In the world of interior architectural paints, rheology, or the deformation and flow of a fluid, is one of the largest economic and development hurdles for paint formulators. To achieve maximum functionality, coverage, and economy of product, the rheology of the coating must be properly optimized, balancing performance while minimizing undesirable flow defects such as paint sagging or visible brush and roller marks; these visual imperfections are associated with the sag and leveling properties of the paint. Many researchers have attempted to develop a better understanding of sag and leveling, either by drawing correlations or through mathematical derivation; however, neither approach adequately predicts sag and leveling behavior. This provides the opportunity for machine learning to create a powerful model that utilizes formulation and rheological data and industry-standard tests to predict sag and leveling before the formulator creates the paint, reducing the resources necessary to optimize paint compared to a heuristic approach. Since little attention has been paid to the full rheological effects of sag and leveling, this approach also provides a first step in gaining new insight into the mechanisms behind this behavior.
","abstract_html":"<p>In the world of interior architectural paints, rheology, or the deformation and flow of a fluid, is one of the largest economic and development hurdles for paint formulators. To achieve maximum functionality, coverage, and economy of product, the rheology of the coating must be properly optimized, balancing performance while minimizing undesirable flow defects such as paint sagging or visible brush and roller marks; these visual imperfections are associated with the sag and leveling properties of the paint. Many researchers have attempted to develop a better understanding of sag and leveling, either by drawing correlations or through mathematical derivation; however, neither approach adequately predicts sag and leveling behavior. This provides the opportunity for machine learning to create a powerful model that utilizes formulation and rheological data and industry-standard tests to predict sag and leveling before the formulator creates the paint, reducing the resources necessary to optimize paint compared to a heuristic approach. Since little attention has been paid to the full rheological effects of sag and leveling, this approach also provides a first step in gaining new insight into the mechanisms behind this behavior.</p>","abstract_has_math":false,"creators":["Kim, Ethan"],"institution":null,"degree_name":"MS in Polymers and Coatings","degree_level":null,"degree_discipline":"Chemistry & Biochemistry","degree_department":null,"school":null,"contributors":["Erik Sapper","Chemistry & Biochemistry","College of Science and Mathematics"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-09-01T07:00:00Z","date_published":"2020-09-01T07:00:00Z","updated_at":"2026-07-24T01:32:13Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2020.89"],"render_values":[{"text":"10.15368/theses.2020.89","href":"https://doi.org/10.15368/theses.2020.89","code":true}]}]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2205","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Erik Sapper","Chemistry & Biochemistry","College of Science and Mathematics"]},{"key":"dc:creator","label":"Author","values":["Kim, Ethan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2020-09-03T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Chemistry & Biochemistry"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Polymers and Coatings"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2205","10.15368/theses.2020.89"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In the world of interior architectural paints, rheology, or the deformation and flow of a fluid, is one of the largest economic and development hurdles for paint formulators. To achieve maximum functionality, coverage, and economy of product, the rheology of the coating must be properly optimized, balancing performance while minimizing undesirable flow defects such as paint sagging or visible brush and roller marks; these visual imperfections are associated with the sag and leveling properties of the paint. Many researchers have attempted to develop a better understanding of sag and leveling, either by drawing correlations or through mathematical derivation; however, neither approach adequately predicts sag and leveling behavior. This provides the opportunity for machine learning to create a powerful model that utilizes formulation and rheological data and industry-standard tests to predict sag and leveling before the formulator creates the paint, reducing the resources necessary to optimize paint compared to a heuristic approach. Since little attention has been paid to the full rheological effects of sag and leveling, this approach also provides a first step in gaining new insight into the mechanisms behind this behavior.
"]},{"key":"dc:title","label":"Title","values":["Using Machine Learning to Predict Sag and Leveling Behavior of Interior Architectural Paints"]}]}],"canonical_facts":{"dc:contributor":["Erik Sapper","Chemistry & Biochemistry","College of Science and Mathematics"],"dc:creator":["Kim, Ethan"],"dc:date.available":["2020-09-03T07:00:00Z"],"dc:description.abstract":["In the world of interior architectural paints, rheology, or the deformation and flow of a fluid, is one of the largest economic and development hurdles for paint formulators. To achieve maximum functionality, coverage, and economy of product, the rheology of the coating must be properly optimized, balancing performance while minimizing undesirable flow defects such as paint sagging or visible brush and roller marks; these visual imperfections are associated with the sag and leveling properties of the paint. Many researchers have attempted to develop a better understanding of sag and leveling, either by drawing correlations or through mathematical derivation; however, neither approach adequately predicts sag and leveling behavior. This provides the opportunity for machine learning to create a powerful model that utilizes formulation and rheological data and industry-standard tests to predict sag and leveling before the formulator creates the paint, reducing the resources necessary to optimize paint compared to a heuristic approach. Since little attention has been paid to the full rheological effects of sag and leveling, this approach also provides a first step in gaining new insight into the mechanisms behind this behavior.
"],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2205","10.15368/theses.2020.89"],"dc:title":["Using Machine Learning to Predict Sag and Leveling Behavior of Interior Architectural Paints"],"thesis:degree_discipline":["Chemistry & Biochemistry"],"thesis:degree_name":["MS in Polymers and Coatings"]},"updated_at":"2026-07-24T01:32:13Z"}