{"corpus_id":238226987,"paper_sha":"81cbc4a42e2d1296a33311bca0f578d685a2fe2a","doi":null,"arxiv_id":"2109.14737","pmid":null,"pmcid":null,"mag_id":null,"dblp_id":"journals/corr/abs-2109-14737","acl_id":null,"title":"Unlocking the potential of deep learning for marine ecology: overview, applications, and outlook","year":2021,"publication_date":"2021-09-29","venue":"arXiv.org","journal":{"name":"ArXiv","pages":null,"volume":"abs/2109.14737"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle","Review"],"pubmed_pub_types":null,"s2_fields_of_study":["Computer Science","Environmental Science"],"reference_count":128,"citation_count":36,"influential_citation_count":3,"is_open_access":false,"arxiv_categories":["cs.LG","cs.AI","cs.CV"],"arxiv_license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"The deep learning revolution is touching all scientific disciplines and corners of our lives as a means of harnessing the power of big data. Marine ecology is no exception. These new methods provide analysis of data from sensors, cameras, and acoustic recorders, even in real time, in ways that are reproducible and rapid. Off-the-shelf algorithms can find, count, and classify species from digital images or video and detect cryptic patterns in noisy data. Using these opportunities requires collaboration across ecological and data science disciplines, which can be challenging to initiate. To facilitate these collaborations and promote the use of deep learning towards ecosystem-based management of the sea, this paper aims to bridge the gap between marine ecologists and computer scientists. We provide insight into popular deep learning approaches for ecological data analysis in plain language, focusing on the techniques of supervised learning with deep neural networks, and illustrate challenges and opportunities through established and emerging applications of deep learning to marine ecology. We use established and future-looking case studies on plankton, fishes, marine mammals, pollution, and nutrient cycling that involve object detection, classification, tracking, and segmentation of visualized data. We conclude with a broad outlook of the field's opportunities and challenges, including potential technological advances and issues with managing complex data sets.","claims":[{"public_id":"cl_68d332a179706c20b2af64f1718331ce","status":"active","text":"Applying deep learning in marine ecology requires cross-disciplinary collaboration between ecologists and data scientists, which can be challenging to initiate.","confidence":0.8,"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/claims/cl_68d332a179706c20b2af64f1718331ce"},{"public_id":"cl_e639afae8914018b8104f2563a7db921","status":"active","text":"Off-the-shelf deep learning algorithms can find, count, and classify species from digital images or video, and detect cryptic patterns in noisy marine ecology data.","confidence":0.85,"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/claims/cl_e639afae8914018b8104f2563a7db921"}],"concepts":[{"public_id":"co_01220349990a35f4a91d3cd1d0db0d5d","status":"active","name":"tracking","description":"A computer vision task of following identified organisms or objects across video frames, listed as a key deep learning application in marine ecology.","types":["method","task"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_01220349990a35f4a91d3cd1d0db0d5d"},{"public_id":"co_555b3f8f413c85968910b58f651f1786","status":"active","name":"supervised learning with deep neural networks","description":"A machine learning paradigm where deep neural networks are trained on labeled examples, identified in this paper as the primary technical focus for marine ecological data analysis.","types":["method"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_555b3f8f413c85968910b58f651f1786"},{"public_id":"co_65f622bb64bfcab3078992886079320f","status":"active","name":"ecosystem-based management","description":"A marine resource management approach considering whole-ecosystem dynamics, identified here as the motivating goal for applying deep learning to the sea.","types":["management approach"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_65f622bb64bfcab3078992886079320f"},{"public_id":"co_6c85cc8eed3cb412ac5fedec8ab7844c","status":"active","name":"deep learning","description":"A class of machine learning methods using multi-layered neural networks to analyze large datasets from sensors, cameras, and acoustic recorders in marine ecological contexts.","types":["method"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_6c85cc8eed3cb412ac5fedec8ab7844c"},{"public_id":"co_7ee3c6c93bf45722fd339b9db2507ddd","status":"active","name":"plankton","description":"Microscopic marine organisms used as an established case study for deep learning object detection and classification applications.","types":["organism group","case study subject"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_7ee3c6c93bf45722fd339b9db2507ddd"},{"public_id":"co_919bbd887b27b185a12c2d7e7de59fa4","status":"active","name":"nutrient cycling","description":"The biogeochemical process of nutrient movement through marine ecosystems, used as a case study for detecting cryptic patterns with deep learning.","types":["ecological phenomenon","case study subject"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_919bbd887b27b185a12c2d7e7de59fa4"},{"public_id":"co_93193d9fbfbb27c667cd1a27abe7f7ab","status":"active","name":"marine ecology","description":"The scientific discipline studying marine organisms and their interactions with the sea environment, serving as the application domain for deep learning methods reviewed here.","types":["scientific field"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_93193d9fbfbb27c667cd1a27abe7f7ab"},{"public_id":"co_98a1275dfb93f1ab21afaf95ae4c7ba7","status":"active","name":"marine mammals","description":"Aquatic mammals used as a case study for deep learning detection, tracking, and monitoring in marine ecology.","types":["organism group","case study subject"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_98a1275dfb93f1ab21afaf95ae4c7ba7"},{"public_id":"co_b09dc8f38ecb4dfabb66cfe6ae62a886","status":"active","name":"classification","description":"A machine learning task of assigning category labels to data items, applied here to identify marine species from visual data.","types":["method","task"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_b09dc8f38ecb4dfabb66cfe6ae62a886"},{"public_id":"co_c767fcd55152f62f9a0243bab64b0d5d","status":"active","name":"acoustic recorders","description":"Sensor devices that capture underwater sound data, listed as a primary data source for deep learning analysis in marine ecological monitoring.","types":["data collection technology"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_c767fcd55152f62f9a0243bab64b0d5d"},{"public_id":"co_d57e15c8c4a8d384f6db5bf748df618e","status":"active","name":"object detection","description":"A computer vision task for locating and identifying organisms or objects within images or video, applied here to marine ecological data.","types":["method","task"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_d57e15c8c4a8d384f6db5bf748df618e"},{"public_id":"co_f0ffbb90c10653a8c5aece63bfd22be3","status":"active","name":"segmentation","description":"An image analysis task that partitions visual data into labeled regions, applied here to marine ecological imaging data.","types":["method","task"],"aliases":[],"contributors":[{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["extraction"],"url":"https://sah.borca.ai/u/b9tnx83g25"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_f0ffbb90c10653a8c5aece63bfd22be3"}],"external_ids":{"DOI":null,"ArXiv":"2109.14737","PubMed":null,"PubMedCentral":null,"MAG":null,"DBLP":"journals/corr/abs-2109-14737","ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://arxiv.org/pdf/2109.14737","landing_url":"https://arxiv.org/abs/2109.14737","source":"arxiv","pdf_url_source":"derived_arxiv","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":true,"full_text_source":"arxiv","count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":631910,"paper_uid":"1dba505f-eddf-416a-b7cd-523ffa924e0c","canonical_identity":{"paper_id":631910,"paper_uid":"1dba505f-eddf-416a-b7cd-523ffa924e0c","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/238226987"}