{"id":{"repo_id":"houston","oai_identifier":"oai:uh-ir.tdl.org:10657/5824"},"canonical_url":"https://search.dev.ndltd.org/etd/houston/oai:uh-ir.tdl.org:10657/5824","repository":{"repo_id":"houston","name":"University of Houston","base_url":"https://uh-ir.tdl.org/server/oai/request"},"display":{"title":"Application of Data Analytics to Prediction of Initial Production in Tight Oil Reservoir","abstract":"The main objective of this study is to develop a quick predictive tool to forecast IP for wells in LT reservoir in the three fields J, K and N. Data includes the petrophysical properties, completion history, lab and field measurements (PVT, pressure transient test, production and pressure data). Missing pressure data is handled by pressure versus time correlation corresponding to the drive mechanisms in the reservoir. Thirty well samples with 39 possibly correlated parameters have been analyzed and transformed by principal component analysis (PCA) to construct a vector space of 29 orthogonal components. Then, the scores of the components are used for linear regression to develop a prediction model for IP. After analyzing transforming data, two methods of picking components have been tested: Method (1) picking the first 10 components and Method (2) picking the 10 components most correlated to IP. Method (2) yields a better prediction model with an R2 equal to 0.76 (while method (1) has an R2 equal to 0.5). Robustness of the prediction model has been tested by reducing the data size from 30 to 25 samples. The reduced sample set generates a less accurate prediction during the blind test (only one out of seven testing wells falls within the tolerance range). Some uncertainties for the model have also been addressed. Reservoir structure is not described in detail. In addition, drilling data and details of perforation are not considered in the data base. Operation aspects are not considered in this approach at this time.","abstract_html":"The main objective of this study is to develop a quick predictive tool to forecast IP for wells in LT reservoir in the three fields J, K and N. Data includes the petrophysical properties, completion history, lab and field measurements (PVT, pressure transient test, production and pressure data). Missing pressure data is handled by pressure versus time correlation corresponding to the drive mechanisms in the reservoir. Thirty well samples with 39 possibly correlated parameters have been analyzed and transformed by principal component analysis (PCA) to construct a vector space of 29 orthogonal components. Then, the scores of the components are used for linear regression to develop a prediction model for IP. After analyzing transforming data, two methods of picking components have been tested: Method (1) picking the first 10 components and Method (2) picking the 10 components most correlated to IP. Method (2) yields a better prediction model with an R2 equal to 0.76 (while method (1) has an R2 equal to 0.5). Robustness of the prediction model has been tested by reducing the data size from 30 to 25 samples. The reduced sample set generates a less accurate prediction during the blind test (only one out of seven testing wells falls within the tolerance range). Some uncertainties for the model have also been addressed. Reservoir structure is not described in detail. In addition, drilling data and details of perforation are not considered in the data base. Operation aspects are not considered in this approach at this time.","abstract_has_math":false,"creators":["Tran, Nathan H."],"institution":"University of Houston","degree_name":"Master of Science in Petroleum Engineering","degree_level":"Masters","degree_discipline":"Petroleum Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Thakur, Ganesh C."],"committee_chairs":[],"committee_members":["Chawathe, Adwait","Qin, Guan"],"year":2018,"date_issued":"2018-12","date_published":"2018-12","updated_at":"2026-07-24T02:33:01Z","subjects":["Data analytics","Initial Production","Tight oil","Petroleum engineering","Reservoir management"],"languages":["eng"],"rights":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10657/5824","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Thakur, Ganesh C."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Chawathe, Adwait","Qin, Guan"]},{"key":"dc:creator","label":"Author","values":["Tran, Nathan H."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-01-07T03:38:54Z"]},{"key":"dc:date.issued","label":"Date","values":["2018-12"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Petroleum Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"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":["Data analytics","Initial Production","Tight oil","Petroleum engineering","Reservoir management"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10657/5824"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The main objective of this study is to develop a quick predictive tool to forecast IP for wells in LT reservoir in the three fields J, K and N. Data includes the petrophysical properties, completion history, lab and field measurements (PVT, pressure transient test, production and pressure data). Missing pressure data is handled by pressure versus time correlation corresponding to the drive mechanisms in the reservoir. Thirty well samples with 39 possibly correlated parameters have been analyzed and transformed by principal component analysis (PCA) to construct a vector space of 29 orthogonal components. Then, the scores of the components are used for linear regression to develop a prediction model for IP. After analyzing transforming data, two methods of picking components have been tested: Method (1) picking the first 10 components and Method (2) picking the 10 components most correlated to IP. Method (2) yields a better prediction model with an R2 equal to 0.76 (while method (1) has an R2 equal to 0.5). Robustness of the prediction model has been tested by reducing the data size from 30 to 25 samples. The reduced sample set generates a less accurate prediction during the blind test (only one out of seven testing wells falls within the tolerance range). Some uncertainties for the model have also been addressed. Reservoir structure is not described in detail. In addition, drilling data and details of perforation are not considered in the data base. Operation aspects are not considered in this approach at this time."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Application of Data Analytics to Prediction of Initial Production in Tight Oil Reservoir"]}]}],"canonical_facts":{"dc:contributor.advisor":["Thakur, Ganesh C."],"dc:contributor.committeemember":["Chawathe, Adwait","Qin, Guan"],"dc:creator":["Tran, Nathan H."],"dc:date.accessioned":["2020-01-07T03:38:54Z"],"dc:date.issued":["2018-12"],"dc:description.abstract":["The main objective of this study is to develop a quick predictive tool to forecast IP for wells in LT reservoir in the three fields J, K and N. Data includes the petrophysical properties, completion history, lab and field measurements (PVT, pressure transient test, production and pressure data). Missing pressure data is handled by pressure versus time correlation corresponding to the drive mechanisms in the reservoir. Thirty well samples with 39 possibly correlated parameters have been analyzed and transformed by principal component analysis (PCA) to construct a vector space of 29 orthogonal components. Then, the scores of the components are used for linear regression to develop a prediction model for IP. After analyzing transforming data, two methods of picking components have been tested: Method (1) picking the first 10 components and Method (2) picking the 10 components most correlated to IP. Method (2) yields a better prediction model with an R2 equal to 0.76 (while method (1) has an R2 equal to 0.5). Robustness of the prediction model has been tested by reducing the data size from 30 to 25 samples. The reduced sample set generates a less accurate prediction during the blind test (only one out of seven testing wells falls within the tolerance range). Some uncertainties for the model have also been addressed. Reservoir structure is not described in detail. In addition, drilling data and details of perforation are not considered in the data base. Operation aspects are not considered in this approach at this time."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10657/5824"],"dc:language.iso":["eng"],"dc:rights":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."],"dc:subject":["Data analytics","Initial Production","Tight oil","Petroleum engineering","Reservoir management"],"dc:title":["Application of Data Analytics to Prediction of Initial Production in Tight Oil Reservoir"],"thesis:degree_discipline":["Petroleum Engineering"],"thesis:degree_level":["Masters"],"thesis:degree_name":["Master of Science in Petroleum Engineering"],"thesis:institution_name":["University of Houston"]},"updated_at":"2026-07-24T02:33:01Z"}