{"id":"W3175382161","doi":"","title":"Regional hydrological modelling with deep convolutional-recurrent neural networks: A case study in Western Canada","year":2020,"lang":"en","type":"article","venue":"AGU Fall Meeting 2020","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convolutional neural network; Geography; Artificial intelligence; Computer science","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001877668,0.0001817241,0.0002100119,0.00001179134,0.0001950436,0.00001423636,0.0001757199,0.00003820544,0.00002152537],"category_scores_gemma":[0.00001241538,0.0001451984,0.00002449517,0.0001998541,0.0001131236,0.00007948024,0.0002961692,0.0002565185,0.00001424142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001027183,"about_ca_system_score_gemma":0.00001158838,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3610041,"about_ca_topic_score_gemma":0.8565629,"domain_scores_codex":[0.9984992,0.0001506945,0.0002382404,0.0004786798,0.0002676655,0.0003655274],"domain_scores_gemma":[0.9996075,0.00009190182,0.00007077647,0.0001023321,0.000005593581,0.0001219084],"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":[0.00004437457,0.00004299192,0.4791333,0.000002543284,0.00001765444,0.002633429,0.0006768694,0.5170285,4.199065e-7,0.000002011277,0.0003658092,0.00005207017],"study_design_scores_gemma":[0.0007272901,0.0003092516,0.02400306,0.000008848094,0.0000346939,0.0001146124,0.001317507,0.9722895,2.226605e-7,0.00001054215,0.0009578439,0.0002266303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935788,0.00008755333,0.001396007,0.004244533,0.00005988841,0.0003230243,9.363675e-7,0.00003545601,0.000273797],"genre_scores_gemma":[0.9972621,0.00001073428,0.00019053,0.002394125,0.00006810451,0.00004025096,0.000005187981,0.000009891726,0.00001905574],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4955588,"threshold_uncertainty_score":0.643251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02652545876739772,"score_gpt":0.2191288647992566,"score_spread":0.1926034060318589,"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."}}