{"id":"W4240944730","doi":"10.5194/hessd-6-7055-2009","title":"Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology – Part 1: Concepts and methodology","year":2009,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Genetic programming; Computer science; Support vector machine; Data mining; Evapotranspiration; Process (computing); Sampling (signal processing); Regression; Regression analysis; Machine learning; Artificial intelligence; Statistics; Mathematics","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":[0.00114262,0.0001689105,0.0004090047,0.00004054519,0.00003211173,0.000004796107,0.0006682338,0.0003237249,0.0001147322],"category_scores_gemma":[0.0002974524,0.0001206391,0.00003624539,0.00008412222,0.001624277,0.0001029434,0.002972835,0.0003538794,4.254346e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009007299,"about_ca_system_score_gemma":0.00002905132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001807939,"about_ca_topic_score_gemma":0.0001692907,"domain_scores_codex":[0.9977801,0.0008039062,0.0004931294,0.0005638769,0.0001876896,0.0001712489],"domain_scores_gemma":[0.998799,0.0002362846,0.000261523,0.0006566228,0.00001019434,0.00003633141],"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":[0.0001159294,0.000167698,0.06275053,0.00009441267,0.00004200525,0.000002058833,0.01400688,0.8377851,0.0819626,0.0005249252,0.0002089618,0.002338853],"study_design_scores_gemma":[0.0001548501,0.0002861038,0.00297255,0.0001456956,0.00002789386,0.000006938402,0.0003407117,0.857922,0.09617342,0.04177302,0.00001428423,0.0001825837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947077,0.00007482446,0.003007659,0.0002469748,0.0000588779,0.000453423,0.00003726986,0.00003413055,0.001379156],"genre_scores_gemma":[0.9484708,0.00001377871,0.05131081,0.0001235651,0.00001487476,0.00002333132,0.00002194101,0.000007142519,0.00001370313],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05977798,"threshold_uncertainty_score":0.5984717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1842041633704771,"score_gpt":0.3623999800340776,"score_spread":0.1781958166636005,"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."}}