\"Wettability alteration with surfactants has been widely applied to improve oil recovery in carbonate reservoirs. An effective surfactant huff-puff application design requires comprehensive guidelines about where, how, and when this method could be applied. Besides, traditional methods to design an effective application and optimize surfactant performance are dependent on extensive experiments and are time-consuming. This study is to assist in the design of surfactant huff-puff via statistical methods and machine learning techniques.
In this study, a dataset including 402 effective surfactant imbibition tests is established by collecting information from nearly 50 publications. The dataset provides a foundation for further data analysis. Descriptive statistical analysis methods are used to establish comprehensive application guidelines for surfactant huff-puff treatments. A Random Forest (RF) model was built to predict surfactant performance. Based on RF model, Shapley additive explanations approach was applied to obtain new insights to promote the understanding of wettability alteration with surfactants. Also, a new procedure integrating RF model with Powell’s method was built to optimize surfactant performance. Besides, principal component analysis and hierarchical clustering algorithm was applied to uncover the hidden pattens embedded in global surfactant huff-puff treatments. The analog reasoning was utilized to provide valuable experiences for designing surfactant treatments and predicting performance for new candidate projects. Finally, an adaptive, offline, and friendly desktop application was developed to facilitate data analysis and support decision making\"--Abstract, p. iv
","abstract_html":"<p>"Wettability alteration with surfactants has been widely applied to improve oil recovery in carbonate reservoirs. An effective surfactant huff-puff application design requires comprehensive guidelines about where, how, and when this method could be applied. Besides, traditional methods to design an effective application and optimize surfactant performance are dependent on extensive experiments and are time-consuming. This study is to assist in the design of surfactant huff-puff via statistical methods and machine learning techniques.</p> <p>In this study, a dataset including 402 effective surfactant imbibition tests is established by collecting information from nearly 50 publications. The dataset provides a foundation for further data analysis. Descriptive statistical analysis methods are used to establish comprehensive application guidelines for surfactant huff-puff treatments. A Random Forest (RF) model was built to predict surfactant performance. Based on RF model, Shapley additive explanations approach was applied to obtain new insights to promote the understanding of wettability alteration with surfactants. Also, a new procedure integrating RF model with Powell’s method was built to optimize surfactant performance. Besides, principal component analysis and hierarchical clustering algorithm was applied to uncover the hidden pattens embedded in global surfactant huff-puff treatments. The analog reasoning was utilized to provide valuable experiences for designing surfactant treatments and predicting performance for new candidate projects. Finally, an adaptive, offline, and friendly desktop application was developed to facilitate data analysis and support decision making"--Abstract, p. iv</p>","abstract_has_math":false,"creators":["Yao, Ya"],"institution":"Missouri University of Science and Technology","degree_name":"Ph. D. in Petroleum Engineering","degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-07-24T03:18:26Z","subjects":["Chemical Engineering","Engineering","Petroleum Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://scholarsmine.mst.edu/doctoral_dissertations/3270","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Yao, Ya"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:type","label":"Dc Type","values":["Dissertation - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph. D. in Petroleum Engineering"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Missouri University of Science and Technology"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Chemical Engineering","Engineering","Petroleum Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarsmine.mst.edu/doctoral_dissertations/3270"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["\"Wettability alteration with surfactants has been widely applied to improve oil recovery in carbonate reservoirs. An effective surfactant huff-puff application design requires comprehensive guidelines about where, how, and when this method could be applied. Besides, traditional methods to design an effective application and optimize surfactant performance are dependent on extensive experiments and are time-consuming. This study is to assist in the design of surfactant huff-puff via statistical methods and machine learning techniques.
In this study, a dataset including 402 effective surfactant imbibition tests is established by collecting information from nearly 50 publications. The dataset provides a foundation for further data analysis. Descriptive statistical analysis methods are used to establish comprehensive application guidelines for surfactant huff-puff treatments. A Random Forest (RF) model was built to predict surfactant performance. Based on RF model, Shapley additive explanations approach was applied to obtain new insights to promote the understanding of wettability alteration with surfactants. Also, a new procedure integrating RF model with Powell’s method was built to optimize surfactant performance. Besides, principal component analysis and hierarchical clustering algorithm was applied to uncover the hidden pattens embedded in global surfactant huff-puff treatments. The analog reasoning was utilized to provide valuable experiences for designing surfactant treatments and predicting performance for new candidate projects. Finally, an adaptive, offline, and friendly desktop application was developed to facilitate data analysis and support decision making\"--Abstract, p. iv
"]},{"key":"dc:title","label":"Title","values":["Data Analytics of Wettability Alteration with Surfactants in Carbonate Reservoirs"]}]}],"canonical_facts":{"dc:creator":["Yao, Ya"],"dc:description.abstract":["\"Wettability alteration with surfactants has been widely applied to improve oil recovery in carbonate reservoirs. An effective surfactant huff-puff application design requires comprehensive guidelines about where, how, and when this method could be applied. Besides, traditional methods to design an effective application and optimize surfactant performance are dependent on extensive experiments and are time-consuming. This study is to assist in the design of surfactant huff-puff via statistical methods and machine learning techniques.
In this study, a dataset including 402 effective surfactant imbibition tests is established by collecting information from nearly 50 publications. The dataset provides a foundation for further data analysis. Descriptive statistical analysis methods are used to establish comprehensive application guidelines for surfactant huff-puff treatments. A Random Forest (RF) model was built to predict surfactant performance. Based on RF model, Shapley additive explanations approach was applied to obtain new insights to promote the understanding of wettability alteration with surfactants. Also, a new procedure integrating RF model with Powell’s method was built to optimize surfactant performance. Besides, principal component analysis and hierarchical clustering algorithm was applied to uncover the hidden pattens embedded in global surfactant huff-puff treatments. The analog reasoning was utilized to provide valuable experiences for designing surfactant treatments and predicting performance for new candidate projects. Finally, an adaptive, offline, and friendly desktop application was developed to facilitate data analysis and support decision making\"--Abstract, p. iv
"],"dc:identifier":["https://scholarsmine.mst.edu/doctoral_dissertations/3270"],"dc:subject":["Chemical Engineering","Engineering","Petroleum Engineering"],"dc:title":["Data Analytics of Wettability Alteration with Surfactants in Carbonate Reservoirs"],"dc:type":["Dissertation - Open Access"],"thesis:degree_name":["Ph. D. in Petroleum Engineering"],"thesis:institution_name":["Missouri University of Science and Technology"]},"updated_at":"2026-07-24T03:18:26Z"}