{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/138660"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/138660","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Integrated approaches for monitoring sharks: Leveraging machine learning, big data, and molecular biology","abstract":"Sharks are ecologically important predators facing severe global declines, yet conservation and management are hindered by data deficiencies in taxonomy, distribution, and abundance. In this dissertation, I develop and integrate complementary technological approaches: machine learning, big data workflows, and molecular techniques—to expand scalable, non-invasive monitoring of sharks with programmatic and practical field methodologies. First, I constructed the largest global shark image dataset to date and developed the Shark Detector, a pipeline combining object detection and hierarchical classification. This system automatically locates, identifies, and classifies sharks in heterogeneous media, achieving >90% recall for detection and up to 92% species-level classification accuracy across 80 species, outperforming existing biodiversity classifiers. Second, we refined these methods for ecological survey applications by packaging the models into sharkDetectoR (R package) and SharkByte (desktop application), enabling accessible, semi-automatic processing of baited remote underwater videos (BRUVs). These tools reduced annotation effort by up to 95% while preserving high taxonomic resolution, and demonstrated iterative improvement through survey-specific data boosting. Third, I designed scalable pipelines to mine and filter >5 million social network (Instagram, Flickr) and open source (iNaturalist and Global Biodiversity Information Facility) posts and >600k opportunistic shark observations. By pairing automated classification with effort-standardized statistical models, we derived species-specific abundance indices that revealed regionally consistent population trends: increasing trajectories for coastal taxa in the Bahamas, and recent declines of reef-associated sharks in the Hawaiian Islands. Finally, I piloted molecular monitoring of critically endangered white sharks (Carcharodon carcharias) in the Mediterranean Sea using complimentary Environmental DNA detection and validation workflows. I collected 204 samples across the Sicilian Channel, Adriatic and Ligurian Seas, and detected white sharks at four stations. Detections were confirmed in the lab. Particle simulations identified the detected individuals as nearby for the purpose of tracking them in the field. A preliminary multi-species assay detected 12 elasmobranch species. These workflows provided novel spatiotemporal insights into white shark (and other elasmobranch) occurrence in hypothesized hotspots. Together, these chapters demonstrate how integrated computational and molecular approaches can overcome data limitations, provide reproducible ecological indices, and inform conservation of threatened shark populations in data-poor regions.","abstract_html":"Sharks are ecologically important predators facing severe global declines, yet conservation and management are hindered by data deficiencies in taxonomy, distribution, and abundance. In this dissertation, I develop and integrate complementary technological approaches: machine learning, big data workflows, and molecular techniques—to expand scalable, non-invasive monitoring of sharks with programmatic and practical field methodologies. First, I constructed the largest global shark image dataset to date and developed the Shark Detector, a pipeline combining object detection and hierarchical classification. This system automatically locates, identifies, and classifies sharks in heterogeneous media, achieving >90% recall for detection and up to 92% species-level classification accuracy across 80 species, outperforming existing biodiversity classifiers. Second, we refined these methods for ecological survey applications by packaging the models into sharkDetectoR (R package) and SharkByte (desktop application), enabling accessible, semi-automatic processing of baited remote underwater videos (BRUVs). These tools reduced annotation effort by up to 95% while preserving high taxonomic resolution, and demonstrated iterative improvement through survey-specific data boosting. Third, I designed scalable pipelines to mine and filter >5 million social network (Instagram, Flickr) and open source (iNaturalist and Global Biodiversity Information Facility) posts and >600k opportunistic shark observations. By pairing automated classification with effort-standardized statistical models, we derived species-specific abundance indices that revealed regionally consistent population trends: increasing trajectories for coastal taxa in the Bahamas, and recent declines of reef-associated sharks in the Hawaiian Islands. Finally, I piloted molecular monitoring of critically endangered white sharks (Carcharodon carcharias) in the Mediterranean Sea using complimentary Environmental DNA detection and validation workflows. I collected 204 samples across the Sicilian Channel, Adriatic and Ligurian Seas, and detected white sharks at four stations. Detections were confirmed in the lab. Particle simulations identified the detected individuals as nearby for the purpose of tracking them in the field. A preliminary multi-species assay detected 12 elasmobranch species. These workflows provided novel spatiotemporal insights into white shark (and other elasmobranch) occurrence in hypothesized hotspots. Together, these chapters demonstrate how integrated computational and molecular approaches can overcome data limitations, provide reproducible ecological indices, and inform conservation of threatened shark populations in data-poor regions.","abstract_has_math":false,"creators":["Jenrette, Jeremy Freeman"],"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":["Ferretti, Francesco"],"committee_members":["Hallerman, Eric M.","Fox, Edward A.","Johnson, Leah Renee"],"year":2025,"date_issued":"2025-10-24","date_published":"2025-10-24","updated_at":"2026-07-22T22:19:27Z","subjects":["Big data","Environmental DNA","Machine Learning","Sharks"],"languages":["en"],"rights":["Creative Commons Attribution 4.0 International"],"rights_urls":["http://creativecommons.org/licenses/by/4.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44757"],"render_values":[{"text":"vt_gsexam:44757","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/138660","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Ferretti, Francesco"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Hallerman, Eric M.","Fox, Edward A.","Johnson, Leah Renee"]},{"key":"dc:contributor.department","label":"Department","values":["Fish and Wildlife Conservation"]},{"key":"dc:creator","label":"Author","values":["Jenrette, Jeremy Freeman"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-10-25T08:00:13Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-10-25T08:00:13Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-10-24"]},{"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":["Big data","Environmental DNA","Machine Learning","Sharks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Creative Commons Attribution 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44757"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/138660"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Sharks are ecologically important predators facing severe global declines, yet conservation and management are hindered by data deficiencies in taxonomy, distribution, and abundance. In this dissertation, I develop and integrate complementary technological approaches: machine learning, big data workflows, and molecular techniques—to expand scalable, non-invasive monitoring of sharks with programmatic and practical field methodologies. First, I constructed the largest global shark image dataset to date and developed the Shark Detector, a pipeline combining object detection and hierarchical classification. This system automatically locates, identifies, and classifies sharks in heterogeneous media, achieving >90% recall for detection and up to 92% species-level classification accuracy across 80 species, outperforming existing biodiversity classifiers. Second, we refined these methods for ecological survey applications by packaging the models into sharkDetectoR (R package) and SharkByte (desktop application), enabling accessible, semi-automatic processing of baited remote underwater videos (BRUVs). These tools reduced annotation effort by up to 95% while preserving high taxonomic resolution, and demonstrated iterative improvement through survey-specific data boosting. Third, I designed scalable pipelines to mine and filter >5 million social network (Instagram, Flickr) and open source (iNaturalist and Global Biodiversity Information Facility) posts and >600k opportunistic shark observations. By pairing automated classification with effort-standardized statistical models, we derived species-specific abundance indices that revealed regionally consistent population trends: increasing trajectories for coastal taxa in the Bahamas, and recent declines of reef-associated sharks in the Hawaiian Islands. Finally, I piloted molecular monitoring of critically endangered white sharks (Carcharodon carcharias) in the Mediterranean Sea using complimentary Environmental DNA detection and validation workflows. I collected 204 samples across the Sicilian Channel, Adriatic and Ligurian Seas, and detected white sharks at four stations. Detections were confirmed in the lab. Particle simulations identified the detected individuals as nearby for the purpose of tracking them in the field. A preliminary multi-species assay detected 12 elasmobranch species. These workflows provided novel spatiotemporal insights into white shark (and other elasmobranch) occurrence in hypothesized hotspots. Together, these chapters demonstrate how integrated computational and molecular approaches can overcome data limitations, provide reproducible ecological indices, and inform conservation of threatened shark populations in data-poor regions."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Sharks are vital to healthy oceans but remain among the most threatened and data-poor groups of animals, largely because they are difficult to monitor. This dissertation develops new ways to study sharks using artificial intelligence, online citizen science data, and Environmental DNA. I built the largest collection of shark images ever assembled and trained computer models to automatically find and identify species in photos and videos, making surveys faster and more accurate. I created tools that allow researchers and citizen scientists to process underwater footage on their own computers, greatly reducing the time required to review hours of video. By analyzing millions of shark images shared on Social Networks and biodiversity websites, I uncovered patterns of abundance that reflect real population trends. I identified coastal shark numbers rising in the Bahamas but declining around the Hawaiian Islands. Finally, I tested Environmental DNA techniques to detect critically endangered sharks in the Mediterranean Sea including the white shark (Carcharodon carcharias), successfully finding their genetic traces in the Sicilian Channel, Adriatic and Ligurian Seas. Together, these approaches show how combining big data, machine learning, and molecular methods can fill major knowledge gaps and provide new tools to protect sharks worldwide."]},{"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":["Integrated approaches for monitoring sharks: Leveraging machine learning, big data, and molecular biology"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Ferretti, Francesco"],"dc:contributor.committeemember":["Hallerman, Eric M.","Fox, Edward A.","Johnson, Leah Renee"],"dc:contributor.department":["Fish and Wildlife Conservation"],"dc:creator":["Jenrette, Jeremy Freeman"],"dc:date.accessioned":["2025-10-25T08:00:13Z"],"dc:date.available":["2025-10-25T08:00:13Z"],"dc:date.issued":["2025-10-24"],"dc:description.abstract":["Sharks are ecologically important predators facing severe global declines, yet conservation and management are hindered by data deficiencies in taxonomy, distribution, and abundance. In this dissertation, I develop and integrate complementary technological approaches: machine learning, big data workflows, and molecular techniques—to expand scalable, non-invasive monitoring of sharks with programmatic and practical field methodologies. First, I constructed the largest global shark image dataset to date and developed the Shark Detector, a pipeline combining object detection and hierarchical classification. This system automatically locates, identifies, and classifies sharks in heterogeneous media, achieving >90% recall for detection and up to 92% species-level classification accuracy across 80 species, outperforming existing biodiversity classifiers. Second, we refined these methods for ecological survey applications by packaging the models into sharkDetectoR (R package) and SharkByte (desktop application), enabling accessible, semi-automatic processing of baited remote underwater videos (BRUVs). These tools reduced annotation effort by up to 95% while preserving high taxonomic resolution, and demonstrated iterative improvement through survey-specific data boosting. Third, I designed scalable pipelines to mine and filter >5 million social network (Instagram, Flickr) and open source (iNaturalist and Global Biodiversity Information Facility) posts and >600k opportunistic shark observations. By pairing automated classification with effort-standardized statistical models, we derived species-specific abundance indices that revealed regionally consistent population trends: increasing trajectories for coastal taxa in the Bahamas, and recent declines of reef-associated sharks in the Hawaiian Islands. Finally, I piloted molecular monitoring of critically endangered white sharks (Carcharodon carcharias) in the Mediterranean Sea using complimentary Environmental DNA detection and validation workflows. I collected 204 samples across the Sicilian Channel, Adriatic and Ligurian Seas, and detected white sharks at four stations. Detections were confirmed in the lab. Particle simulations identified the detected individuals as nearby for the purpose of tracking them in the field. A preliminary multi-species assay detected 12 elasmobranch species. These workflows provided novel spatiotemporal insights into white shark (and other elasmobranch) occurrence in hypothesized hotspots. Together, these chapters demonstrate how integrated computational and molecular approaches can overcome data limitations, provide reproducible ecological indices, and inform conservation of threatened shark populations in data-poor regions."],"dc:description.abstractgeneral":["Sharks are vital to healthy oceans but remain among the most threatened and data-poor groups of animals, largely because they are difficult to monitor. This dissertation develops new ways to study sharks using artificial intelligence, online citizen science data, and Environmental DNA. I built the largest collection of shark images ever assembled and trained computer models to automatically find and identify species in photos and videos, making surveys faster and more accurate. I created tools that allow researchers and citizen scientists to process underwater footage on their own computers, greatly reducing the time required to review hours of video. By analyzing millions of shark images shared on Social Networks and biodiversity websites, I uncovered patterns of abundance that reflect real population trends. I identified coastal shark numbers rising in the Bahamas but declining around the Hawaiian Islands. Finally, I tested Environmental DNA techniques to detect critically endangered sharks in the Mediterranean Sea including the white shark (Carcharodon carcharias), successfully finding their genetic traces in the Sicilian Channel, Adriatic and Ligurian Seas. Together, these approaches show how combining big data, machine learning, and molecular methods can fill major knowledge gaps and provide new tools to protect sharks worldwide."],"dc:description.degree":["Doctor of Philosophy"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:44757"],"dc:identifier.uri":["https://hdl.handle.net/10919/138660"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["Creative Commons Attribution 4.0 International"],"dc:rights.uri":["http://creativecommons.org/licenses/by/4.0/"],"dc:subject":["Big data","Environmental DNA","Machine Learning","Sharks"],"dc:title":["Integrated approaches for monitoring sharks: Leveraging machine learning, big data, and molecular biology"],"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":"2026-07-22T22:19:27Z"}