{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/140951"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/140951","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Advancing Fisheries and Aquaculture Management with Machine Learning: Bycatch Risk Prediction and Autonomous Mortality Modeling","abstract":"Machine learning is proving to play an increasingly important role in many fields, including ecology and fisheries sciences. Machine learning models offer many advantages over traditional statistical analysis methods, such as being well suited for analyzing large data sets, capable of incorporating multiple data types in a single model, and able to handle cross-correlated variables without severely affecting model performance. They can also potentially detect complex patterns among variables that other modeling methods cannot. As seafood demand continues to rise, it becomes crucial for managers of both wild capture fisheries and aquaculture to maximize their production while minimizing potential negative environmental and ecological impacts. This study aimed to demonstrate the utility of applying machine learning methods to fisheries and aquaculture management, specifically for bycatch analysis and for predicting caged-fish mortality and productivity in offshore aquaculture. Our study found that, machine learning methods effectively assess how fishing tactics, spatial, temporal and environmental variables impact bycatch risk of vulnerable organisms such as seabirds, helping refine fishing regulations to reduce future bycatch events. Hook density and float density had a very strong influence on bycatch risk and had been previously unexamined in bycatch models. This study also identified two machine learning model frameworks for effective bycatch prediction. Machine learning models were developed to predict fish growth and mortality rates, and facilitate determining the optimal harvest schedule for productivity and profit. The linear model was most effective for estimating daily growth of the cobia. ARIMA-ANN hybrid model framework was the best the five model frameworks for assessing mortality patterns in Cobia and in predicting future mortality rates. This automation is particularly important in offshore fish farms, which are in remote and hazardous environments. In conclusion, machine learning models can be extremely beneficial to advancing fisheries and aquaculture management.","abstract_html":"Machine learning is proving to play an increasingly important role in many fields, including ecology and fisheries sciences. Machine learning models offer many advantages over traditional statistical analysis methods, such as being well suited for analyzing large data sets, capable of incorporating multiple data types in a single model, and able to handle cross-correlated variables without severely affecting model performance. They can also potentially detect complex patterns among variables that other modeling methods cannot. As seafood demand continues to rise, it becomes crucial for managers of both wild capture fisheries and aquaculture to maximize their production while minimizing potential negative environmental and ecological impacts. This study aimed to demonstrate the utility of applying machine learning methods to fisheries and aquaculture management, specifically for bycatch analysis and for predicting caged-fish mortality and productivity in offshore aquaculture. Our study found that, machine learning methods effectively assess how fishing tactics, spatial, temporal and environmental variables impact bycatch risk of vulnerable organisms such as seabirds, helping refine fishing regulations to reduce future bycatch events. Hook density and float density had a very strong influence on bycatch risk and had been previously unexamined in bycatch models. This study also identified two machine learning model frameworks for effective bycatch prediction. Machine learning models were developed to predict fish growth and mortality rates, and facilitate determining the optimal harvest schedule for productivity and profit. The linear model was most effective for estimating daily growth of the cobia. ARIMA-ANN hybrid model framework was the best the five model frameworks for assessing mortality patterns in Cobia and in predicting future mortality rates. This automation is particularly important in offshore fish farms, which are in remote and hazardous environments. In conclusion, machine learning models can be extremely beneficial to advancing fisheries and aquaculture management.","abstract_has_math":false,"creators":["Pakzad, Iman Yeganeh"],"institution":"Virginia Tech","degree_name":"Doctor of Philosophy","degree_level":"doctoral","degree_discipline":"Fisheries and Wildlife Science","degree_department":"Fish and Wildlife Conservation","school":null,"contributors":[],"advisors":[],"committee_chairs":["Jiao, Yan"],"committee_members":["Galappaththi, Eranga","Schwarz, Michael H.","Zuo, Lei"],"year":2026,"date_issued":"2026-01-22","date_published":"2026-01-22","updated_at":"2026-07-22T22:19:35Z","subjects":["Seabird bycatch","Pelagic longline fishery","offshore aquaculture","mortality","U.S. Atlantic coast","Random Forest","XGBoost","ARIMA","Neural Network"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:45597"],"render_values":[{"text":"vt_gsexam:45597","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/140951","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Jiao, Yan"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Galappaththi, Eranga","Schwarz, Michael H.","Zuo, Lei"]},{"key":"dc:contributor.department","label":"Department","values":["Fish and Wildlife Conservation"]},{"key":"dc:creator","label":"Author","values":["Pakzad, Iman Yeganeh"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-01-23T09:00:49Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-01-23T09:00:49Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-01-22"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Fisheries and Wildlife Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Seabird bycatch","Pelagic longline fishery","offshore aquaculture","mortality","U.S. Atlantic coast","Random Forest","XGBoost","ARIMA","Neural Network"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:45597"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/140951"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Machine learning is proving to play an increasingly important role in many fields, including ecology and fisheries sciences. Machine learning models offer many advantages over traditional statistical analysis methods, such as being well suited for analyzing large data sets, capable of incorporating multiple data types in a single model, and able to handle cross-correlated variables without severely affecting model performance. They can also potentially detect complex patterns among variables that other modeling methods cannot. As seafood demand continues to rise, it becomes crucial for managers of both wild capture fisheries and aquaculture to maximize their production while minimizing potential negative environmental and ecological impacts. This study aimed to demonstrate the utility of applying machine learning methods to fisheries and aquaculture management, specifically for bycatch analysis and for predicting caged-fish mortality and productivity in offshore aquaculture. Our study found that, machine learning methods effectively assess how fishing tactics, spatial, temporal and environmental variables impact bycatch risk of vulnerable organisms such as seabirds, helping refine fishing regulations to reduce future bycatch events. Hook density and float density had a very strong influence on bycatch risk and had been previously unexamined in bycatch models. This study also identified two machine learning model frameworks for effective bycatch prediction. Machine learning models were developed to predict fish growth and mortality rates, and facilitate determining the optimal harvest schedule for productivity and profit. The linear model was most effective for estimating daily growth of the cobia. ARIMA-ANN hybrid model framework was the best the five model frameworks for assessing mortality patterns in Cobia and in predicting future mortality rates. This automation is particularly important in offshore fish farms, which are in remote and hazardous environments. In conclusion, machine learning models can be extremely beneficial to advancing fisheries and aquaculture management."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Machine learning, or the process by which computers learn from data, is playing an increasingly important role in many fields, including fisheries science. As the demand for seafood is on the rise, fishermen, fish farm managers and ecologists must find ways to increase seafood production without negatively impacting other natural resources. Machine learning will be a critical tool in accomplishing this goal as machine learning allows computers to quickly transform large, complex data sets into easily interpreted results that let fishermen and farm managers make informed, real-time decisions. For wild capture fisheries, machine learning models can be used to refine fishing regulations to reduce the probability of catching vulnerable species such as seabirds without negatively impacting the total yield. Using machine learning methods, I identified that hook density and float density strongly impact seabird bycatch risk, both of which have not been evaluated in prior bycatch research. Additionally, I identified two machine learning algorithms: random forest and XGBoost, that can be used to estimate future bycatch events. For fish farms, machine learning can be used automize and optimize processes like feeding and harvesting to maximize productivity and profit. Automation is particularly important for offshore fish farms, which have the capacity for high rates of seafood production but can be extremely hazardous environments. By automating more aspects of fish farm production, fish farm managers can respond to issues that arise in real time without exposing workers to undue risk. I identified effective algorithms to estimate offshore cobia growth and mortality. The outputs of these models can be synthesized further to estimate total fish yield and profit using different harvest strategies. Aquaculture operations can then use these tools to further enhance their productivity. In conclusion, machine learning will likely be an invaluable tool to ecologists, fish farm managers and fishermen to address the rising demand for seafood and similar management challenges in the future."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Doctor of Philosophy"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Advancing Fisheries and Aquaculture Management with Machine Learning: Bycatch Risk Prediction and Autonomous Mortality Modeling"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Jiao, Yan"],"dc:contributor.committeemember":["Galappaththi, Eranga","Schwarz, Michael H.","Zuo, Lei"],"dc:contributor.department":["Fish and Wildlife Conservation"],"dc:creator":["Pakzad, Iman Yeganeh"],"dc:date.accessioned":["2026-01-23T09:00:49Z"],"dc:date.available":["2026-01-23T09:00:49Z"],"dc:date.issued":["2026-01-22"],"dc:description.abstract":["Machine learning is proving to play an increasingly important role in many fields, including ecology and fisheries sciences. Machine learning models offer many advantages over traditional statistical analysis methods, such as being well suited for analyzing large data sets, capable of incorporating multiple data types in a single model, and able to handle cross-correlated variables without severely affecting model performance. They can also potentially detect complex patterns among variables that other modeling methods cannot. As seafood demand continues to rise, it becomes crucial for managers of both wild capture fisheries and aquaculture to maximize their production while minimizing potential negative environmental and ecological impacts. This study aimed to demonstrate the utility of applying machine learning methods to fisheries and aquaculture management, specifically for bycatch analysis and for predicting caged-fish mortality and productivity in offshore aquaculture. Our study found that, machine learning methods effectively assess how fishing tactics, spatial, temporal and environmental variables impact bycatch risk of vulnerable organisms such as seabirds, helping refine fishing regulations to reduce future bycatch events. Hook density and float density had a very strong influence on bycatch risk and had been previously unexamined in bycatch models. This study also identified two machine learning model frameworks for effective bycatch prediction. Machine learning models were developed to predict fish growth and mortality rates, and facilitate determining the optimal harvest schedule for productivity and profit. The linear model was most effective for estimating daily growth of the cobia. ARIMA-ANN hybrid model framework was the best the five model frameworks for assessing mortality patterns in Cobia and in predicting future mortality rates. This automation is particularly important in offshore fish farms, which are in remote and hazardous environments. In conclusion, machine learning models can be extremely beneficial to advancing fisheries and aquaculture management."],"dc:description.abstractgeneral":["Machine learning, or the process by which computers learn from data, is playing an increasingly important role in many fields, including fisheries science. As the demand for seafood is on the rise, fishermen, fish farm managers and ecologists must find ways to increase seafood production without negatively impacting other natural resources. Machine learning will be a critical tool in accomplishing this goal as machine learning allows computers to quickly transform large, complex data sets into easily interpreted results that let fishermen and farm managers make informed, real-time decisions. For wild capture fisheries, machine learning models can be used to refine fishing regulations to reduce the probability of catching vulnerable species such as seabirds without negatively impacting the total yield. Using machine learning methods, I identified that hook density and float density strongly impact seabird bycatch risk, both of which have not been evaluated in prior bycatch research. Additionally, I identified two machine learning algorithms: random forest and XGBoost, that can be used to estimate future bycatch events. For fish farms, machine learning can be used automize and optimize processes like feeding and harvesting to maximize productivity and profit. Automation is particularly important for offshore fish farms, which have the capacity for high rates of seafood production but can be extremely hazardous environments. By automating more aspects of fish farm production, fish farm managers can respond to issues that arise in real time without exposing workers to undue risk. I identified effective algorithms to estimate offshore cobia growth and mortality. The outputs of these models can be synthesized further to estimate total fish yield and profit using different harvest strategies. Aquaculture operations can then use these tools to further enhance their productivity. In conclusion, machine learning will likely be an invaluable tool to ecologists, fish farm managers and fishermen to address the rising demand for seafood and similar management challenges in the future."],"dc:description.degree":["Doctor of Philosophy"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:45597"],"dc:identifier.uri":["https://hdl.handle.net/10919/140951"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Seabird bycatch","Pelagic longline fishery","offshore aquaculture","mortality","U.S. Atlantic coast","Random Forest","XGBoost","ARIMA","Neural Network"],"dc:title":["Advancing Fisheries and Aquaculture Management with Machine Learning: Bycatch Risk Prediction and Autonomous Mortality Modeling"],"dc:type":["Dissertation"],"thesis:degree_discipline":["Fisheries and Wildlife Science"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:35Z"}