{"id":"W4256238924","doi":"10.5194/hess-2020-430","title":"Resampling and ensemble techniques for improving ANN-based high streamflow forecast accuracy","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"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; AdaBoost; Flood forecasting; Random forest; Streamflow; Machine learning; Artificial neural network; Ensemble learning; Artificial intelligence; Ensemble forecasting; Bootstrap aggregating; Data mining; Undersampling; Flood myth; Support vector machine","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004658524,0.0004161659,0.0004366026,0.00005025527,0.0002460963,0.000195492,0.0004524241,0.0004231909,0.0002858145],"category_scores_gemma":[0.001000578,0.0003565486,0.0001367577,0.0001187218,0.0002128654,0.0001040089,0.001504554,0.0005440971,0.00002699097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001916051,"about_ca_system_score_gemma":0.00004260583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002078081,"about_ca_topic_score_gemma":0.0001273978,"domain_scores_codex":[0.9975927,0.00005136882,0.0004136311,0.001153684,0.0002820607,0.000506484],"domain_scores_gemma":[0.998513,0.0005092098,0.0002704558,0.0004672965,0.00002100575,0.000219022],"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":[0.0005222473,0.0003072388,0.008066865,0.001426354,0.00007623457,0.00005532322,0.0004277133,0.09334195,0.129365,0.0004396537,0.006564103,0.7594073],"study_design_scores_gemma":[0.0005696351,0.000684869,0.001388002,0.0002191713,0.0001141273,0.000008877067,0.00001514471,0.8846305,0.07278968,0.03391049,0.004471922,0.001197548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6758416,0.00002965146,0.3156271,0.002611894,0.0002114193,0.00179712,0.0001271694,0.0009491043,0.002804965],"genre_scores_gemma":[0.7174119,0.000003518868,0.2814616,0.0006729101,0.0001137708,0.0001413546,0.00007425982,0.00004414772,0.00007647291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7912886,"threshold_uncertainty_score":0.9998887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04604312162746976,"score_gpt":0.2797162340773093,"score_spread":0.2336731124498396,"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."}}