{"id":"W3092278000","doi":"10.5194/hess-25-2543-2021","title":"Resampling and ensemble techniques for improving ANN-based high-flow forecast accuracy","year":2021,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Resampling; Boosting (machine learning); Computer science; Random forest; Oversampling; Undersampling; AdaBoost; Artificial neural network; Ensemble learning; Machine learning; Regression; Data mining; Artificial intelligence; Jackknife resampling; Statistics; Mathematics; Support vector machine; Estimator","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001237443,0.0001524953,0.0002405059,0.00004675676,0.0008604993,0.0001066431,0.0001558804,0.0001458149,0.00004858299],"category_scores_gemma":[0.0003289163,0.0001218391,0.00003647624,0.0002433012,0.0007888138,0.0001949772,0.0001588307,0.0001077915,0.00001214833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001820228,"about_ca_system_score_gemma":0.00003386613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002356109,"about_ca_topic_score_gemma":0.0001560253,"domain_scores_codex":[0.9983743,0.0001164107,0.0002421336,0.000644439,0.0001726105,0.0004500488],"domain_scores_gemma":[0.9990802,0.0005084957,0.0001225553,0.000158909,0.00001767559,0.0001122021],"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":[0.0003736444,0.0002367137,0.1483336,0.0009937203,0.00005150725,0.0002609467,0.001229474,0.1147416,0.2027405,0.005288676,0.0005308736,0.5252187],"study_design_scores_gemma":[0.0004392553,0.0007310797,0.004746629,0.0000874128,0.00002987911,0.0002866895,0.00009882234,0.9706325,0.01915128,0.001549277,0.001912396,0.0003348184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9843109,0.0001675309,0.01302075,0.0006670989,0.0001472533,0.0002504344,0.000009078261,0.0001297627,0.001297227],"genre_scores_gemma":[0.9524569,0.000004319062,0.04702238,0.0003693076,0.00005178524,0.00003158966,0.000003979271,0.000007186504,0.00005256371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8558909,"threshold_uncertainty_score":0.6618352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02644895765558115,"score_gpt":0.2512165177998116,"score_spread":0.2247675601442304,"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."}}