{"id":"W4388907259","doi":"10.1016/j.jhydrol.2023.130504","title":"Using a physics-based hydrological model and storm transposition to investigate machine-learning algorithms for streamflow prediction","year":2023,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Streamflow; Computer science; Algorithm; Machine learning; Hindcast; Artificial neural network; Hydrological modelling; Artificial intelligence; Benchmarking; Data mining; Climatology; Drainage basin; Geology","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":[0.0005108308,0.0001204983,0.000224082,0.0001026373,0.0002316415,0.000008552638,0.00009586077,0.00008865267,0.0000154767],"category_scores_gemma":[0.00003569287,0.00009954996,0.0000702022,0.000156797,0.0001578129,0.0001465499,0.00005834536,0.0001905333,0.000009410227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005413265,"about_ca_system_score_gemma":0.000007340902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002051674,"about_ca_topic_score_gemma":0.00001995026,"domain_scores_codex":[0.9990794,0.00008136602,0.0002509477,0.0001908604,0.0001351211,0.0002623173],"domain_scores_gemma":[0.9996316,0.00006884837,0.0001303213,0.0000584015,0.00001166394,0.00009912714],"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":[0.0002081219,0.00003491104,0.02938055,0.000009107589,0.00004159993,0.00001763201,0.0004187569,0.9561977,0.01249045,0.0000209648,0.0001418505,0.001038287],"study_design_scores_gemma":[0.0008393797,0.000981831,0.006317384,0.000007830262,0.00009375661,0.00001865775,0.00001449592,0.9859166,0.0004873133,0.004882324,0.0003552052,0.00008527281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9260789,0.00001707022,0.07105746,0.002498207,0.00009592367,0.0001652434,0.00001232236,0.00003365238,0.00004124542],"genre_scores_gemma":[0.9916483,0.000026778,0.007281502,0.0009031766,0.0000744192,0.00001204831,0.000009048962,0.00001100624,0.00003375019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0655694,"threshold_uncertainty_score":0.405953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04420554298186091,"score_gpt":0.2713726334938387,"score_spread":0.2271670905119778,"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."}}