“What do you mean the model doesn’t use **INSERT PET GEOLOGIC VARIABLE HERE**?!” Anyone who’s built and reviewed enough machine learning models and SHAP values will instantly recognize the question above. The algorithm dropped some geologic variable in the feature selection process due to high correlation with another input geologic variable, and someone in the […]
Conference Presentations
Water, water everywhere: oil well water analysis with machine learning models to improve produced water forecasts in the Williston Basin: URTeC 2020 Novi Paper Summary
How often does an engineer dash off a simple oil well water analysis, doing something like applying a flat WOR to their oil prediction? It’s easy to ignore water, but unexpectedly high production, leading to more produced water, can damage well economics. In the worst cases, it can force shut-in if disposal capacity is full. […]
The Changing Impact of Oil Well Design Completions Through Time: URTeC 2020 Novi Paper Summary
“Upsizing well completions increase production 37.5%*!!!” Sure, but when? Where that asterisk lands will have a huge impact on the returns of oil well design completions. If it’s Peak Rate, that might shorten payback. If it’s EUR — now you might have a real valuable well. Oil and gas machine learning models can be trained […]
Building Unbiased Benchmarks with Machine Learning Oil and Gas Modeling: URTeC 2020 Novi Paper Summary
90% of American drivers say they’re better than average, and 90% of Shale focused Operators have “peer-leading” breakevens, returns and well production forecasts. Suuuure they do! How do you cut through Investor Relations fluff to identify top-performing operators to learn from, or underperformers to acquire? We will use machine learning to build unbiased benchmarks for […]