{"id":"W4389242199","doi":"10.1093/plankt/fbad048","title":"Automatic estimation of lipid content from <i>in situ</i> images of Arctic copepods using machine learning","year":2023,"lang":"en","type":"article","venue":"Journal of Plankton Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Sorbonne Université; Agence Nationale de la Recherche; Université Laval","keywords":"Trophic level; Arctic; Marine ecosystem; Plankton; Copepod; The arctic; Computer science; Ecosystem; In situ; Convolutional neural network; Environmental science; Ecology; Oceanography; Artificial intelligence; Biology; Meteorology; Geology; Geography; Crustacean","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001839036,0.00007844747,0.0003172196,0.00037786,0.00004614444,0.00001390619,0.0001651679,0.00006108308,0.00002793687],"category_scores_gemma":[0.001107279,0.00006446253,0.00008340825,0.0003485687,0.00008961235,0.00000776019,0.0001287715,0.0002829031,0.000001701086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002726884,"about_ca_system_score_gemma":0.0000985661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002798458,"about_ca_topic_score_gemma":0.00003623262,"domain_scores_codex":[0.9985276,0.0002473147,0.0004982192,0.0001130215,0.0004137047,0.0002001255],"domain_scores_gemma":[0.9989877,0.0001824688,0.0003185858,0.0001185199,0.0003465568,0.00004618793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001206962,0.00005762835,0.02294511,0.0000926058,0.0001034181,0.00001508778,0.00009689936,0.001725966,0.9731911,0.00001311092,0.0001764115,0.001461982],"study_design_scores_gemma":[0.001296314,0.0009115509,0.0630631,0.0002748052,0.00003447122,0.00002522846,0.0005689517,0.02219718,0.9107456,0.0002280566,0.0005459981,0.000108807],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975679,0.001726411,0.0002888608,0.0001222042,0.00008699432,0.00008408183,0.00002462226,0.000002073745,0.00009688437],"genre_scores_gemma":[0.9953958,0.001394043,0.003003734,0.000005454161,0.00007919769,0.000001299778,0.00002586574,0.000009922139,0.00008461822],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06244554,"threshold_uncertainty_score":0.2628706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07933553144616441,"score_gpt":0.3638868094755514,"score_spread":0.284551278029387,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}