SPE Online Education
AI/ML Drilling Systems Need Timely Trusted Data to Deliver Trusted Results
Recorded On: 02/19/2020
Real-time data now represents a growing stream of scores of channels of digital data being fed concurrently to numerous receiving entities in the operator's remote monitoring amenities, at contractor centers and other facilities. Analytics are applied to data channels to signal or predict deviations from expected readings that require attention. For such systems to work effectively and reliably the input data must be trustworthy.
Establishing trust in a digital, i.e. binary, manner requires more rigor than what would be performed by a human observer. The boundary conditions for trust must be codified into rules that are grouped in a policy suitable for each data stream. Such conditions could include e.g. temperature range for a sensor outside of which readings are invalid.
The standards-based transmittals of WITSML data can be augmented with Data Assurance that codifies the rules that have established each data sample’s “pass” or “fail” status. To avoid cluttering the transmission channels, samples are transmitted with a blank Data Assurance field if the relevant policy was satisfied; the metadata indicating the rule or rules that were failed and the policy they are attached to are sent only with samples that failed. This information can be ingested by automated analytical tools.
This webinars is categorized under the Data Science and Engineering Analytics Discipline.
All content contained within this webinar is copyrighted by Jay Hollingsworth and its use and/or reproduction outside the portal requires express permission from Jay Hollingsworth.
Chief Technology Officer, Energistics
Jay Hollingsworth is currently Chief Technology Officer for Energistics. In this role, he is responsible for the technical adequacy of the standards stewarded by the organization, including WITSML, PRODML, and RESQML among others.
Jay has a BS plus post-graduate studies in Chemical Engineering at Tulane University in New Orleans. In addition, he attended graduate school in Computer Science at University of Texas in Dallas. As his career advanced as an Environmental and Process Engineer, he focused on technical computing – first as a consultant and then for 20 years at Mobil Oil. At Mobil he was responsible for the data model of their FINDER global master data store and the suite of engineering applications in global use. After leaving ExxonMobil, he spent time in Landmark’s data modeling group before settling at Schlumberger. He spent 10 years at Schlumberger where he was responsible for the data modeling group and was the Portfolio manager for the Seabed database technology. After Schlumberger, he was an Industry Principal at Oracle, focusing on oil & gas solutions.
Jay is active in numerous industry organizations, including APSG, ISO, SPE and SEG. He was a Technical Editor of the SPE Microcomputer Journal and is currently on the Board of the SPE Digital Energy Technical Section. He was a long-time member of the Board of Directors of PPDM and served as past president of APSG.
SPE Webinars are FREE to members courtesy of the