{"id":"W4360619298","doi":"10.5194/hess-2023-69","title":"Advancement of a blended hydrologic model for robust model performance","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Overfitting; Calibration; Computer science; Evapotranspiration; Process (computing); Hydrological modelling; Statistics; Mathematics; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002453331,0.0008945406,0.0007173308,0.0005888459,0.0005473387,0.00141087,0.001898983,0.001099764,0.001997233],"category_scores_gemma":[0.007719973,0.0005384209,0.00108364,0.0005358464,0.0005604754,0.001953336,0.001881315,0.002058066,0.0004601993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000956838,"about_ca_system_score_gemma":0.001409988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007244544,"about_ca_topic_score_gemma":0.005302636,"domain_scores_codex":[0.9993016,0.0002536133,0.0000603501,0.0001275002,0.0002005414,0.00005645186],"domain_scores_gemma":[0.9977549,0.0008389262,0.0002385042,0.0004416025,0.0006230127,0.0001030965],"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":[0.00008438818,0.00008973562,0.003565836,0.00001940204,0.00004938221,0.00002641153,0.00002943052,0.9804731,0.002805335,0.00221489,0.0003518365,0.01029027],"study_design_scores_gemma":[0.000009399717,0.00001078665,0.0001629182,0.000001739559,0.000003785556,0.000002782608,0.000002865519,0.9985611,0.00065454,0.0004493603,0.0001374044,0.000003391995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3626939,0.00008771053,0.6282975,0.0006101186,0.00006626334,0.0002516276,0.0007076297,0.002227667,0.005057521],"genre_scores_gemma":[0.86835,0.00002604327,0.1298409,0.00007710457,0.00001170162,0.000199914,0.0005360148,0.0002417557,0.0007166531],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007244544,"threshold_uncertainty_score":0.01440477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07196563641021468,"score_gpt":0.2620071404730228,"score_spread":0.1900415040628081,"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."}}