{"id":"W4399689732","doi":"10.5194/hess-2024-169","title":"A diversity centric strategy for the selection of spatio-temporal training data for LSTM-based streamflow forecasting","year":2024,"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":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Training (meteorology); Resampling; Undersampling; Computer science; Machine learning; Diversity (politics); Streamflow; Selection (genetic algorithm); Representation (politics); Cluster analysis; Artificial intelligence; Artificial neural network; Data mining; Geography; Drainage basin; Cartography; Meteorology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003306452,0.0007030676,0.0006863748,0.0009732391,0.000647369,0.0007327669,0.001269567,0.0010484,0.001022754],"category_scores_gemma":[0.008492066,0.0004293284,0.0008083886,0.0009437118,0.0008547108,0.001154225,0.001741694,0.001460648,0.0003640943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006674146,"about_ca_system_score_gemma":0.001039563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003199398,"about_ca_topic_score_gemma":0.005550233,"domain_scores_codex":[0.9990097,0.0004739569,0.00006877665,0.0001970923,0.0001595665,0.00009079705],"domain_scores_gemma":[0.9969503,0.001543015,0.0001874062,0.0004237416,0.0006920694,0.0002034585],"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":[0.0009114175,0.0003597921,0.009913987,0.00009691026,0.0002774169,0.0002878208,0.0003609551,0.6649402,0.02942223,0.008496217,0.004694617,0.2802384],"study_design_scores_gemma":[0.00002052512,0.00005065566,0.0005625482,0.000009124277,0.00001478186,0.00002220006,0.00002585166,0.9934001,0.003368385,0.002176946,0.0003425076,0.000006397069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1379687,0.0002629799,0.8589182,0.0004293763,0.00006871056,0.00009423784,0.0001885432,0.0006243455,0.001444794],"genre_scores_gemma":[0.8318865,0.0001021518,0.1655663,0.0003105061,0.00009628337,0.0002018349,0.0007895097,0.00009854938,0.0009483137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003306452,"threshold_uncertainty_score":0.01748639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1357390177983606,"score_gpt":0.2852989144413967,"score_spread":0.149559896643036,"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."}}