{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-4967"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-4967","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Automatic Red Tide Detection using MODIS Satellite Images","abstract":"Red tides pose a significant economic and environmental threat in the Gulf of Mexico. Detecting red tide is important for understanding this phenomenon. In this thesis, machine learning approaches based on Random Forests, Support Vector Machines and K-Nearest Neighbors have been evaluated for red tide detection from MODIS satellite images. Detection results using machine learning algorithms were compared to ship collected ground truth red tide data. This work has three major contributions. First, machine learning approaches outperformed two of the latest thresholding red tide detection algorithms based on bio-optical characterization by more than 10% in terms of F measure and more than 4% in terms of area under the ROC curve. Machine Learning approaches are effective in more locations on the West Florida Shelf. Second, the thresholds developed in recent thresholding methods were introduced as input attributes to the machine learning approaches and this strategy improved Random Forests and KNearest Neighbors approaches' F-measures. Third, voting the machine learning and thresholding methods could achieve the better performance compared with using machine learning alone, which implied a combination between machine learning models and biocharacterization thresholding methods can be used to obtain effective red tide detection results.","abstract_html":"Red tides pose a significant economic and environmental threat in the Gulf of Mexico. Detecting red tide is important for understanding this phenomenon. In this thesis, machine learning approaches based on Random Forests, Support Vector Machines and K-Nearest Neighbors have been evaluated for red tide detection from MODIS satellite images. Detection results using machine learning algorithms were compared to ship collected ground truth red tide data. This work has three major contributions. First, machine learning approaches outperformed two of the latest thresholding red tide detection algorithms based on bio-optical characterization by more than 10% in terms of F measure and more than 4% in terms of area under the ROC curve. Machine Learning approaches are effective in more locations on the West Florida Shelf. Second, the thresholds developed in recent thresholding methods were introduced as input attributes to the machine learning approaches and this strategy improved Random Forests and KNearest Neighbors approaches&#x27; F-measures. Third, voting the machine learning and thresholding methods could achieve the better performance compared with using machine learning alone, which implied a combination between machine learning models and biocharacterization thresholding methods can be used to obtain effective red tide detection results.","abstract_has_math":false,"creators":["Cheng, Wijian"],"institution":"University of South Florida","degree_name":null,"degree_level":"Thesis","degree_discipline":"Computer Science and Engineering","degree_department":null,"school":null,"contributors":["Dmitry B. Goldgof, Ph.D.","Lawrence O. Hall, Ph.D.","Sudeep Sarkar, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2009,"date_issued":"2009-06-08T07:00:00Z","date_published":"2009-06-08T07:00:00Z","updated_at":"2026-11-19T08:37:20Z","subjects":["karenia brevis","West Florida Shelf","machine learning","random forest","support vector machine","American Studies","Arts and Humanities","Computer Sciences"],"languages":["EN-US"],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/3772","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/3772","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-4967","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dmitry B. Goldgof, Ph.D.","Lawrence O. Hall, Ph.D.","Sudeep Sarkar, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Cheng, Wijian"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2009-06-08T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science and Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis","M.S.Cp.E."]},{"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":["karenia brevis","West Florida Shelf","machine learning","random forest","support vector machine","American Studies","Arts and Humanities","Computer Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["EN-US"]},{"key":"dc:rights.license","label":"Dc Rights License","values":["default"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/3772"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Red tides pose a significant economic and environmental threat in the Gulf of Mexico. Detecting red tide is important for understanding this phenomenon. In this thesis, machine learning approaches based on Random Forests, Support Vector Machines and K-Nearest Neighbors have been evaluated for red tide detection from MODIS satellite images. Detection results using machine learning algorithms were compared to ship collected ground truth red tide data. This work has three major contributions. First, machine learning approaches outperformed two of the latest thresholding red tide detection algorithms based on bio-optical characterization by more than 10% in terms of F measure and more than 4% in terms of area under the ROC curve. Machine Learning approaches are effective in more locations on the West Florida Shelf. Second, the thresholds developed in recent thresholding methods were introduced as input attributes to the machine learning approaches and this strategy improved Random Forests and KNearest Neighbors approaches' F-measures. Third, voting the machine learning and thresholding methods could achieve the better performance compared with using machine learning alone, which implied a combination between machine learning models and biocharacterization thresholding methods can be used to obtain effective red tide detection results."]},{"key":"dc:title","label":"Title","values":["Automatic Red Tide Detection using MODIS Satellite Images"]}]}],"canonical_facts":{"dc:contributor":["Dmitry B. Goldgof, Ph.D.","Lawrence O. Hall, Ph.D.","Sudeep Sarkar, Ph.D."],"dc:creator":["Cheng, Wijian"],"dc:date":["2009-06-08T07:00:00Z"],"dc:description":["Red tides pose a significant economic and environmental threat in the Gulf of Mexico. Detecting red tide is important for understanding this phenomenon. In this thesis, machine learning approaches based on Random Forests, Support Vector Machines and K-Nearest Neighbors have been evaluated for red tide detection from MODIS satellite images. Detection results using machine learning algorithms were compared to ship collected ground truth red tide data. This work has three major contributions. First, machine learning approaches outperformed two of the latest thresholding red tide detection algorithms based on bio-optical characterization by more than 10% in terms of F measure and more than 4% in terms of area under the ROC curve. Machine Learning approaches are effective in more locations on the West Florida Shelf. Second, the thresholds developed in recent thresholding methods were introduced as input attributes to the machine learning approaches and this strategy improved Random Forests and KNearest Neighbors approaches' F-measures. Third, voting the machine learning and thresholding methods could achieve the better performance compared with using machine learning alone, which implied a combination between machine learning models and biocharacterization thresholding methods can be used to obtain effective red tide detection results."],"dc:identifier":["https://digitalcommons.usf.edu/etd/3772"],"dc:language":["EN-US"],"dc:rights.license":["default"],"dc:subject":["karenia brevis","West Florida Shelf","machine learning","random forest","support vector machine","American Studies","Arts and Humanities","Computer Sciences"],"dc:title":["Automatic Red Tide Detection using MODIS Satellite Images"],"thesis:degree_discipline":["Computer Science and Engineering"],"thesis:degree_level":["Thesis","M.S.Cp.E."],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:37:20Z"}