{"id":"W4379094320","doi":"10.1016/j.watres.2023.120075","title":"Predicting microbial water quality in on-site water reuse systems with online sensors","year":2023,"lang":"en","type":"article","venue":"Water Research","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Eidgenössische Anstalt für Wasserversorgung Abwasserreinigung und Gewässerschutz; Japan Society for the Promotion of Science; Eidgenössische Technische Hochschule Zürich","keywords":"Reuse; Water quality; Random forest; Support vector machine; Constant false alarm rate; Computer science; Environmental science; Logistic regression; Data mining; Machine learning; Artificial intelligence; Engineering; Waste management; Ecology","routes":{"ca_aff":true,"ca_fund":false,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00522118,0.0002511792,0.0003024966,0.0004160516,0.0003021771,0.0001918702,0.001044871,0.0002070305,0.0001443474],"category_scores_gemma":[0.0001233918,0.0001215144,0.00004508672,0.0004398653,0.0005275065,0.0002477478,0.002707149,0.00093195,0.008104219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004755203,"about_ca_system_score_gemma":0.000006466426,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01015607,"about_ca_topic_score_gemma":0.0005497997,"domain_scores_codex":[0.9947478,0.0008567587,0.0004973084,0.0008150165,0.00128482,0.001798287],"domain_scores_gemma":[0.9984043,0.00007598921,0.00002155864,0.001339774,0.00003836148,0.0001200228],"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":[0.0002177385,0.0001524555,0.2261585,0.0000929228,0.00001766154,0.0002784603,0.01084654,0.00629203,0.754501,0.000004571416,0.001367275,0.00007089982],"study_design_scores_gemma":[0.0006914922,0.0002650749,0.03314621,0.0001232147,0.000003038151,0.00001230587,0.001576574,0.0004245949,0.9584644,0.0002168053,0.004746475,0.0003297715],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941996,0.000001924304,0.000001307003,0.004209053,0.0001915808,0.0005866097,0.00003051738,0.0005409596,0.0002384939],"genre_scores_gemma":[0.9940156,0.000007159726,0.0001454633,0.00001850151,0.0001351616,0.00007443342,0.0001284962,0.00005401485,0.005421137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2039635,"threshold_uncertainty_score":0.9964354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1281664055121099,"score_gpt":0.3689069588138424,"score_spread":0.2407405533017326,"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."}}