{"id":"W4392604747","doi":"10.5194/egusphere-egu24-12293","title":"Towards improved spatio-temporal selection of training data for LSTM-based flow forecasting models in Canadian basins","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Training (meteorology); Selection (genetic algorithm); Computer science; Artificial intelligence; Flow (mathematics); Machine learning; Training set; Geography; Meteorology; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001158457,0.0003063154,0.0004566942,0.0007058536,0.00002896483,0.00008115526,0.0003859089,0.0003639459,0.00003021606],"category_scores_gemma":[0.0002427453,0.0003365944,0.0001083863,0.0003174253,0.0000104653,0.0001191506,0.000128306,0.0005810897,4.262945e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004008085,"about_ca_system_score_gemma":0.0009891249,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06720766,"about_ca_topic_score_gemma":0.3528524,"domain_scores_codex":[0.9983167,0.00003546998,0.0005891144,0.0004513241,0.0001495415,0.0004578387],"domain_scores_gemma":[0.9989962,0.0001377879,0.00005087258,0.0005449122,0.00009854759,0.0001716665],"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":[0.00000937213,0.000003996755,0.00006779018,0.001334944,0.00004812074,0.000001429185,0.0002462276,0.9845204,0.00005286493,0.00008468911,0.0001413377,0.01348878],"study_design_scores_gemma":[0.0003325696,0.00001838163,0.0000309598,0.000310276,0.00003066574,8.667614e-7,0.00002990088,0.9957086,0.0003859286,0.001952077,0.0008882305,0.0003115393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04668278,0.0001433652,0.9480223,0.00007935629,0.0009237092,0.0006956994,0.00129209,0.0003579445,0.001802764],"genre_scores_gemma":[0.6223233,0.000003293277,0.3761305,0.000005940721,0.0001140629,0.00006691722,0.001234655,0.00007683528,0.00004449136],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5756406,"threshold_uncertainty_score":0.9999086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1258903144288686,"score_gpt":0.3149873680882399,"score_spread":0.1890970536593714,"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."}}