{"id":"W3124254264","doi":"10.1002/hyp.14064","title":"Machine learning for accelerating <scp>2D</scp> flood models: Potential and challenges","year":2021,"lang":"en","type":"article","venue":"Hydrological Processes","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Australian Research Council","keywords":"Computer science; Generalization; Artificial neural network; Momentum (technical analysis); Applied mathematics; Mathematical optimization; Flow (mathematics); Algorithm; Artificial intelligence; Machine learning; Mathematics; Mathematical analysis; Geometry","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000228426,0.0001754035,0.0001964043,0.00001884873,0.0003154983,0.00009753655,0.000155265,0.00009196084,0.0001532523],"category_scores_gemma":[0.0003056903,0.000138845,0.00004292472,0.0001264224,0.00009162756,0.0003173359,0.000426047,0.0001601451,0.00001974983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001826131,"about_ca_system_score_gemma":0.00001193225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001928148,"about_ca_topic_score_gemma":0.00009207623,"domain_scores_codex":[0.9986621,0.00005396782,0.0001807717,0.0005260179,0.0002234659,0.0003536664],"domain_scores_gemma":[0.9995384,0.0001694751,0.0000737732,0.0001068035,0.0000215144,0.00009006362],"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":[0.00009885414,0.002193056,0.01934738,0.002603192,0.0003367956,0.0003671231,0.004470454,0.7593866,0.01314359,0.01178665,0.002303862,0.1839625],"study_design_scores_gemma":[0.001800855,0.0009003606,0.003495994,0.00004204256,0.0001691503,0.00004724164,0.00163032,0.8594179,0.00390471,0.04258849,0.08564149,0.0003615224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9006333,0.02348308,0.02591245,0.002621275,0.0001472956,0.0006699764,0.000007571603,0.0003496541,0.04617536],"genre_scores_gemma":[0.9833412,0.009362011,0.005896546,0.0002688949,0.00007590269,0.00008971808,0.00002362996,0.00001553677,0.0009266262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.183601,"threshold_uncertainty_score":0.5661934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04976052508597557,"score_gpt":0.2429517877524307,"score_spread":0.1931912626664551,"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."}}