{"id":"W4229447720","doi":"10.1029/2021wr031862","title":"Temporal Hierarchical Reconciliation for Consistent Water Resources Forecasting Across Multiple Timescales: An Application to Precipitation Forecasting","year":2022,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exponential smoothing; Benchmark (surveying); Computer science; Precipitation; Autoregressive integrated moving average; Econometrics; Moving average; Artificial neural network; Scaling; Smoothing; Climatology; Time series; Environmental science; Meteorology; Machine learning; Mathematics; Geography; Geology","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.007393098,0.0002822053,0.0003082177,0.0001987257,0.003149555,0.0003018718,0.0008436434,0.0001417669,0.0006199724],"category_scores_gemma":[0.0008628607,0.0002048184,0.0001288276,0.0004755984,0.000427354,0.0002911432,0.001765386,0.0007268398,0.0002566444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007448127,"about_ca_system_score_gemma":0.00001001161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001132003,"about_ca_topic_score_gemma":0.0005429756,"domain_scores_codex":[0.9938741,0.001052187,0.0006844859,0.001215087,0.001527627,0.00164647],"domain_scores_gemma":[0.998096,0.000716341,0.0001015197,0.0005644067,0.0001153425,0.0004063947],"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":[0.002395534,0.000609476,0.05561955,0.0001185872,0.0000454115,0.00002748344,0.1839582,0.4995485,0.1342292,0.000006886482,0.001244044,0.1221971],"study_design_scores_gemma":[0.001114447,0.002088094,0.001984176,0.00002962034,0.00001266815,0.00005118269,0.002299695,0.7579233,0.01610048,0.001829615,0.2160149,0.0005517941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934748,0.000007164921,0.002017593,0.001457154,0.00009327538,0.00212572,0.00008286072,0.0001652881,0.0005761484],"genre_scores_gemma":[0.9893465,3.029033e-7,0.006355137,0.0002325462,0.0002256721,0.001845765,0.0003598534,0.00007412633,0.001560086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2583748,"threshold_uncertainty_score":0.9981482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1084761380527273,"score_gpt":0.3383844023989326,"score_spread":0.2299082643462054,"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."}}