{"id":"W4408423613","doi":"10.5194/egusphere-egu25-3709","title":"Rapid and responsive water quality risk assessment using a hybrid machine learning integrated quantitative microbial risk assessment model","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Global Health Research; York University","funders":"","keywords":"Risk assessment; Quality assessment; Quality (philosophy); Computer science; Water quality; Risk analysis (engineering); Artificial intelligence; Machine learning; Engineering; Reliability engineering; Business; Evaluation methods; Biology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001240255,0.0009800773,0.0008818679,0.0004453199,0.0002868642,0.001085585,0.001418578,0.001533814,0.001839628],"category_scores_gemma":[0.002960055,0.0004988075,0.0008784563,0.0003292343,0.0005902678,0.0008352654,0.001044748,0.001378049,0.0002890986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001015656,"about_ca_system_score_gemma":0.001176403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01916459,"about_ca_topic_score_gemma":0.008626527,"domain_scores_codex":[0.9994934,0.0001332454,0.0000283587,0.0001720069,0.00009078444,0.00008219075],"domain_scores_gemma":[0.9984811,0.0009094611,0.0001735994,0.00004258296,0.0003302085,0.00006310235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002622865,0.00002978769,0.001260209,0.0000150636,0.00002015801,0.00003003968,0.00001425784,0.9919702,0.0002811334,0.0007715258,0.0002038487,0.005377614],"study_design_scores_gemma":[0.000001870533,0.000005912536,0.00007999795,0.000001129701,0.000002375674,0.000001889809,0.000001411991,0.999537,0.00004125536,0.0002856301,0.00003980127,0.00000171118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1771853,0.0008688198,0.8118045,0.001797606,0.0001210399,0.0001252651,0.0006748607,0.001383967,0.006038724],"genre_scores_gemma":[0.9691482,0.0001422311,0.02692313,0.0003178953,0.00004501136,0.0001616582,0.0003380498,0.00003330925,0.0028906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01916459,"threshold_uncertainty_score":0.03810608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06846360168078189,"score_gpt":0.3635391160496813,"score_spread":0.2950755143688994,"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."}}