BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Denver SPE - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://denverspe.org
X-WR-CALDESC:Events for Denver SPE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:20240310T090000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:20241103T080000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:20250309T090000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:20251102T080000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:20260308T090000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:20261101T080000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Denver:20251016T160000
DTEND;TZID=America/Denver:20251016T180000
DTSTAMP:20260613T233524
CREATED:20250911T163428Z
LAST-MODIFIED:20250911T163740Z
UID:5550-1760630400-1760637600@denverspe.org
SUMMARY:SPE Denver Technical Happy Hour - October 2025
DESCRIPTION:Host: Society of Petroleum Engineers\, Denver SectionEvent: October 2025 Technical Happy HourTime: October 16th\, 4-6 (HH begins at 4\, Talk at 430\, Social until 6)Location: Liberty Energy\, 950 17th St\, Suite 2400\, Denver\, CO 80202Sponsor: LibertyStudy Group Category: CompletionsSpeaker: Jessica Iriarte\, General Completions Manager\, Corva \nTitle: Enhancing Operational Awareness in Haynesville Operations with Advanced Stage-Categorization Models \n  \nAbstract: \n  \nThis study presents an AI-driven approach to stage categorization for hydraulic\nfracturing operations\, addressing deviations from pumping designs that result in\nincreased costs\, reduced efficiency\, and operational unpredictability. The dataset\nincludes 1\,595 stages\, of which 970 exhibited at least one issue such as mid-stage\nshutdowns\, screen outs\, and rate reductions. The objective is to improve\noperational decision-making by automating stage categorization\, distinguishing\nbetween surface and subsurface issues\, and lay the foundation for future\npredictive machine learning models to anticipate trouble stages. \n  \n  \nThe stage categorization model evolved through eight iterations to refine detection\nof operational issues and differentiate between surface- and subsurface-driven\nproblems. Version 1 implemented basic pressure slope algorithms\, while Version 2\nimproved accuracy with steady-rate pressure checks. Version 3 expanded\ndiagnostic capabilities by incorporating proppant and chemical concentrations.\nVersion 4 adjusted the search for specific activities like pad for ball-seat stages\,\nflush\, and pressure test. Version 5 introduced dynamic thresholds to account for\nfriction effects from varying casing sizes and stage measured depths. Version 6\noptimized the overall model\, removing factors that reduced Precision\, resulting in\nsignificantly improved performance. Version 7 improved Clean Sweep remediation\ndetection using stage activities\, such as flushes\, to determine the most accurate\nperiod to scan. Screen outs were updated based on a sensitivity analysis around\nthe required pressure per minute reading. Finally\, in Version 8 logic was added to\nconnect subsequent subsurface-related issues to one that occurred earlier in the\nstage’s progression. \n  \n  \nThe finalized stage categorization model analyzes time-series data\, including\npressure\, rate\, proppant and chemical concentration\, and wellbore design\nparameters\, capturing key variables affecting treatment behavior. It achieved 98%\naccuracy and 88% precision in identifying issues like mid-stage shutdowns and \nscreen outs. By distinguishing surface from subsurface problems\, operators can\noptimize resource allocation and treatment designs. The study also revealed\nsignificant correlations between operational challenges and geological variability\,\nhighlighting the importance of integrating rock and operational data. These\ninsights facilitate improved treatment consistency\, reduced costs\, and enhanced\ndecision-making. \n  \nBio: \n  \nJessica Iriarte is the General Manager of Completions at Corva. Jessica is a data\nscience and energy leader\, has held various leadership positions in oil and gas\,\nincluding international experience in data\, research\, and operations. Jessica is an\ninventor\, a distinguished lecturer\, and has 17 publications with SPE\, JPT\, and URTeC.\nJessica holds a Bachelor of Science degree in Petroleum Engineering from\nUniversidad del Zulia and a Master of Science degree in Petroleum Engineering from\nColorado School of Mines. \n  \nRegister Here
URL:https://denverspe.org/event/spe-denver-technical-happy-hour-october-2025/
LOCATION:Liberty Energy\, 950 17th St Suite #24\, Denver\, CO\, 80202\, United States
CATEGORIES:Technical
ATTACH;FMTTYPE=image/png:https://denverspe.org/wp-content/uploads/2025/09/SPE_TechProg_LinkedIn-23.png
ORGANIZER;CN="SPE Denver Section":MAILTO:denversection@spemail.org
END:VEVENT
END:VCALENDAR