{"id":"W4400997048","doi":"10.2139/ssrn.4905294","title":"Advancing Machine Learning-Based Streamflow Prediction Through Event Greedy Sampling, Asymmetric Loss Function, and Rainfall Forecasting Uncertainty","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Streamflow; Event (particle physics); Computer science; Sampling (signal processing); Function (biology); Artificial intelligence; Machine learning; Econometrics; Mathematics; Geography; Cartography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003975351,0.0006266353,0.0005208222,0.0002487709,0.0007970023,0.000252051,0.0004303526,0.0004611498,0.0001574693],"category_scores_gemma":[0.000906188,0.0005496877,0.0003178958,0.0006624628,0.0002448908,0.0001783004,0.001031781,0.009810182,0.00006103834],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003969587,"about_ca_system_score_gemma":0.0009180896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001470882,"about_ca_topic_score_gemma":0.002908482,"domain_scores_codex":[0.9940364,0.0003208604,0.0008382938,0.001115561,0.0008455918,0.002843292],"domain_scores_gemma":[0.9984993,0.0002460638,0.0006428915,0.0003207323,0.00005591614,0.0002350759],"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":[0.0001272715,0.0001112475,0.03243053,0.00008051657,0.0001984177,0.00001796559,0.0001249049,0.9418129,0.00003930119,0.0007225378,0.0000614723,0.02427295],"study_design_scores_gemma":[0.0008139619,0.0015257,0.00181146,0.0003811232,0.000346378,0.0006822015,0.0000704162,0.564236,0.000007334529,0.4267378,0.002785411,0.000602276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8265201,0.004840395,0.1640719,0.0009941382,0.001336784,0.0005437767,0.00004278194,0.000399049,0.001251046],"genre_scores_gemma":[0.9960508,0.0009830624,0.001688646,0.0001523699,0.0005467753,0.00002589707,0.0001018443,0.0001008372,0.0003497592],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4260153,"threshold_uncertainty_score":0.999854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01554636131830269,"score_gpt":0.2487518274038975,"score_spread":0.2332054660855948,"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."}}