{"id":"W4388298017","doi":"10.5194/hess-2023-237","title":"Enhancing LSTM-based streamflow prediction with a spatially distributed approach","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Power Generation; University of Waterloo","funders":"Environment and Climate Change Canada","keywords":"Streamflow; Routing (electronic design automation); Structural basin; Drainage basin; Computer science; Feature (linguistics); Flow routing; Hydrology (agriculture); Climatology; Environmental science; Artificial intelligence; Geology; Geomorphology; Cartography; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004316002,0.0005372244,0.000385827,0.0003892163,0.0001588689,0.0004092966,0.0007018864,0.0004750481,0.0007863569],"category_scores_gemma":[0.001049615,0.0002452932,0.0004588646,0.0005414067,0.0003081726,0.001149461,0.0006025899,0.0005465676,0.0002049404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006481925,"about_ca_system_score_gemma":0.0006571643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01054213,"about_ca_topic_score_gemma":0.0151137,"domain_scores_codex":[0.9998815,0.00002952854,0.000008318065,0.00004436392,0.00002178613,0.00001448124],"domain_scores_gemma":[0.9997665,0.00009121407,0.00003268772,0.00003444181,0.00006341001,0.0000117099],"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":[0.00005953584,0.00005520519,0.00142469,0.00002578385,0.00005205005,0.00005421596,0.00003861021,0.9154658,0.008857365,0.001005448,0.0006683646,0.07229298],"study_design_scores_gemma":[0.000001793078,0.000005125844,0.0001315226,8.466977e-7,0.000002986143,0.000002448847,0.000001735949,0.9989649,0.0005617792,0.0002703267,0.00005529169,0.000001126992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3208162,0.0004877236,0.6722444,0.0005134962,0.0001447598,0.0000377773,0.0002787032,0.002896355,0.002580564],"genre_scores_gemma":[0.9547011,0.00009195026,0.04390417,0.0001152533,0.00003320852,0.00002408996,0.0001641875,0.0000383351,0.0009277313],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01054213,"threshold_uncertainty_score":0.02096152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01471432389118848,"score_gpt":0.2073073834249119,"score_spread":0.1925930595337234,"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."}}