BEGIN:VCALENDAR VERSION:2.0 METHOD:PUBLISH PRODID:-//Tendenci - The Open Source AMS for Associations//Tendenci Codeba se MIMEDIR//EN BEGIN:VEVENT DESCRIPTION:--- This iCal file does *NOT* confirm registration.\r\nEvent d etails subject to change. ---\r\nhttps://www.spegcs.org/events/5916/\r\n\r \nEvent Title: Data Analytics as a key to digital transformation: Case Stu dies from the Energy Industry\r\nStart Date / Time: Nov 19, 2020 17:00 PM US/Central\r\nLocation: Virtual\r\nSpeaker: Prashant Mehrotra, Shane J. Pr ochnow\r\n \r\nThe Energy industry needs to constantly adapt to the quickl y changing business landscape. The companies are betting on digital transf ormation as a way to innovate and grow. This webinar event will feature tw o technical talks demonstrating data analytics as a key ingredient in deli vering improved productivity and higher efficiency. The talks will be fol lowed by a virtual networking opportunity.\r\nAbstract Case Study #1: \r\n Several years ago the analytic workflow Type-Curve Optimizing Geostatistic al Array (TOGA) was introduced in the industry to tie unconventional reser voir and well completion characteristics to historical production and make robust predictions of well performance. TOGA is built on a foundational g eologic framework and leveraging random forest machine learning optimizati on for subsurface data sets. Random forest methods are preferred for uncon ventional systems because they capture complex, multidimensional, and non- linear interactions in noisy databases. TOGA is part of a portfolio of oth er machine learning and physically-based reservoir engineering tools used by companies to reduce uncertainty in unconventional reservoir performance prediction. The workflow generates performance prediction maps by applyin g the random forest multivariate relationships to grids of the key reservo ir predictor variables. These production prediction maps are stacked to fo rm an array of locations that each have a unique expected production profi le through time. TOGA output may be used to calibrate existing type curve workflows, define reservoir sweet spots, establish reservoir continuity, a nd predict ultimate recovery. Data science and machine learning approaches have progressed the organization&rsquo\;s understanding of its assets, es pecially in the Permian Basin. Unconventional plays were once thought to b e relatively unpredictable, highly variable, and have little connection to reservoir properties. TOGA and other proprietary data analytic technologi es have enabled the identification of key reservoir performance drivers fo r each unconventional target zone under development.\r\n \r\nAbstract Case Study #2: \r\nIn this talk, we will showcase a pragmatic, value-focused, agile approach to the digital transformation of upstream oil and gas produ ction operations. We will discuss how this approach enables oil and gas co mpanies to deliver a set of &lsquo\;mutually reinforcing&rsquo\; data anal ytics solutions to transform their end-to-end workflows and unlock signifi cant value from their producing assets. To illustrate the impact of digita l solutions on production operations, we will highlight specific use cases that have delivered game-changing results in the production surveillance and optimization space. Finally, we will discuss some common pitfalls in A I-driven transformation in upstream oil and gas, and some recommendations for how companies can avoid these pitfalls.\r\n \r\n \r\n\r\n \r\n \r\n \r \n --- This iCal file does *NOT* confirm registration.Event details subjec t to change. ---\r\n\r\n--- By Tendenci - The Open Source AMS for Associat ions ---\r\n UID:uid5916@spegcs.org SUMMARY:Data Analytics as a key to digital transformation: Case Studies from the Energy Industry DTSTART:20201119T230000Z DTEND:20201120T003000Z CLASS:PUBLIC PRIORITY:5 DTSTAMP:20240328T201726Z TRANSP:OPAQUE SEQUENCE:0 LOCATION:Virtual X-ALT-DESC;FMTTYPE=text/html:
The Energy industry needs to constantly adapt to the quickly changing bus iness landscape. The companies are betting on digital transformation as a way to innovate and grow. This webinar event will feature two technical ta lks demonstrating data analytics as a key ingredient in delivering improve d productivity and higher efficiency. \; The talks will be followed by a virtual networking opportunity.
Abstract Case Study # 1: \;
S everal years ago \;the analytic workflow \;Ty pe-Curve Optimizing Geostatistical Array \;(TOGA) was introduced in the industry to tie unconventional reservoir and well completion charac teristics to historical production and make robust predictions of well per formance. TOGA is built on a foundational geologic framework and leveragin g random forest machine learning optimization for subsurface data sets. Ra ndom forest methods are preferred for unconventional systems because they capture complex, multidimensional, and non-linear interactions in noisy da tabases. TOGA is part of a portfolio of other machine learning and physica lly-based reservoir engineering tools used by companies to reduce uncertai nty in unconventional reservoir performance prediction. The workflow gener ates performance prediction maps by applying the random forest multivariat e relationships to grids of the key reservoir predictor variables. These p roduction prediction maps are stacked to form an array of locations that e ach have a unique expected production profile through time. TOGA output ma y be used to calibrate existing type curve workflows, define reservoir swe et spots, establish reservoir continuity, and predict ultimate recovery. D ata science and machine learning approaches have progressed the organizati on&rsquo\;s understanding of its assets, especially in the Permian Basin. Unconventional plays were once thought to be relatively unpredictable, hig hly variable, and have little connection to reservoir properties. TOGA and other proprietary data analytic technologies have enabled the identificat ion of key reservoir performance drivers for each unconventional target zo ne under development.
 \;
Abstract Case Study #2: \;
In this talk, we will showcase a pragmatic, value-focused, agile approach to the digital transformation of upstream oil and gas production operatio ns. We will discuss how this approach enables oil and gas companies to del iver a set of &lsquo\;mutually reinforcing&rsquo\; data analytics solution s to transform their end-to-end workflows and unlock significant value fro m their producing assets. To illustrate the impact of digital solutions on production operations, we will highlight specific use cases that have del ivered game-changing results in the production surveillance and optimizati on space. Finally, we will discuss some common pitfalls in AI-driven trans formation in upstream oil and gas, and some recommendations for how compan ies can avoid these pitfalls.
 \;
 \;
 \;
 \;
 \;
 \;