{"id":"W4388728270","doi":"10.3390/w15223982","title":"Flood Forecasting Using Hybrid LSTM and GRU Models with Lag Time Preprocessing","year":2023,"lang":"en","type":"article","venue":"Water","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakes Environmental (Canada); University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mean squared error; Deep learning; Flood myth; Computer science; Artificial intelligence; Convolutional neural network; Recurrent neural network; Machine learning; Flood forecasting; Data pre-processing; Artificial neural network; Lag; Data mining; Statistics; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001695526,0.00009574595,0.00008021146,0.0000305547,0.0001592789,0.00007822862,0.00007345924,0.00001428616,0.0001994814],"category_scores_gemma":[0.000001209936,0.00006038712,0.00001264143,0.00008432521,0.00005032054,0.0004278044,0.0002924958,0.00004247323,0.0002329102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000276019,"about_ca_system_score_gemma":0.000002256683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001183075,"about_ca_topic_score_gemma":0.00002068386,"domain_scores_codex":[0.9991975,0.00001179464,0.00008678698,0.0002579642,0.000170805,0.0002751712],"domain_scores_gemma":[0.9998147,0.000005623845,0.00001996865,0.0001146003,0.00000275371,0.00004233857],"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":[0.0001349018,0.0001767464,0.08785605,0.0003115324,0.0001900424,0.0005186351,0.008051644,0.6969605,0.1473348,0.0001234857,0.008748206,0.04959345],"study_design_scores_gemma":[0.0003577099,0.0000449636,0.001532362,0.00004115442,0.00003971668,0.00001810813,0.00008315096,0.9831968,0.01123276,0.001974547,0.001255436,0.0002232705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869657,0.00000669966,0.001746812,0.0001035447,0.00002141563,0.0001349951,0.000001157528,0.00009025018,0.01092942],"genre_scores_gemma":[0.9921948,0.000003846434,0.004294355,0.00005531318,0.00002118193,0.00000811203,0.000008276865,0.00001784725,0.003396209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2862363,"threshold_uncertainty_score":0.2993667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02617324649336886,"score_gpt":0.2096036202611604,"score_spread":0.1834303737677916,"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."}}