{"id":"W4293124670","doi":"10.3389/fmars.2022.842946","title":"Machine learning applied to big data from marine cabled observatories: A case study of sablefish monitoring in the NE Pacific","year":2022,"lang":"en","type":"article","venue":"Frontiers in Marine Science","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ocean Networks Canada Society; University of Victoria","funders":"Agencia Estatal de Investigación; Horizon 2020 Framework Programme","keywords":"Canyon; Artificial intelligence; Remotely operated vehicle; Pipeline (software); Computer science; Tracking (education); Remote sensing; Oceanography; Geology; Cartography; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.004123943,0.0002186084,0.0003776168,0.000239813,0.0005390396,0.0001015159,0.004076076,0.00003631742,0.0000830573],"category_scores_gemma":[0.0005367108,0.000190258,0.00001839171,0.004109612,0.0003977886,0.0003623963,0.01640809,0.0007310948,0.00000491242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005169557,"about_ca_system_score_gemma":0.00004592174,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04836264,"about_ca_topic_score_gemma":0.002044751,"domain_scores_codex":[0.9963428,0.0002603462,0.0005659846,0.001019796,0.001240984,0.0005701259],"domain_scores_gemma":[0.997768,0.0001439178,0.000182304,0.00181973,0.00001159182,0.00007449068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005182026,0.0002538413,0.9508521,0.000004803845,0.000005277697,0.0003275748,0.007484569,0.01316181,0.0008016872,0.000003159647,0.0002059409,0.02684741],"study_design_scores_gemma":[0.001174028,0.0003783816,0.7712257,0.00001108601,0.00001747426,0.00003948375,0.2164831,0.004499532,0.0009769381,0.001516821,0.00323216,0.0004452668],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969827,0.000008864147,0.0001450598,0.0001443593,0.001269254,0.0007085967,0.00001979814,0.00007772862,0.0006436653],"genre_scores_gemma":[0.9729061,0.000006346521,0.02669789,0.00001635549,0.00005172511,0.0001637292,0.00001419167,0.00001591647,0.0001277291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2089986,"threshold_uncertainty_score":0.991547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06627645186583264,"score_gpt":0.2702044436757654,"score_spread":0.2039279918099328,"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."}}