{"id":"W3139251132","doi":"10.1016/j.watres.2021.117073","title":"Machine learning for anomaly detection in cyanobacterial fluorescence signals","year":2021,"lang":"en","type":"article","venue":"Water Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Anomaly detection; Fluorescence; Anomaly (physics); Artificial intelligence; Environmental science; Chemistry; Computer science; Physics; Optics","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":[0.0007971219,0.00007850794,0.000121339,0.00009516619,0.0001431235,0.00004815104,0.000102406,0.00007621547,0.00005432146],"category_scores_gemma":[0.0002793097,0.00006240381,0.00005121371,0.0001304832,0.0000450943,0.000003137041,0.0002162211,0.000158725,0.00001093813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000181217,"about_ca_system_score_gemma":0.00003407392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000692704,"about_ca_topic_score_gemma":0.0002203974,"domain_scores_codex":[0.9988161,0.0001845424,0.0001370468,0.0003221486,0.0001397297,0.0004004796],"domain_scores_gemma":[0.9995944,0.00001189428,0.00001302516,0.0001552053,0.0001847865,0.00004070675],"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":[0.0001668823,0.00003492244,0.001991545,0.00001886073,0.00002025698,0.000006781261,0.00004224692,0.00001313662,0.9950985,0.00002955627,0.00003241501,0.002544861],"study_design_scores_gemma":[0.0004686229,0.0002290801,0.001461267,0.000004425051,0.000002333316,0.000004853009,0.00004082242,0.0001675617,0.9422505,0.0001933604,0.05509755,0.00007962679],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.998156,0.0004563153,0.0005278609,0.0002346663,0.0001093731,0.0001728715,0.00000714361,0.000004879889,0.000330857],"genre_scores_gemma":[0.9969641,0.0004316231,0.0003165195,0.00001677001,0.0002377161,0.00007000168,0.0000885098,0.00001448554,0.001860284],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05506514,"threshold_uncertainty_score":0.2544754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03799573000792498,"score_gpt":0.3248480890477717,"score_spread":0.2868523590398467,"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."}}