{"id":"W4383069805","doi":"10.1139/cjfas-2023-0045","title":"The future of fish age estimation: deep machine learning coupled with Fourier transform near-infrared spectroscopy of otoliths","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Marine Fisheries Service; National Oceanic and Atmospheric Administration","keywords":"Otolith; Mean squared error; Fourier transform; Pattern recognition (psychology); Artificial intelligence; Biological system; Data set; Mathematics; Convolutional neural network; Absorbance; Partial least squares regression; Statistics; Fish <Actinopterygii>; Computer science; Fishery; Biology; Optics; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003934982,0.0001068202,0.000275624,0.0001295649,0.0005246682,0.0001607014,0.000281378,0.00004426128,0.0003166123],"category_scores_gemma":[0.0001754427,0.00006505851,0.00006508624,0.0009771341,0.0009882289,0.0001755196,0.000006294899,0.0001721996,3.301585e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002888394,"about_ca_system_score_gemma":0.0005857395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001374918,"about_ca_topic_score_gemma":0.01391949,"domain_scores_codex":[0.9989655,0.00001386873,0.0003459116,0.0001024563,0.0003172192,0.0002550491],"domain_scores_gemma":[0.9991254,0.000216041,0.0003140169,0.00009433585,0.00006067846,0.0001895089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009702705,0.000159902,0.7663797,0.001778214,0.002344132,0.0009800772,0.04531821,0.01069679,0.0129298,0.003167397,0.01666488,0.1386106],"study_design_scores_gemma":[0.004521878,0.004026867,0.03371671,0.0008958657,0.00131381,0.0007023351,0.1058651,0.6844553,0.07717331,0.01697483,0.06893212,0.001421903],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903362,0.001844452,0.0003397816,0.003368139,0.00007925851,0.00004424983,0.000009674657,0.000007020373,0.003971247],"genre_scores_gemma":[0.9963112,0.0004273008,0.002331134,0.00005126531,0.00007391876,0.000001712031,0.000003877582,0.000008000067,0.0007915951],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.732663,"threshold_uncertainty_score":0.77674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01073933628413983,"score_gpt":0.2347406451123615,"score_spread":0.2240013088282216,"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."}}