{"id":"W6977756599","doi":"10.6084/m9.figshare.28485792","title":"Improving multi-model ensemble streamflow forecasts by combining lumped, distributed and deep learning hydrological models","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Streamflow; Artificial neural network; Deep learning; Hydrological modelling; Flood forecasting; Stream flow; Ensemble forecasting","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009586479,0.0005912615,0.0004584997,0.0006131878,0.0002440268,0.0007458577,0.0006832773,0.0004118047,0.0009953333],"category_scores_gemma":[0.002334749,0.0002476264,0.0004398817,0.0006145897,0.000196499,0.001719553,0.0008118686,0.0008009891,0.0001921932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008655026,"about_ca_system_score_gemma":0.001002909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03110293,"about_ca_topic_score_gemma":0.04743278,"domain_scores_codex":[0.9998395,0.00003876526,0.00001105084,0.00004978114,0.00003582145,0.00002491894],"domain_scores_gemma":[0.999536,0.0002098335,0.00004675848,0.00006052832,0.0001169162,0.00002997821],"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":[0.00008521425,0.00009188505,0.005357677,0.00003010068,0.0001247724,0.00002599926,0.00003936404,0.88911,0.002569738,0.0009266637,0.0008388332,0.1007997],"study_design_scores_gemma":[0.00000461246,0.000009150194,0.0005211509,0.000001777631,0.000007945521,0.000002103361,0.000004800556,0.9985417,0.0003947356,0.0003932055,0.0001157997,0.000002940842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5257799,0.0006364695,0.462787,0.0009213745,0.0001598442,0.00006229272,0.0007424785,0.003078697,0.005831969],"genre_scores_gemma":[0.9547931,0.0001096963,0.04367237,0.0000793579,0.00002712707,0.00002135498,0.0003566513,0.00003797473,0.0009023966],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03110293,"threshold_uncertainty_score":0.06184375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02939878325667841,"score_gpt":0.2427876764815095,"score_spread":0.2133888932248311,"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."}}