{"id":"W4322007492","doi":"10.5194/egusphere-egu23-9114","title":"Cluster-based hyperparameter optimisation for LSTM-based flow forecasting in Canadian catchments","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Hyperparameter; Cluster analysis; Hyperparameter optimization; Computer science; Machine learning; Artificial intelligence; Heuristic; Grid; Data mining; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001006713,0.0009459377,0.0005907155,0.0009694531,0.0008444565,0.0008145692,0.001451406,0.0009179037,0.00117656],"category_scores_gemma":[0.003489972,0.0004165141,0.0006356494,0.001294872,0.0006644659,0.0007268657,0.0005661732,0.001010057,0.0001645974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005593939,"about_ca_system_score_gemma":0.004907189,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6258981,"about_ca_topic_score_gemma":0.5851293,"domain_scores_codex":[0.9998,0.00003995808,0.00001180098,0.00006355066,0.00002964028,0.000054979],"domain_scores_gemma":[0.9993984,0.0003032294,0.00004302459,0.00003294333,0.0001852464,0.00003720394],"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":[0.00004855207,0.00001722664,0.002093804,0.00001525253,0.0000195861,0.00001907871,0.00004538608,0.9776217,0.0006711723,0.0003499231,0.0006807078,0.01841772],"study_design_scores_gemma":[0.000003515424,0.000002544735,0.0007130554,0.000001535586,0.000002041173,0.000001484889,0.00001383605,0.9987088,0.0002260882,0.000219675,0.0001041629,0.000003224882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8082381,0.0005920506,0.1816534,0.0008210688,0.00005826135,0.0001686776,0.001756692,0.002708522,0.00400319],"genre_scores_gemma":[0.9596177,0.00008023351,0.03775756,0.00007793686,0.00001242476,0.00007542662,0.00128812,0.0001066341,0.0009839883],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3741019,"threshold_uncertainty_score":0.7526101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05801462099735478,"score_gpt":0.2656626915228565,"score_spread":0.2076480705255018,"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."}}