this paper, we propose a new approach to highlighting network errors, in order to allow petrophysicists to focus on these areas.The approach is illustrated on the challenge of grain size prediction from microresistivity data. It uses a Neural Network Ensemble of networks, each dedicated to one grain size category. Each network consists of a Multiple Input Multiple Output (MIMO) Network, allowing multiple data sources (such as microresistivity and GR) to train the networks even when data is missing. Combined with a sliding window mechanism, more than 60 different predictions are realized per depth sample, allowing a statistical treatment of these NN outputs. A prediction can be realized alongside an uncertainty curve, highlighting difficult areas for study by the interpreter.This approach combines Machine Learning prediction and uncertainty analysis to reshape, using deterministic methods, the “black box” predictions of the Neural Network. This provides a more accurate methodology than conventional Machine Learning, which is also aware of its own inaccuracies. It automates most of the interpretation work while highlighting areas where machine learning is not yet able to properly perform, allowing the user to focus on the problematic areas to provide a more precise interpretation.
Florian Basier works as a Senior R&D Product Developer in Emerson E&P Software Houston, assisting several teams with their Machine Learning needs. He has 10 years of experience in exploration and production, focusing mainly on modeling and automation. Before joining Paradigm in 2015, Florian worked for several E&P companies in France (Techsia, Total) and the US (Chevron, INT). He holds a MSc degree in Geomodeling and Computer Sciences from the National Superior School of Geology (ENSG) of Nancy, France, as well as a MSc degree in Petroleum Engineering from the National Polytechnics Institute of Lorraine (INPL) from Nancy, France.