{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-12318"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-12318","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"The Asset Management Optimization Engine: An AI and Machine Learning Model Approach to Pavement Asset Management","abstract":"While state Departments of Transportation (DOT) face major funding challenges, the need to find optimal ways to preserve and maintain pavement assets remains. Asset management employs a lowest cost lifecycle method to analyze asset costs and determine the best investment strategies to preserve it throughout its lifecycle. As new technology emerges, so do opportunities to leverage it. DOTs collect a significant amount of performance data on pavement and use it to decide how to keep it in a state of good repair. The literature in this area focuses on engineering techniques applied to treatment strategies. This dissertation research focuses on how practitioners can apply machine learning to pavement asset management and use it to make decisions. The research explores the development of machine learning models to identify factors affecting pavement performance from the pavement management system and use the models to augment investment need identification and recommend investment strategies. Using Action Design Research and data from the Washington State DOT, the research introduces three models to answer each of the research questions—two regression models and an artificial neural network paired with computer vision to analyze pavement cracking. The results demonstrate statistical significance, suggesting the right data is in place to optimize decision making through machine learning. Factors such as rutting, days since rehab, percentage of trucks, and roughness index can be used to predict pavement condition. Cost factors, including replacement costs, Equivalent Uniform Annual Costs (EUAC), and lifecycle, can predict how much is needed to invest to keep the pavement in a state of good repair. It also provides a path for practitioners to use machine learning through low code and no code tools that non-data scientists can employ. The value of the models is the ability to predict the impact to structural condition and overall spending by a change in the variables.","abstract_html":"While state Departments of Transportation (DOT) face major funding challenges, the need to find optimal ways to preserve and maintain pavement assets remains. Asset management employs a lowest cost lifecycle method to analyze asset costs and determine the best investment strategies to preserve it throughout its lifecycle. As new technology emerges, so do opportunities to leverage it. DOTs collect a significant amount of performance data on pavement and use it to decide how to keep it in a state of good repair. The literature in this area focuses on engineering techniques applied to treatment strategies. This dissertation research focuses on how practitioners can apply machine learning to pavement asset management and use it to make decisions. The research explores the development of machine learning models to identify factors affecting pavement performance from the pavement management system and use the models to augment investment need identification and recommend investment strategies. Using Action Design Research and data from the Washington State DOT, the research introduces three models to answer each of the research questions—two regression models and an artificial neural network paired with computer vision to analyze pavement cracking. The results demonstrate statistical significance, suggesting the right data is in place to optimize decision making through machine learning. Factors such as rutting, days since rehab, percentage of trucks, and roughness index can be used to predict pavement condition. Cost factors, including replacement costs, Equivalent Uniform Annual Costs (EUAC), and lifecycle, can predict how much is needed to invest to keep the pavement in a state of good repair. It also provides a path for practitioners to use machine learning through low code and no code tools that non-data scientists can employ. The value of the models is the ability to predict the impact to structural condition and overall spending by a change in the variables.","abstract_has_math":false,"creators":["Versdahl, Matt"],"institution":"University of South Florida","degree_name":null,"degree_level":"Dissertation","degree_discipline":"Business","degree_department":null,"school":null,"contributors":["James Stock, Ph.D.","Jason Cherubini, D.B.A.","Jennifer Wolgemuth, Ph.D.","Uday Murthy, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-03-27T07:00:00Z","date_published":"2025-03-27T07:00:00Z","updated_at":"2026-11-19T08:49:40Z","subjects":["Action Design Research","Artificial Intelligence","Artificial Neural Network","Computer Vision","Data Science","Artificial Intelligence and Robotics","Engineering","Urban Studies and Planning"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/11015","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/11015","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.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-12318","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["James Stock, Ph.D.","Jason Cherubini, D.B.A.","Jennifer Wolgemuth, Ph.D.","Uday Murthy, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Versdahl, Matt"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-03-27T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Business"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation","D.B.A."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Action Design Research","Artificial Intelligence","Artificial Neural Network","Computer Vision","Data Science","Artificial Intelligence and Robotics","Engineering","Urban Studies and Planning"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/11015"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["While state Departments of Transportation (DOT) face major funding challenges, the need to find optimal ways to preserve and maintain pavement assets remains. Asset management employs a lowest cost lifecycle method to analyze asset costs and determine the best investment strategies to preserve it throughout its lifecycle. As new technology emerges, so do opportunities to leverage it. DOTs collect a significant amount of performance data on pavement and use it to decide how to keep it in a state of good repair. The literature in this area focuses on engineering techniques applied to treatment strategies. This dissertation research focuses on how practitioners can apply machine learning to pavement asset management and use it to make decisions. The research explores the development of machine learning models to identify factors affecting pavement performance from the pavement management system and use the models to augment investment need identification and recommend investment strategies. Using Action Design Research and data from the Washington State DOT, the research introduces three models to answer each of the research questions—two regression models and an artificial neural network paired with computer vision to analyze pavement cracking. The results demonstrate statistical significance, suggesting the right data is in place to optimize decision making through machine learning. Factors such as rutting, days since rehab, percentage of trucks, and roughness index can be used to predict pavement condition. Cost factors, including replacement costs, Equivalent Uniform Annual Costs (EUAC), and lifecycle, can predict how much is needed to invest to keep the pavement in a state of good repair. It also provides a path for practitioners to use machine learning through low code and no code tools that non-data scientists can employ. The value of the models is the ability to predict the impact to structural condition and overall spending by a change in the variables."]},{"key":"dc:title","label":"Title","values":["The Asset Management Optimization Engine: An AI and Machine Learning Model Approach to Pavement Asset Management"]}]}],"canonical_facts":{"dc:contributor":["James Stock, Ph.D.","Jason Cherubini, D.B.A.","Jennifer Wolgemuth, Ph.D.","Uday Murthy, Ph.D."],"dc:creator":["Versdahl, Matt"],"dc:date":["2025-03-27T07:00:00Z"],"dc:description":["While state Departments of Transportation (DOT) face major funding challenges, the need to find optimal ways to preserve and maintain pavement assets remains. Asset management employs a lowest cost lifecycle method to analyze asset costs and determine the best investment strategies to preserve it throughout its lifecycle. As new technology emerges, so do opportunities to leverage it. DOTs collect a significant amount of performance data on pavement and use it to decide how to keep it in a state of good repair. The literature in this area focuses on engineering techniques applied to treatment strategies. This dissertation research focuses on how practitioners can apply machine learning to pavement asset management and use it to make decisions. The research explores the development of machine learning models to identify factors affecting pavement performance from the pavement management system and use the models to augment investment need identification and recommend investment strategies. Using Action Design Research and data from the Washington State DOT, the research introduces three models to answer each of the research questions—two regression models and an artificial neural network paired with computer vision to analyze pavement cracking. The results demonstrate statistical significance, suggesting the right data is in place to optimize decision making through machine learning. Factors such as rutting, days since rehab, percentage of trucks, and roughness index can be used to predict pavement condition. Cost factors, including replacement costs, Equivalent Uniform Annual Costs (EUAC), and lifecycle, can predict how much is needed to invest to keep the pavement in a state of good repair. It also provides a path for practitioners to use machine learning through low code and no code tools that non-data scientists can employ. The value of the models is the ability to predict the impact to structural condition and overall spending by a change in the variables."],"dc:identifier":["https://digitalcommons.usf.edu/etd/11015"],"dc:subject":["Action Design Research","Artificial Intelligence","Artificial Neural Network","Computer Vision","Data Science","Artificial Intelligence and Robotics","Engineering","Urban Studies and Planning"],"dc:title":["The Asset Management Optimization Engine: An AI and Machine Learning Model Approach to Pavement Asset Management"],"thesis:degree_discipline":["Business"],"thesis:degree_level":["Dissertation","D.B.A."],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:49:40Z"}