{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-3691"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-3691","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Combining Machine Learning and Empirical Engineering Methods Towards Improving Oil Production Forecasting","abstract":"Current methods of production forecasting such as decline curve analysis (DCA) or numerical simulation require years of historical production data, and their accuracy is limited by the choice of model parameters. Unconventional resources have proven challenging to apply traditional methods of production forecasting because they lack long production histories and have extremely variable model parameters. This research proposes a data-driven alternative to reservoir simulation and production forecasting techniques. We create a proxy-well model for predicting cumulative oil production by selecting statistically significant well completion parameters and reservoir information as independent predictor variables in regression-based models. Then, principal component analysis (PCA) is applied to extract key features of a well’s time-rate production profile and is used to estimate cumulative oil production. The efficacy of models is examined on field data of over 400 wells in the Eagle Ford Shale in South Texas, supplied from an industry database. The results of this study can be used to help oil and gas companies determine the estimated ultimate recovery (EUR) of a well and in turn inform financial and operational decisions based on available production and well completion data.","abstract_html":"Current methods of production forecasting such as decline curve analysis (DCA) or numerical simulation require years of historical production data, and their accuracy is limited by the choice of model parameters. Unconventional resources have proven challenging to apply traditional methods of production forecasting because they lack long production histories and have extremely variable model parameters. This research proposes a data-driven alternative to reservoir simulation and production forecasting techniques. We create a proxy-well model for predicting cumulative oil production by selecting statistically significant well completion parameters and reservoir information as independent predictor variables in regression-based models. Then, principal component analysis (PCA) is applied to extract key features of a well’s time-rate production profile and is used to estimate cumulative oil production. The efficacy of models is examined on field data of over 400 wells in the Eagle Ford Shale in South Texas, supplied from an industry database. The results of this study can be used to help oil and gas companies determine the estimated ultimate recovery (EUR) of a well and in turn inform financial and operational decisions based on available production and well completion data.","abstract_has_math":false,"creators":["Allen, Andrew J"],"institution":null,"degree_name":"MS in Industrial Engineering","degree_level":null,"degree_discipline":"Industrial and Manufacturing Engineering","degree_department":null,"school":null,"contributors":["Roy Jafari Marandi","Industrial and Manufacturing Engineering","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:11:57Z","subjects":["Machine Learning","Shale Gas","Production Forecasting","Feature Extraction","Principal Components Analysis","Applied Statistics","Data Science","Geological Engineering","Industrial Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2020.119"],"render_values":[{"text":"10.15368/theses.2020.119","href":"https://doi.org/10.15368/theses.2020.119","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2223","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/2223","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-3691","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Roy Jafari Marandi","Industrial and Manufacturing Engineering","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Allen, Andrew J"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2020-07-21T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2020-07-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Industrial and Manufacturing Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Industrial Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine Learning","Shale Gas","Production Forecasting","Feature Extraction","Principal Components Analysis","Applied Statistics","Data Science","Geological Engineering","Industrial Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2223","10.15368/theses.2020.119"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Current methods of production forecasting such as decline curve analysis (DCA) or numerical simulation require years of historical production data, and their accuracy is limited by the choice of model parameters. Unconventional resources have proven challenging to apply traditional methods of production forecasting because they lack long production histories and have extremely variable model parameters. This research proposes a data-driven alternative to reservoir simulation and production forecasting techniques. We create a proxy-well model for predicting cumulative oil production by selecting statistically significant well completion parameters and reservoir information as independent predictor variables in regression-based models. Then, principal component analysis (PCA) is applied to extract key features of a well’s time-rate production profile and is used to estimate cumulative oil production. The efficacy of models is examined on field data of over 400 wells in the Eagle Ford Shale in South Texas, supplied from an industry database. The results of this study can be used to help oil and gas companies determine the estimated ultimate recovery (EUR) of a well and in turn inform financial and operational decisions based on available production and well completion data."]},{"key":"dc:title","label":"Title","values":["Combining Machine Learning and Empirical Engineering Methods Towards Improving Oil Production Forecasting"]}]}],"canonical_facts":{"dc:contributor":["Roy Jafari Marandi","Industrial and Manufacturing Engineering","College of Engineering"],"dc:creator":["Allen, Andrew J"],"dc:date.available":["2020-07-21T07:00:00Z"],"dc:date.created":["2020-07-01T07:00:00Z"],"dc:description.abstract":["Current methods of production forecasting such as decline curve analysis (DCA) or numerical simulation require years of historical production data, and their accuracy is limited by the choice of model parameters. Unconventional resources have proven challenging to apply traditional methods of production forecasting because they lack long production histories and have extremely variable model parameters. This research proposes a data-driven alternative to reservoir simulation and production forecasting techniques. We create a proxy-well model for predicting cumulative oil production by selecting statistically significant well completion parameters and reservoir information as independent predictor variables in regression-based models. Then, principal component analysis (PCA) is applied to extract key features of a well’s time-rate production profile and is used to estimate cumulative oil production. The efficacy of models is examined on field data of over 400 wells in the Eagle Ford Shale in South Texas, supplied from an industry database. The results of this study can be used to help oil and gas companies determine the estimated ultimate recovery (EUR) of a well and in turn inform financial and operational decisions based on available production and well completion data."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2223","10.15368/theses.2020.119"],"dc:subject":["Machine Learning","Shale Gas","Production Forecasting","Feature Extraction","Principal Components Analysis","Applied Statistics","Data Science","Geological Engineering","Industrial Engineering"],"dc:title":["Combining Machine Learning and Empirical Engineering Methods Towards Improving Oil Production Forecasting"],"thesis:degree_discipline":["Industrial and Manufacturing Engineering"],"thesis:degree_name":["MS in Industrial Engineering"]},"updated_at":"2026-11-19T07:11:57Z"}