{"id":"W3014107227","doi":"","title":"Machine Learning for Streamflow Prediction: Current Status and Future Prospects","year":2019,"lang":"en","type":"article","venue":"AGU Fall Meeting Abstracts","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Streamflow; Current (fluid); Computer science; Machine learning; Environmental science; Artificial intelligence; Geography; Engineering; Cartography; Drainage basin","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":[],"consensus_categories":[],"category_scores_codex":[0.0004381925,0.0001977291,0.0001828303,0.00002601743,0.000227328,0.00006835318,0.0001161939,0.000103114,0.00005598842],"category_scores_gemma":[0.0002314201,0.0001677736,0.00004837548,0.0001132064,0.00007488541,0.0001507728,0.0001224779,0.0003708185,0.0001775147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009637594,"about_ca_system_score_gemma":0.0000103454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007960727,"about_ca_topic_score_gemma":0.0002980706,"domain_scores_codex":[0.9984052,0.00003965686,0.0002663268,0.0004989397,0.0002782777,0.0005116101],"domain_scores_gemma":[0.9993167,0.0001519312,0.000163941,0.0001645339,0.00001383601,0.0001890454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003558372,0.00007257899,0.8850681,0.00005683084,0.000008893279,0.0000030263,0.0002819721,0.07993331,0.0008393424,0.00002268948,0.0001855482,0.03349208],"study_design_scores_gemma":[0.001204869,0.0006732712,0.6969492,0.00015864,0.00004077682,0.00002229495,0.00005089055,0.06280077,0.0003632853,0.0005826169,0.2366882,0.0004652766],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9884654,0.0004023348,0.000009873665,0.0002250759,0.0005384572,0.0004427573,0.00001385744,0.0001857103,0.009716496],"genre_scores_gemma":[0.9973206,0.000109731,0.001815804,0.00005676995,0.0002975861,0.00001918392,0.00003911445,0.00002564658,0.0003155598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2365026,"threshold_uncertainty_score":0.6841609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01184844199857864,"score_gpt":0.2307383291524525,"score_spread":0.2188898871538739,"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."}}