[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125819-en":3,"doc-seo-125819-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125819,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Machine Learning for Identifying Emergent and Floating Aquatic Vegetation from Space - A Case Study in the Dniester Delta, Ukraine","Monitoring aquatic vegetation, including both floating and emergent types, supports understanding freshwater ecosystem dynamics. This study targets the Lower Dniester Basin in Southern Ukraine, spanning about 1800 square kilometers of steppe plains and wetlands, and uses Sentinel-2 satellite imagery to segment aquatic vegetation into emergent and floating classes. Traditional machine learning methods—random forest and boosting trees—are validated with annually collected in-situ field measurements over five years. The floating-vegetation classifier reaches an F1-score of 0.88 ± 0.03 and improves over histogram-based thresholding, while feature analysis via mRMR supports ecological monitoring workflows.","SN Computer Science (2024) 5:597  \n[https://doi.org/10.1007/s42979-024-02873-7](https://doi.org/10.1007/s42979-024-02873-7)  \nORIGINAL RESEARCH  \nMachine Learning for Identifying Emergent and Floating Aquatic Vegetation from Space: A Case Study in the Dniester Delta, Ukraine  \nLeonidas Alagialoglou1 · Ioannis Manakos2 · Eleftherios Katsikis2 · Sergiy Medinets3,4 · Yevgen Gazyetov3 · Volodymyr Medinets3 · Anastasios Delopoulos1  \nReceived: 17 October 2023 / Accepted: 4 April 2024 © The Author(s) 2024  \nAbstract  \nMonitoring aquatic vegetation, including both floating and emergent types, plays a crucial role in understanding the dynamics of freshwater ecosystems. Our research focused on the Lower Dniester Basin in Southern Ukraine, covering approximately 1800 square kilometers of steppe plains and wetlands. We applied traditional machine learning algorithms, specifically random forest and boosting trees, to analyze Sentinel-2 satellite imagery for segmenting aquatic vegetation into emergent and floating types. Our methodology was validated against detailed in-situ field measurements collected annually over a 5-year study period. The machine learning classifiers achieved an F1-score of 0.88 ± 0.03 in classifying floating vegetation, outperforming our previously suggested histogram-based thresholding methodology for the same task. While emergent vegetation and open water were easily identifiable from satellite imagery, the robustness and temporal transferability of our methodology included accurately delineating floating vegetation as well. Additionally, we explored the significance of various features through the Minimum Redundancy-Maximum Relevance algorithm. This study highlights advancementsin aquatic vegetation mapping and demonstrates a valuable tool for ecological monitoring and future research endeavors.  \nKeywords Wetland · Sentinel-2 · Floating vegetation · Emergent vegetation · Machine learning · Thresholding · Multi-class segmentation · Feature importance  \nThis article is part of the topical collection “Advances on Geographical Information Systems Theory, Applications and Management” guest edited by Lemonia Ragia, Cédric Grueau and Armanda Rodrigues.  \n* Leonidas Alagialoglou [lalagial@mug.ee.auth.gr](lalagial@mug.ee.auth.gr)[ ](lalagial@mug.ee.auth.gr)Ioannis Manakos[imanakos@iti.gr](imanakos@iti.gr)[ ](imanakos@iti.gr)Eleftherios Katsikis[lefkats@iti.gr](lefkats@iti.gr)  \nSergiy Medinets  \n[s.medinets@gmail.com](s.medinets@gmail.com)[ ](s.medinets@gmail.com)Yevgen Gazyetov [gazetov@gmail.com](gazetov@gmail.com)  \nVolodymyr Medinets [medinets@te.net.ua](medinets@te.net.ua)  \nIntroduction  \nFreshwater ecosystems constitute a vital resource, delivering ecosystem services that infulence the well-being of local communities and regional economies. These services encompass critical functions such as the production of drinking water, support for tourism, aquaculture, and the  \nAnastasios Delopoulos  \n[antelopo@ece.auth.gr](antelopo@ece.auth.gr)  \n1 Multimedia Understanding Group, Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, Greece  \n2 Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece  \n3 Odesa National I.I. Mechnikov University, Odesa, Ukraine  \n4 Atmospheric Chemistry and Effects, UK Centre for Ecology & Hydrology, Edinburgh, United Kingdom  \nSN Computer Science  \ngeneration of hydropower [1] . Nevertheless, these precious ecosystems face a growing vulnerability to anthropogenic influences.  \nThe primary driver of ecological concerns in numerous transboundary river catchments, including the Dniester, stems from the excessive anthropogenic load of nutrients. This load results from a spectrum of human activities, including agriculture, industrial processes characterized by wastewater discharges and gas emission redeposition, domestic sewage discharges, and other anthropogenic actions [2–4] . These activities have led t","cbCaiodHXlULla2U","https://ap.wps.com/l/cbCaiodHXlULla2U","pdf",2333343,1,13,"English","en",105,"# Introduction\n## Ecological need for aquatic vegetation monitoring\n## Satellite-based estimation approaches\n## Study area and data overview\n## Machine learning methods and segmentation\n## Validation and performance results\n## Feature importance and feature relevance\n## Discussion and implications","[{\"question\":\"What vegetation types does the study aim to identify from space?\",\"answer\":\"The study segments aquatic vegetation into two types: floating vegetation and emergent vegetation using Sentinel-2 satellite imagery.\"},{\"question\":\"How is the machine learning approach validated?\",\"answer\":\"Validation uses detailed in-situ field measurements collected annually over a five-year study period.\"},{\"question\":\"What performance level is reported for floating vegetation classification?\",\"answer\":\"The floating vegetation classifier achieves an F1-score of 0.88 ± 0.03 and outperforms a prior histogram-based thresholding method for the same task.\"}]","Machine Learning for Identifying Emergent and Floating Aquatic Vegetation from Space - A Case Study in the Dniester Delta, Ukraine | PDF",1785901394,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-for-identifying-emergent-and-floating-aquatic-vegetation-from-space-a-case-study-in-the-dniester-delta-ukraine","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-for-identifying-emergent-and-floating-aquatic-vegetation-from-space-a-case-study-in-the-dniester-delta-ukraine/125819/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What vegetation types does the study aim to identify from space?","Question",{"text":75,"@type":76},"The study segments aquatic vegetation into two types: floating vegetation and emergent vegetation using Sentinel-2 satellite imagery.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the machine learning approach validated?",{"text":80,"@type":76},"Validation uses detailed in-situ field measurements collected annually over a five-year study period.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance level is reported for floating vegetation classification?",{"text":84,"@type":76},"The floating vegetation classifier achieves an F1-score of 0.88 ± 0.03 and outperforms a prior histogram-based thresholding method for the same task.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]