{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001346555,0.0002580562,0.0002557431,0.00003189314,0.000409182,0.0001037576,0.000282515,0.0002389496,0.007665498],"category_scores_gemma":[0.001103905,0.0002318035,0.00006447688,0.000240541,0.00005755975,0.0002483857,0.0007676994,0.0004663412,0.0002154085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000126076,"about_ca_system_score_gemma":0.00001191905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005763948,"about_ca_topic_score_gemma":0.000030512,"domain_scores_codex":[0.9982611,0.0000802689,0.0002600435,0.0006295027,0.0002120084,0.0005570537],"domain_scores_gemma":[0.9993398,0.0001926779,0.00008522657,0.0002026067,0.00001575933,0.000163944],"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":[0.00003835783,0.0001564902,0.001377337,0.00006741814,0.00002029408,0.0000261281,0.0002029408,0.8856402,0.00687521,0.00001386504,0.01947751,0.08610427],"study_design_scores_gemma":[0.0004904204,0.00007729859,0.0002157442,0.0001511329,0.00001199911,0.000006867095,0.000011372,0.9959859,0.000548525,0.0004133166,0.001845926,0.0002415292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9271837,0.0004564888,0.04131654,0.0002639651,0.00008302701,0.0007981224,0.02128038,0.0008809182,0.007736878],"genre_scores_gemma":[0.9861369,0.000002947223,0.002781035,0.0002667578,0.000008427476,0.00007610515,0.01027269,0.00001992825,0.0004352641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1103457,"threshold_uncertainty_score":0.9932416,"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."}}