{"id":"W2064720685","doi":"10.1111/jawr.12259","title":"Development and Operational Testing of a Super‐Ensemble Artificial Intelligence Flood‐Forecast Model for a Pacific Northwest River","year":2014,"lang":"en","type":"article","venue":"JAWRA Journal of the American Water Resources Association","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Forests; University of British Columbia","funders":"","keywords":"Flood forecasting; Flood myth; Snowmelt; Environmental science; Meteorology; Storm; Streamflow; Probabilistic logic; Climatology; Hydrological modelling; Ensemble forecasting; Computer science; Geography; Geology; Drainage basin; Snow; Artificial intelligence; Cartography","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":[],"consensus_categories":[],"category_scores_codex":[0.0008856758,0.00008571341,0.0001882617,0.00003992066,0.0002571907,0.0000232195,0.0001528725,0.00002262899,0.00000541281],"category_scores_gemma":[0.0001493911,0.00005091248,0.00005338336,0.00009806834,0.0001707395,0.0001125762,0.0001356942,0.00008167395,0.000004091004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001111195,"about_ca_system_score_gemma":0.000005435023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000768244,"about_ca_topic_score_gemma":0.0001037164,"domain_scores_codex":[0.999036,0.0000746669,0.0003494721,0.0001086338,0.0002570999,0.0001741322],"domain_scores_gemma":[0.9992962,0.0001117471,0.0004514197,0.00006519878,0.00004576662,0.00002959118],"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":[0.0001695553,0.0001218292,0.7862932,0.00001800833,0.0001913126,6.649404e-7,0.03675905,0.124055,0.01126581,0.00005853231,0.0002761041,0.04079089],"study_design_scores_gemma":[0.0006427953,0.0007461882,0.3166142,0.00008702927,0.0002875343,0.00001915094,0.003013243,0.6193841,0.03791984,0.009009944,0.01174918,0.0005268474],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.989122,0.000003773408,0.009409321,0.001184506,0.00004103857,0.0001026656,0.000002453338,0.000003494152,0.0001307178],"genre_scores_gemma":[0.9878321,0.000003810924,0.01178608,0.0001617886,0.00004575275,0.000005442446,0.000001338668,0.000006055444,0.000157588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4953291,"threshold_uncertainty_score":0.2076151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02007101152506559,"score_gpt":0.2190890573552585,"score_spread":0.1990180458301929,"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."}}