{"id":{"repo_id":"houston","oai_identifier":"oai:uh-ir.tdl.org:10657/19854"},"canonical_url":"https://search.dev.ndltd.org/etd/houston/oai:uh-ir.tdl.org:10657/19854","repository":{"repo_id":"houston","name":"University of Houston","base_url":"https://uh-ir.tdl.org/server/oai/request"},"display":{"title":"Automated Estimation of ISIP and Friction Losses in Hydraulic Fracture Treatment Falloff Data","abstract":"A recent publication revealed a method to estimate wellbore and perforation friction loss and tortuosity friction loss from hydraulic fracture treatment falloff data. It illustrated friction loss estimations for 270 stages in 16 shale gas wells drilled from the same pad. The resulting estimates reflect a combination of formation and well completion variations. However, the effort required to analyze each falloff by hand compels a need to develop an automated estimation process. This work will automate the parameter estimation and provide additional insights derived from spatial analysis using the resulting estimates. This study investigates two approaches to automate ISIP and friction loss estimation, first, automating a deterministic approach published recently, and second, applying a statistical approach based on machine learning. We validate the algorithms by comparing them with previously analyzed data. We apply the automated deterministic algorithm on several hydraulic fracture stages from a field dataset to isolate its falloff data and estimate its ISIP and friction losses. We then use the data we generated from the deterministic approach to build a data-driven model that estimates ISIP and friction losses statistically using machine learning techniques. Finally, we apply the data-driven model to independent field data to test its performance. This study provides a consistent, efficient, and accurate approach to estimate ISIP and friction losses from hydraulic fracture treatment. The same analysis also can be applied to the early portion of the diagnostic fracture injection test (DFIT) data. Furthermore, this study eliminates human bias and the subjectivity that accompanies the manual selection of shut-in pressure and ISIP. Finally, this study opens the door for performing spatial and statistical analysis for field data from several different shale gas and tight oil well pads to understand the relationship between the parameters under investigation, the treatment specifications, and the rock properties.","abstract_html":"A recent publication revealed a method to estimate wellbore and perforation friction loss and tortuosity friction loss from hydraulic fracture treatment falloff data. It illustrated friction loss estimations for 270 stages in 16 shale gas wells drilled from the same pad. The resulting estimates reflect a combination of formation and well completion variations. However, the effort required to analyze each falloff by hand compels a need to develop an automated estimation process. This work will automate the parameter estimation and provide additional insights derived from spatial analysis using the resulting estimates. This study investigates two approaches to automate ISIP and friction loss estimation, first, automating a deterministic approach published recently, and second, applying a statistical approach based on machine learning. We validate the algorithms by comparing them with previously analyzed data. We apply the automated deterministic algorithm on several hydraulic fracture stages from a field dataset to isolate its falloff data and estimate its ISIP and friction losses. We then use the data we generated from the deterministic approach to build a data-driven model that estimates ISIP and friction losses statistically using machine learning techniques. Finally, we apply the data-driven model to independent field data to test its performance. This study provides a consistent, efficient, and accurate approach to estimate ISIP and friction losses from hydraulic fracture treatment. The same analysis also can be applied to the early portion of the diagnostic fracture injection test (DFIT) data. Furthermore, this study eliminates human bias and the subjectivity that accompanies the manual selection of shut-in pressure and ISIP. Finally, this study opens the door for performing spatial and statistical analysis for field data from several different shale gas and tight oil well pads to understand the relationship between the parameters under investigation, the treatment specifications, and the rock properties.","abstract_has_math":false,"creators":["Alwarda, Fahad Ahmed Qasim"],"institution":"University of Houston","degree_name":"Master of Science in Petroleum Engineering","degree_level":null,"degree_discipline":"Petroleum Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Economides, Christine","Lee, Dr. Kyung Jae"],"committee_chairs":[],"committee_members":["Nikolaou, Michael"],"year":2020,"date_issued":"2020-12","date_published":"2020-12","updated_at":"2026-07-24T02:33:01Z","subjects":["Computer science","Petroleum engineering","Mathematics"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10657/19854","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Economides, Christine","Lee, Dr. Kyung Jae"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Nikolaou, Michael"]},{"key":"dc:creator","label":"Author","values":["Alwarda, Fahad Ahmed Qasim"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-07-23T15:57:37Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-12"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Petroleum Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Petroleum Engineering"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Houston"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer science","Petroleum engineering","Mathematics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10657/19854"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["A recent publication revealed a method to estimate wellbore and perforation friction loss and tortuosity friction loss from hydraulic fracture treatment falloff data. It illustrated friction loss estimations for 270 stages in 16 shale gas wells drilled from the same pad. The resulting estimates reflect a combination of formation and well completion variations. However, the effort required to analyze each falloff by hand compels a need to develop an automated estimation process. This work will automate the parameter estimation and provide additional insights derived from spatial analysis using the resulting estimates. This study investigates two approaches to automate ISIP and friction loss estimation, first, automating a deterministic approach published recently, and second, applying a statistical approach based on machine learning. We validate the algorithms by comparing them with previously analyzed data. We apply the automated deterministic algorithm on several hydraulic fracture stages from a field dataset to isolate its falloff data and estimate its ISIP and friction losses. We then use the data we generated from the deterministic approach to build a data-driven model that estimates ISIP and friction losses statistically using machine learning techniques. Finally, we apply the data-driven model to independent field data to test its performance. This study provides a consistent, efficient, and accurate approach to estimate ISIP and friction losses from hydraulic fracture treatment. The same analysis also can be applied to the early portion of the diagnostic fracture injection test (DFIT) data. Furthermore, this study eliminates human bias and the subjectivity that accompanies the manual selection of shut-in pressure and ISIP. Finally, this study opens the door for performing spatial and statistical analysis for field data from several different shale gas and tight oil well pads to understand the relationship between the parameters under investigation, the treatment specifications, and the rock properties."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Automated Estimation of ISIP and Friction Losses in Hydraulic Fracture Treatment Falloff Data"]}]}],"canonical_facts":{"dc:contributor.advisor":["Economides, Christine","Lee, Dr. Kyung Jae"],"dc:contributor.committeemember":["Nikolaou, Michael"],"dc:creator":["Alwarda, Fahad Ahmed Qasim"],"dc:date.accessioned":["2025-07-23T15:57:37Z"],"dc:date.issued":["2020-12"],"dc:description.abstract":["A recent publication revealed a method to estimate wellbore and perforation friction loss and tortuosity friction loss from hydraulic fracture treatment falloff data. It illustrated friction loss estimations for 270 stages in 16 shale gas wells drilled from the same pad. The resulting estimates reflect a combination of formation and well completion variations. However, the effort required to analyze each falloff by hand compels a need to develop an automated estimation process. This work will automate the parameter estimation and provide additional insights derived from spatial analysis using the resulting estimates. This study investigates two approaches to automate ISIP and friction loss estimation, first, automating a deterministic approach published recently, and second, applying a statistical approach based on machine learning. We validate the algorithms by comparing them with previously analyzed data. We apply the automated deterministic algorithm on several hydraulic fracture stages from a field dataset to isolate its falloff data and estimate its ISIP and friction losses. We then use the data we generated from the deterministic approach to build a data-driven model that estimates ISIP and friction losses statistically using machine learning techniques. Finally, we apply the data-driven model to independent field data to test its performance. This study provides a consistent, efficient, and accurate approach to estimate ISIP and friction losses from hydraulic fracture treatment. The same analysis also can be applied to the early portion of the diagnostic fracture injection test (DFIT) data. Furthermore, this study eliminates human bias and the subjectivity that accompanies the manual selection of shut-in pressure and ISIP. Finally, this study opens the door for performing spatial and statistical analysis for field data from several different shale gas and tight oil well pads to understand the relationship between the parameters under investigation, the treatment specifications, and the rock properties."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10657/19854"],"dc:language.iso":["en"],"dc:subject":["Computer science","Petroleum engineering","Mathematics"],"dc:title":["Automated Estimation of ISIP and Friction Losses in Hydraulic Fracture Treatment Falloff Data"],"dc:type":["Thesis"],"thesis:degree_discipline":["Petroleum Engineering"],"thesis:degree_name":["Master of Science in Petroleum Engineering"],"thesis:institution_name":["University of Houston"]},"updated_at":"2026-07-24T02:33:01Z"}