{"id":"W4285394443","doi":"10.1007/s00521-022-07523-8","title":"Streamflow modelling and forecasting for Canadian watersheds using LSTM networks with attention mechanism","year":2022,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; McGill University; Ontario Power Generation; National Research Council Canada","funders":"National Research Council Canada","keywords":"Streamflow; Benchmark (surveying); Computer science; Hydrograph; Flood forecasting; Watershed; Artificial neural network; Machine learning; Sequence (biology); Artificial intelligence; Deep learning; Flood myth; Drainage basin; Cartography; Geography","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":[0.0001369294,0.00007172945,0.00006895615,0.00002740951,0.001821776,0.00002230607,0.00005189047,0.00001480206,0.000006138278],"category_scores_gemma":[7.269222e-7,0.00006566057,0.00001182962,0.0000820639,0.00004923787,0.00004111863,0.0001363304,0.00007592123,2.875404e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003870904,"about_ca_system_score_gemma":0.000002185619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004333956,"about_ca_topic_score_gemma":0.001192578,"domain_scores_codex":[0.9994278,0.00001830909,0.00008377727,0.0002187097,0.00005047852,0.0002009378],"domain_scores_gemma":[0.9998153,0.00002984134,0.00003897232,0.00006007369,0.000003732059,0.00005201388],"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":[0.000004840676,0.000005571762,0.01042488,0.000005274806,0.000008313251,5.781445e-7,0.000104579,0.9840124,0.00006278926,0.0005439614,0.00001384693,0.004812948],"study_design_scores_gemma":[0.0001413204,0.00003845128,0.0007604492,0.000002436232,0.00002240565,0.00001099099,0.0001586048,0.997489,0.000005622855,0.000786462,0.0005010291,0.00008322085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6883716,0.00001521977,0.3108827,0.0002533103,0.00001733415,0.0002900144,0.000003619105,0.0000200263,0.0001461049],"genre_scores_gemma":[0.9941577,0.000002788485,0.00549772,0.0001832003,0.00002956145,0.00006521629,0.00001485044,0.000007586502,0.00004139241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3057861,"threshold_uncertainty_score":0.9994777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02577790985075582,"score_gpt":0.2169534982632517,"score_spread":0.1911755884124959,"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."}}