{"id":"W3168508202","doi":"10.5194/egusphere-egu21-13303","title":"Improving hydrological forecasts through temporal hierarchal reconciliation","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mean squared error; Precipitation; Ordinary least squares; Mean absolute error; Exponential smoothing; Statistics; Environmental science; Moving average; Climatology; Econometrics; Meteorology; Mathematics; Computer science; Geology; Geography","routes":{"ca_aff":true,"ca_fund":false,"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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003159695,0.000149113,0.0001732211,0.00001012721,0.0001748687,0.00004352536,0.0001645707,0.0001487644,0.01060676],"category_scores_gemma":[0.000394884,0.0001177502,0.0000820135,0.0002713746,0.0001852079,0.0002786229,0.0003488035,0.0002136099,0.0009761514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001570095,"about_ca_system_score_gemma":0.00001886903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000409034,"about_ca_topic_score_gemma":0.0002266128,"domain_scores_codex":[0.9984014,0.0001113172,0.0002585143,0.0005222716,0.0003004915,0.0004060032],"domain_scores_gemma":[0.999476,0.00008265534,0.00007470716,0.0002510893,0.0000131385,0.0001024245],"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":[0.0001944412,0.001009421,0.2587364,0.00004265462,0.00006372632,0.001120967,0.001927137,0.04360403,0.1662858,0.006841131,0.01485827,0.505316],"study_design_scores_gemma":[0.002367595,0.001303365,0.03255922,0.00003060825,0.00006583533,0.0008123081,0.0001227042,0.6815965,0.07437456,0.09609616,0.1087859,0.001885308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9225953,0.00001650616,0.009864277,0.001288877,0.0001715406,0.00009385947,0.000001905177,0.0001828824,0.06578481],"genre_scores_gemma":[0.9637564,0.000002762136,0.03180913,0.001663332,0.00007385029,0.000009557257,0.00001888707,0.00001158661,0.00265453],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6379924,"threshold_uncertainty_score":0.9998017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03255078774589145,"score_gpt":0.2471948996179172,"score_spread":0.2146441118720258,"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."}}