The main skill is a working understanding and appreciation of analytical methodologies and statistical, data-driven techniques and soft-computing approaches to turn raw data into actionable knowledge.
The main problem is to gather hidden knowledge from the disparate and siloed Big Data sets traditionally interpreted. To identify patterns and marry interpretation to data-driven models to solve critical business problems, predict failures in facilities, optimize processes and maximize maintenance schedules.
The course starts with a review of historical digital oilfields and the analytical methodologies implemented to solve upstream business issues for surface facilities. We cover equipment and process management workflows identifying different platforms and datasets to address business issues. We detail building models from exploratory data analysis through operationalizing predictive models. We cover flow assurance issues and well/pipeline integrity case studies and then consider soft-computing techniques in drilling optimization and completions strategies in conventional and unconventional reservoirs. We close with several case studies for asset performance analysis and Integrated Planning as well as IIOT opportunities for structured/unstructured data.