{"id":"W6902300300","doi":"10.6084/m9.figshare.3363421","title":"On the importance of training methods and ensemble aggregation for runoff prediction by means of artificial neural networks","year":2016,"lang":"en","type":"article","venue":"Figshare","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Metaheuristic; Training (meteorology); Point (geometry); Ensemble forecasting; Training set","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005799114,0.0005573212,0.0006687307,0.0006390063,0.000320912,0.002157102,0.0008190165,0.0009745377,0.001809109],"category_scores_gemma":[0.01859332,0.0001439032,0.0003557529,0.0009742067,0.0005508589,0.002198223,0.0005551941,0.001697356,0.0005650653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004710037,"about_ca_system_score_gemma":0.0004453729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000930868,"about_ca_topic_score_gemma":0.001501209,"domain_scores_codex":[0.9983366,0.0008560517,0.00009446904,0.0001733946,0.0005015041,0.00003796267],"domain_scores_gemma":[0.9875896,0.008781754,0.0004598263,0.0004405547,0.002576076,0.0001521725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002012012,0.00008100909,0.003616797,0.0006412194,0.0001471643,0.0002719003,0.0002151701,0.1162647,0.003734798,0.02753635,0.04519674,0.802093],"study_design_scores_gemma":[0.00004675875,0.0002613376,0.007132772,0.0005587362,0.0001577065,0.0004470442,0.00044623,0.8021547,0.00757249,0.04653936,0.1345849,0.0000980478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0377472,0.04571608,0.8264331,0.03077032,0.02076848,0.0002280632,0.0001513453,0.0005768395,0.03760849],"genre_scores_gemma":[0.4714953,0.04754213,0.4126163,0.003926921,0.03805073,0.0002674772,0.0002435217,0.0004205919,0.02543702],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005799114,"threshold_uncertainty_score":0.03066903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07462841217960606,"score_gpt":0.2986689211280119,"score_spread":0.2240405089484058,"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."}}