[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121180-en":3,"doc-seo-121180-105":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},121180,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Species assignment from seal diet samples using shape analyses in a machine learning framework","Trophic ecology studies depend on accurately identifying and quantifying prey consumed by predators, yet visual inspection of Baltic ringed seal diets is difficult for distinguishing morphologically similar vendace and whitefish otoliths. This work combines otolith shape outline analyses with machine learning, using an in vitro digestion experiment to train the model. The approach self-assigns known digested otoliths to their origin with over 90% accuracy and assigns 89% of otoliths from digestive tract samples to species level. The method supports improved understanding of feeding habits, predator–prey interactions, and large-scale stock assessment inputs, and it motivates extending discrimination to additional fish diets.","ICES Journal of Marine Science, 2024, Vol. 81, Issue 10, 1952–1962  \n[https://doi.org/10.1093/icesjms/fsae134](https://doi.org/10.1093/icesjms/fsae134)  \nReceived: 24 April 2024; revised: 16 August 2024; accepted: 11 September 2024  \nAdvance access publication date: 7 October 2024  \nOriginal Article  \nSpecies assignment from seal diet samples using shape analyses in a machine learning framework  \nMonica Mion 1 ,* ,†, Florian Berg 2 ,†, Francesco Saltalamacchia1,3 , Valerio Bartolino 1 ,  \nJohan Lövgren1 , Mikaela Bergenius Nord1 , David Gilljam4 , Martina Blass4 , Karl Lundström 1  \n1 Department of Aquatic Resources, Swedish University of Agricultural Sciences, Turistgatan 5, 453 30 Lysekil, Sweden  \n2 Institute of Marine Research, Post Box 1870 Nordnes, 5817 Bergen, Norway  \n3 Department of Biological Sciences, University of Bergen, Post Box 7803, 5020 Bergen, Norway  \n4 Department of Aquatic Resources, Swedish University of Agricultural Sciences, Skolgatan 6, SE-742 42 Öregrund, Sweden  \n∗ Corresponding author. Department of Aquatic Resources, Swedish University of Agricultural Sciences, Turistgatan 5, 453 30 Lysekil, Sweden. E-mail:  \n[monica.mion@slu.se](monica.mion@slu.se)  \n†Joint first authors  \nAbstract  \nThe identification and quantification of prey ingested is a limiting factor in trophic ecology studies and is fundamental for assessing the impact of a predator on prey populations. Vendace (Coregonus albula) and whitefish (C. lavaretus) are two congeneric species, which are commonly preyed on by Baltic ringed seals (Pusa hispida) . The otoliths of these two species are, however, very similar and distinguishing between them in the seal diet using visual inspection has so far been challenging. Here, otolith shape outline analyses were used in combination with machine learning techniques to discriminate between eroded vendace and whitefish otoliths from ringed seal diet samples. An experiment of in vitro digestion of the otoliths was performed totrain a machine learning model. Our model is able to self-assign known digested otoliths back to their species of origin with >90% accuracy. Furthermore, 89%(N = 690) of the otoliths collected from digestive tract samples could be successfully assigned to species level, i.e. vendace or whitefish. This method is readily applicable for improved understanding of ringed seal feeding habits and predator–prey interactions, as well as large-scale applications to generate seal-predation matrix inputs for stock assessments of vendace and whitefish. Further development of the machine learning techniques to discriminate between prey species in seal and other piscivorous diets is strongly encouraged.  \nIntroduction  \nPredator–prey interactions are important drivers of population dynamics in aquatic ecosystems, as they contribute to the natural mortality of fish stocks. In particular, the rate of predation is important in the assessments of interactions between piscivorous organisms and fisheries (Morisette et al. 2012) . Adequate data from dietary assessments are therefore essential building blocks for the road towards an ecosystem-based management approach (ICES 2023a) .  \nIn the latter part of the 20th century, conservation efforts have led to the improvement of the status of numerous marine mammal populations worldwide (Lotze et al.2011, Magera et al. 2013, Chasco et al. 2017) . Many marine mammal species rely on fish as their main source of food. This has resulted in conflicts between piscivorous predators and fisheries, competing for the same resource (Costalago et al. 2019) . This applies for the ringed seal (Pusa hispida) population of the northernmost part of the Baltic Sea, i.e. the Bothnian Bay, in the International Council for the Exploration of the Sea (ICES) subdivision 31, which together with the Bothnian Sea (ICES subdivision 30) forms the Gulf of Bothnia (Fig. 1). The Baltic ringed seal population decreased drastically during the 1900s due to intense hunting and, in the 1960","cbCainq6jZDvhkL3","https://ap.wps.com/l/cbCainq6jZDvhkL3","pdf",1355410,1,11,"English","en",105,"# Abstract\n# Introduction\n## Predator–prey interactions and ecosystem-based management\n## Ringed seal population recovery and seal–fishery conflict\n## Prey composition and relevance for stock assessments","[{\"question\":\"Why is prey identification in ringed seal diet studies challenging for vendace and whitefish?\",\"answer\":\"The otoliths of vendace and whitefish are very similar, making reliable separation from seal diet samples by visual inspection difficult.\"},{\"question\":\"How does the study assign otoliths to species?\",\"answer\":\"It uses otolith shape outline analyses combined with machine learning. An in vitro digestion experiment provides training data to discriminate eroded otoliths.\"},{\"question\":\"What accuracy results does the machine learning model achieve?\",\"answer\":\"Known digested otoliths are self-assigned to their origin with over 90% accuracy, and 89% of otoliths collected from digestive tract samples can be assigned to species level.\"}]","Species assignment from seal diet samples using shape analyses in a machine learning framework | PDF",1785734239,28,{"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},"species-assignment-from-seal-diet-samples-using-shape-analyses-in-a-machine-learning-framework","",{"@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/species-assignment-from-seal-diet-samples-using-shape-analyses-in-a-machine-learning-framework/121180/",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","2026-08-03",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},"Why is prey identification in ringed seal diet studies challenging for vendace and whitefish?","Question",{"text":75,"@type":76},"The otoliths of vendace and whitefish are very similar, making reliable separation from seal diet samples by visual inspection difficult.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the study assign otoliths to species?",{"text":80,"@type":76},"It uses otolith shape outline analyses combined with machine learning. An in vitro digestion experiment provides training data to discriminate eroded otoliths.",{"name":82,"@type":73,"acceptedAnswer":83},"What accuracy results does the machine learning model achieve?",{"text":84,"@type":76},"Known digested otoliths are self-assigned to their origin with over 90% accuracy, and 89% of otoliths collected from digestive tract samples can be assigned to species level.","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"]