{"id":"W4407944493","doi":"10.1080/02626667.2025.2471430","title":"Improving multi-model ensemble streamflow forecasts by combining lumped, distributed and deep learning hydrological models","year":2025,"lang":"en","type":"article","venue":"Hydrological Sciences Journal","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Université du Québec","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Streamflow; Ensemble forecasting; Hydrological modelling; Computer science; Environmental science; Meteorology; Climatology; Artificial intelligence; Geology; Geography; Cartography; Drainage basin","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":[0.001587174,0.000283904,0.0003551624,0.00007904913,0.002247426,0.000189341,0.0005431509,0.0002050272,0.0001953826],"category_scores_gemma":[0.0002231317,0.0001937678,0.00009388001,0.0003836805,0.001511153,0.0005744595,0.0009659642,0.000733592,0.0000221728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009264611,"about_ca_system_score_gemma":0.00001128673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000441801,"about_ca_topic_score_gemma":0.00003380567,"domain_scores_codex":[0.9973966,0.0002402356,0.0004139552,0.0006860571,0.0003804121,0.0008827236],"domain_scores_gemma":[0.9993272,0.0001859332,0.0001448699,0.0001143939,0.000012998,0.000214557],"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":[0.0001092657,0.0002807918,0.1054536,0.000009138086,0.00005724115,0.00006840804,0.0003626411,0.8582479,0.005597293,0.0006672817,0.001118316,0.02802813],"study_design_scores_gemma":[0.0007569342,0.0004192722,0.002114869,0.000009752936,0.00003888909,0.00004595927,0.0001226083,0.9801661,0.0001164976,0.01556543,0.0004171005,0.0002265349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7914209,0.0003292297,0.201648,0.001389174,0.0001105633,0.0001528695,0.000002649506,0.00007695465,0.004869683],"genre_scores_gemma":[0.9938181,0.0003114999,0.00450451,0.0009520755,0.00001697256,0.00001615067,0.000004775905,0.000005614374,0.000370281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2023973,"threshold_uncertainty_score":0.9990515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02185508809850389,"score_gpt":0.2479322780236818,"score_spread":0.2260771899251779,"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."}}