{"id":"W2166781611","doi":"10.1029/2006wr005142","title":"Flood frequency analysis at ungauged sites using artificial neural networks in canonical correlation analysis physiographic space","year":2007,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":176,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Canonical correlation; Jackknife resampling; Artificial neural network; Quantile; Generalization; Computer science; Ensemble forecasting; Artificial intelligence; Kriging; Machine learning; Mathematics; Data mining; Statistics; Estimator","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003704295,0.0002203357,0.0004961691,0.002061096,0.0006876488,0.0000895343,0.000441896,0.000287337,0.002348601],"category_scores_gemma":[0.00005589849,0.0001709925,0.0004956055,0.0114459,0.0006622568,0.0002062578,0.0004765003,0.0007640973,0.0001706457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003823657,"about_ca_system_score_gemma":0.00000560571,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0151916,"about_ca_topic_score_gemma":0.1321715,"domain_scores_codex":[0.9954478,0.000910131,0.0005602725,0.0007928478,0.001038231,0.001250686],"domain_scores_gemma":[0.9987896,0.0002829977,0.00008015297,0.0005672324,0.00003455739,0.0002454217],"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":[0.00008425592,0.00006537417,0.5526459,0.00000120559,0.0004140995,0.00005199996,0.0006301478,0.4371266,0.008877932,0.000007669716,0.000006242355,0.00008854607],"study_design_scores_gemma":[0.0001307784,0.00003960536,0.3551444,0.000001600681,0.0007761772,0.000001476549,0.00009406658,0.6423044,0.00102175,0.0002275811,0.00008490474,0.0001732048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954181,0.0001095082,0.002930359,0.0001940555,0.00001980913,0.0001661293,0.000003156466,0.00004067147,0.001118224],"genre_scores_gemma":[0.9992476,0.000009113636,0.0001926029,0.00003659885,0.00008241298,0.00000799484,0.0001086208,0.00002086615,0.0002941845],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2051778,"threshold_uncertainty_score":0.9985634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03547735419306032,"score_gpt":0.3162222556207778,"score_spread":0.2807449014277175,"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."}}