{"id":"W4383100035","doi":"10.1017/eds.2023.11","title":"A novel workflow for streamflow prediction in the presence of missing gauge observations","year":2023,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"DeepMind","keywords":"Streamflow; Missing data; Imputation (statistics); Categorical variable; Flood forecasting; Computer science; Warning system; Leverage (statistics); Flood myth; Regression; Econometrics; Environmental science; Data mining; Statistics; Artificial intelligence; Machine learning; Drainage basin; Cartography; Mathematics; Geography","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":[0.001414756,0.00008945051,0.00008575959,0.00006171344,0.0004016732,0.0000230455,0.001288501,0.00002431823,0.00008515612],"category_scores_gemma":[0.0001402553,0.00006757124,0.00001819448,0.0006883963,0.001209989,0.001019076,0.001057374,0.00006709756,0.0000703453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005811924,"about_ca_system_score_gemma":0.000006223773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001065651,"about_ca_topic_score_gemma":0.00007131995,"domain_scores_codex":[0.9986134,0.0000265304,0.0001893705,0.0004512588,0.0004125482,0.0003069409],"domain_scores_gemma":[0.9990992,0.0001633594,0.00006175671,0.0006437967,0.000001022278,0.00003085893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004875231,0.0006539229,0.6895135,0.00003197447,0.00002055559,0.000009491977,0.004292204,0.01657093,0.2436085,0.0007662626,0.02294603,0.02153782],"study_design_scores_gemma":[0.0002789336,0.00004985119,0.9290227,0.00001431068,0.0000135162,0.000002407299,0.0005469973,0.06202416,0.0007057315,0.0009798239,0.006267352,0.00009420473],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9905279,0.00001754855,0.004702895,0.002017461,0.0001744162,0.0006997561,0.0008775856,0.00003266739,0.00094982],"genre_scores_gemma":[0.9948032,0.00003767225,0.004485674,0.0001661428,0.00001611981,0.0000566115,0.0002568825,0.000004830419,0.0001728661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2429028,"threshold_uncertainty_score":0.4458257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06838411252735653,"score_gpt":0.2704303668683858,"score_spread":0.2020462543410292,"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."}}